Complete transcript of AI assistance in creating Week 11 Networking & Communications documentation page
Full Conversation
UserUnknown
general guidelines:
— for each image or video add a caption and description.
— make all the text professional and succinct without losing key details
— make the information as organized and as aesthetically pleasing as possible
— don't just take my notes from the prompt, refine it before putting it on the page
tasks:
1. make a copy of week8.html and called it week11.html. make sure its linked on index.html. populate the relevant resources from
https://academy.cba.mit.edu/classes/networking_communications/index.html
2. create recitation card with a placeholder
5. make individual and group assignment sections based on the assignment descriptions:
group assignment: send a message between two projects
individual assignment:
design, build, and connect wired or wireless node(s)
with network or bus addresses and local input &/or
output device(s)
6. for the group assignment section, just keep placeholders according to both assignment descriptions and ill get to it in the morning in this same chat
7. for the individual assignment, summarize
a) 'CircleSquareShapeSongSwingalong' section and 'CircleSquareShapeSongSwingalong Arduino Code
' in week2.html, with clear hyperlinks to: https://fab.cba.mit.edu/classes/863.25/people/SaleemAldajani/week2.html#nintendo-training and https://fab.cba.mit.edu/classes/863.25/people/SaleemAldajani/week2.html#design-files
b) 'Camera Stream Code
' section and 'Camera System Code
' section in week10.html, with clear hyperlinks to: https://fab.cba.mit.edu/classes/863.25/people/SaleemAldajani/week10.html#camera-edge-ai and https://fab.cba.mit.edu/classes/863.25/people/SaleemAldajani/week10.html#design-files-camera
make sure to address everything in the assignment description:
individual assignment:
design, build, and connect wired or wireless node(s)
with network or bus addresses and local input &/or
output device(s)
show the design part, the build part, the connections, the input and output devices, type of network, and make a big table between connected devices and their respective addresses for each along with each of these components for both mac address and ip address through wifi connect
add links to download all the relevant design files when you mention them even if its the same link in week2.html and week10.html again
embed all the relevant images and videos even if they link to the same ones from week2 and week10
AssistantUnknown
Reviewing the relevant files to understand the structure and content.
Searching for the relevant sections in week2.html and week10.html:
Reading the specific sections I need:
Creating week11.html and updating index.html. Starting with week11.html:
Creating week11.html with the required content:
Creating week11.html with the required content. This is a large file, so building it step by step:
Updating week11.html for networking and communications. Making the necessary edits:
Updating week11.html for networking and communications. Making systematic edits:
This week focuses on exploring various output devices and actuators that can be integrated with microcontroller boards. We'll learn about different actuator types, power management, and how to control output devices effectively.
Understanding output device categories and applications
Learning power management and current limiting techniques
Implementing output devices on custom microcontroller boards
This Week's Goals
Explore Output Device Types Learn about LEDs, displays, motors, servos, steppers, speakers, and other actuators
Power Management Understand current limiting, voltage regulation, and power consumption measurement
Implementation Add output devices to microcontroller boards and successfully control them
Assignments
Group Assignment Measure the power consumption of an output device
Individual Assignment Add an output device to a microcontroller board you've designed, and program it to do something
Tools & Materials
Microcontroller Boards
Output Devices (LEDs, displays, motors)
Power Supply
Joulescope Energy Analyzer
Multimeter
Training Documentation
Training materials and documentation for output devices and multi-axis machining.
Multi-Axis Machining
How to multi-axis mill (almost) anything. Understanding the capabilities and limitations of 3-axis and 5-axis machining for complex part fabrication.
Human fabrication techniques are inherently more 5-axis than 3-axis—consider using a Dremel to carve a pumpkin. Additional axes are decreasing in cost, making 5-axis machining increasingly accessible. Modern 5-axis machines (e.g., UMC series) now cost around $100k USD, similar to robotic arms with 3–6 degrees of freedom.
3-Axis Machining
3-axis machining removes material through shearing. The load is applied to a bending beam from spindle to tool, where the rake angle determines tool sharpness and cutting efficiency.
Feed (inches per tooth, IPT) and surface speed (SFM) determine the processing window, balancing:
Tool breakage (high feed) — above maximum force
Overheating (high feed/high speed) — above maximum heat load
Buildup/edge formation (low speed) — material adhesion
Workholding options include clamping, vacuum, adhesives, electrostatic, and magnetic methods. Roughing removes material quickly (can take up to 3 hours), limited by moving the part relative to the machine. Parts need to cool, and thermal expansion must be accounted for. The most accurate approach uses the largest tool that fits, not the smallest. Endmill entry is not flat (helical entry into material), and extra stock is used to account for beam bending of the endmill.
Roughing strategies use adaptive/pocket clearing with simulated stepdowns to balance time vs. inconsistencies. Maximum roughing time should be limited to ~30 minutes before moving on. Surfacing creates surface finishes using toolpath options: steep/shallow, scallop, or contour (you can bound the tool to specific areas in Fusion 360). Larger endmills are faster for surfacing operations.
Multi-Axis (5-Axis) Machining
5-axis machining enables reaching and positioning tools, repositioning workpieces for time and accuracy (without manual intervention), and improved surface finishing. The system is always limited by contact at every point in space.
There are two main approaches:
3+2 machining — repositioning then 3-axis cutting
Simultaneous 5-axis — moving more than 3 axes at once, including advanced swarf, multi-axis contour (perpendicular to surface), or multi-axis finishing with ball mills or circle-shaped end mills
Limitations include CAM software processing speed (single-threaded operations), complexity of simulating tool movement relative to workholding and part interference, and managing remaining stock (Fusion 360) or rest material (Mastercam).
Understanding machine kinematics is critical—see the MAS.865 mechanical design resources for detailed analysis of how machines move in space.
Flexibility
With 5-axis capability, the distinction between mills and lathes becomes blurred. Mills hold the workpiece while the tool spins; lathes hold the tool stationary while spinning the workpiece. This flexibility reduces design limitations. Think of systems in terms of three components: the tool, workholding, and axes.
Axes: different spindle configurations, different head designs
Summary
3-axis and 5-axis machining each have their place. The key is understanding which to use when, and how 5-axis capability breaks down barriers between traditional tool classifications, enabling more flexible and creative fabrication approaches.
Useful Documentation
Essential resources for output devices and actuator integration.
Comprehensive resource covering all output device categories including LEDs, displays (LCD, OLED, TFT), motors (DC, stepper, servo, brushless), speakers, solenoids, and more. Includes detailed tutorials, code examples, and implementation guides for various output device types.
Group Assignment: Measuring Power Consumption of Output Devices
Measuring power consumption of motors, servos, and stepper motors using adjustable power supplies and precision energy analyzers to understand performance characteristics and when to use each type.
Measurement Setup
We used an adjustable power supply set to 15V and measured quiescent power consumption of 450 mW (0.03 A, where P=IV) before connecting any motors. Power measurements were conducted using the Joulescope (JS220) Precision Energy Analyzer to measure current, voltage, power, charge, and energy in real-time.
Power supply set to 15V for motor testing
Joulescope JS220 Precision Energy Analyzer
Joulescope software interface
Using a potentiometer to change motor speed, we observed that below a certain threshold, the motor doesn't have enough power to spin (no mechanical work, just electrical losses). Above this threshold, speed increases with power. The dI/dt (rate of current change) cannot change instantly—it takes time. The PWM signal from the microcontroller (roughly 50% duty cycle) is smoothed after passing through the motor driver, with more linear behavior on the rising edge than the falling edge.
Motor circuit connections
Complete motor testing setup
50% duty cycle PWM from microcontroller
Smoothed PWM signal after motor driver
Zoomed-in power measurement
Zoomed-out power measurement
Motor Comparison Results
All motors tested at 15V supply, 2A current limit, with the same potentiometer value for comparison. The potentiometer determines speed and power for DC motors, and position for servos.
DC Motors (Voltage-Controlled)
DC Brushed Motor (Large)
Characteristics: Low-speed, high torque, no positional control
Current: 57 mA
Voltage: 14.49 V
Power: 0.8 W
Large DC brushed motor measurement
DC Brushed Motor (Small)
Characteristics: High speed, medium torque, no positional control
Current: 0.34 A
Voltage: 14.47 V
Power: 4.86 W
Small DC brushed motor measurement and operation
DC Stepper Motor (Current-Controlled)
Characteristics: Medium speed, medium torque, zero absolute positional control (relative positioning only)
Current: 2.0 A
Voltage: 10.93 V
Power: 22.33 W
Stepper motor measurement and operation
Servo Motors (5V Supply, Position-Controlled)
All servos tested at 5V supply, 2A current limit. Potentiometer determines position; power consumption remains relatively constant.
Characteristics: Absolute positional control, slower response, lower power
Current: 5.04 mA
Voltage: 4.99 V
Power: 25.05 mW
Micro servo motor measurement
Motor Comparison Summary Tables
Constant Voltage Comparison (15V Supply, 2A Current Limit)
DC brushed and stepper motors tested at 15V. Potentiometer controls speed for brushed motors, and step rate for stepper motor.
Motor Type
Size
Current
Voltage
Power
Characteristics
DC Brushed
Large
57 mA
14.49 V
0.8 W
Low-speed, high torque, no positional control
DC Brushed
Small
0.34 A
14.47 V
4.86 W
High speed, medium torque, no positional control
Stepper
N/A
2.0 A
10.93 V
22.33 W
Medium speed, medium torque, relative positioning only
Constant Current Comparison (5V Supply, 2A Current Limit)
Servo motors tested at 5V. Potentiometer controls position; power consumption remains relatively constant regardless of position.
Motor Type
Size
Current
Voltage
Power
Characteristics
Servo
Large
10.6 mA
4.99 V
53.4 mW
Absolute positional control, slower response
Servo
Micro
5.04 mA
4.99 V
25.05 mW
Absolute positional control, slower response, lower power
Summary: When to Use Each Motor Type
DC Brushed Motors: Simple applications requiring variable speed and torque, where positional control is not needed
Stepper Motors: Applications requiring precise relative positioning with medium power consumption
Servo Motors: Applications requiring absolute positional control with low power consumption, especially in battery-powered systems
Individual Assignment: Output Devices
Adding simple and complex output devices to the custom development board designed in Week 4, including a bright LED and OLED display for sensor visualization.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on exploring various output devices and actuators that can be integrated with microcontroller boards. We'll learn about different actuator types, power management, and how to control output devices effectively.
Understanding output device categories and applications
Learning power management and current limiting techniques
Implementing output devices on custom microcontroller boards
This Week's Goals
Explore Output Device Types Learn about LEDs, displays, motors, servos, steppers, speakers, and other actuators
Power Management Understand current limiting, voltage regulation, and power consumption measurement
Implementation Add output devices to microcontroller boards and successfully control them
Assignments
Group Assignment Measure the power consumption of an output device
Individual Assignment Add an output device to a microcontroller board you've designed, and program it to do something
Tools & Materials
Microcontroller Boards
Output Devices (LEDs, displays, motors)
Power Supply
Joulescope Energy Analyzer
Multimeter
Training Documentation
Training materials and documentation for output devices and multi-axis machining.
Multi-Axis Machining
How to multi-axis mill (almost) anything. Understanding the capabilities and limitations of 3-axis and 5-axis machining for complex part fabrication.
Human fabrication techniques are inherently more 5-axis than 3-axis—consider using a Dremel to carve a pumpkin. Additional axes are decreasing in cost, making 5-axis machining increasingly accessible. Modern 5-axis machines (e.g., UMC series) now cost around $100k USD, similar to robotic arms with 3–6 degrees of freedom.
3-Axis Machining
3-axis machining removes material through shearing. The load is applied to a bending beam from spindle to tool, where the rake angle determines tool sharpness and cutting efficiency.
Feed (inches per tooth, IPT) and surface speed (SFM) determine the processing window, balancing:
Tool breakage (high feed) — above maximum force
Overheating (high feed/high speed) — above maximum heat load
Buildup/edge formation (low speed) — material adhesion
Workholding options include clamping, vacuum, adhesives, electrostatic, and magnetic methods. Roughing removes material quickly (can take up to 3 hours), limited by moving the part relative to the machine. Parts need to cool, and thermal expansion must be accounted for. The most accurate approach uses the largest tool that fits, not the smallest. Endmill entry is not flat (helical entry into material), and extra stock is used to account for beam bending of the endmill.
Roughing strategies use adaptive/pocket clearing with simulated stepdowns to balance time vs. inconsistencies. Maximum roughing time should be limited to ~30 minutes before moving on. Surfacing creates surface finishes using toolpath options: steep/shallow, scallop, or contour (you can bound the tool to specific areas in Fusion 360). Larger endmills are faster for surfacing operations.
Multi-Axis (5-Axis) Machining
5-axis machining enables reaching and positioning tools, repositioning workpieces for time and accuracy (without manual intervention), and improved surface finishing. The system is always limited by contact at every point in space.
There are two main approaches:
3+2 machining — repositioning then 3-axis cutting
Simultaneous 5-axis — moving more than 3 axes at once, including advanced swarf, multi-axis contour (perpendicular to surface), or multi-axis finishing with ball mills or circle-shaped end mills
Limitations include CAM software processing speed (single-threaded operations), complexity of simulating tool movement relative to workholding and part interference, and managing remaining stock (Fusion 360) or rest material (Mastercam).
Understanding machine kinematics is critical—see the MAS.865 mechanical design resources for detailed analysis of how machines move in space.
Flexibility
With 5-axis capability, the distinction between mills and lathes becomes blurred. Mills hold the workpiece while the tool spins; lathes hold the tool stationary while spinning the workpiece. This flexibility reduces design limitations. Think of systems in terms of three components: the tool, workholding, and axes.
Axes: different spindle configurations, different head designs
Summary
3-axis and 5-axis machining each have their place. The key is understanding which to use when, and how 5-axis capability breaks down barriers between traditional tool classifications, enabling more flexible and creative fabrication approaches.
Useful Documentation
Essential resources for output devices and actuator integration.
Comprehensive resource covering all output device categories including LEDs, displays (LCD, OLED, TFT), motors (DC, stepper, servo, brushless), speakers, solenoids, and more. Includes detailed tutorials, code examples, and implementation guides for various output device types.
Group Assignment: Measuring Power Consumption of Output Devices
Measuring power consumption of motors, servos, and stepper motors using adjustable power supplies and precision energy analyzers to understand performance characteristics and when to use each type.
Measurement Setup
We used an adjustable power supply set to 15V and measured quiescent power consumption of 450 mW (0.03 A, where P=IV) before connecting any motors. Power measurements were conducted using the Joulescope (JS220) Precision Energy Analyzer to measure current, voltage, power, charge, and energy in real-time.
Power supply set to 15V for motor testing
Joulescope JS220 Precision Energy Analyzer
Joulescope software interface
Using a potentiometer to change motor speed, we observed that below a certain threshold, the motor doesn't have enough power to spin (no mechanical work, just electrical losses). Above this threshold, speed increases with power. The dI/dt (rate of current change) cannot change instantly—it takes time. The PWM signal from the microcontroller (roughly 50% duty cycle) is smoothed after passing through the motor driver, with more linear behavior on the rising edge than the falling edge.
Motor circuit connections
Complete motor testing setup
50% duty cycle PWM from microcontroller
Smoothed PWM signal after motor driver
Zoomed-in power measurement
Zoomed-out power measurement
Motor Comparison Results
All motors tested at 15V supply, 2A current limit, with the same potentiometer value for comparison. The potentiometer determines speed and power for DC motors, and position for servos.
DC Motors (Voltage-Controlled)
DC Brushed Motor (Large)
Characteristics: Low-speed, high torque, no positional control
Current: 57 mA
Voltage: 14.49 V
Power: 0.8 W
Large DC brushed motor measurement
DC Brushed Motor (Small)
Characteristics: High speed, medium torque, no positional control
Current: 0.34 A
Voltage: 14.47 V
Power: 4.86 W
Small DC brushed motor measurement and operation
DC Stepper Motor (Current-Controlled)
Characteristics: Medium speed, medium torque, zero absolute positional control (relative positioning only)
Current: 2.0 A
Voltage: 10.93 V
Power: 22.33 W
Stepper motor measurement and operation
Servo Motors (5V Supply, Position-Controlled)
All servos tested at 5V supply, 2A current limit. Potentiometer determines position; power consumption remains relatively constant.
Characteristics: Absolute positional control, slower response, lower power
Current: 5.04 mA
Voltage: 4.99 V
Power: 25.05 mW
Micro servo motor measurement
Motor Comparison Summary Tables
Constant Voltage Comparison (15V Supply, 2A Current Limit)
DC brushed and stepper motors tested at 15V. Potentiometer controls speed for brushed motors, and step rate for stepper motor.
Motor Type
Size
Current
Voltage
Power
Characteristics
DC Brushed
Large
57 mA
14.49 V
0.8 W
Low-speed, high torque, no positional control
DC Brushed
Small
0.34 A
14.47 V
4.86 W
High speed, medium torque, no positional control
Stepper
N/A
2.0 A
10.93 V
22.33 W
Medium speed, medium torque, relative positioning only
Constant Current Comparison (5V Supply, 2A Current Limit)
Servo motors tested at 5V. Potentiometer controls position; power consumption remains relatively constant regardless of position.
Motor Type
Size
Current
Voltage
Power
Characteristics
Servo
Large
10.6 mA
4.99 V
53.4 mW
Absolute positional control, slower response
Servo
Micro
5.04 mA
4.99 V
25.05 mW
Absolute positional control, slower response, lower power
Summary: When to Use Each Motor Type
DC Brushed Motors: Simple applications requiring variable speed and torque, where positional control is not needed
Stepper Motors: Applications requiring precise relative positioning with medium power consumption
Servo Motors: Applications requiring absolute positional control with low power consumption, especially in battery-powered systems
Individual Assignment: Output Devices
Adding simple and complex output devices to the custom development board designed in Week 4, including a bright LED and OLED display for sensor visualization.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on exploring various output devices and actuators that can be integrated with microcontroller boards. We'll learn about different actuator types, power management, and how to control output devices effectively.
Understanding output device categories and applications
Learning power management and current limiting techniques
Implementing output devices on custom microcontroller boards
This Week's Goals
Explore Output Device Types Learn about LEDs, displays, motors, servos, steppers, speakers, and other actuators
Power Management Understand current limiting, voltage regulation, and power consumption measurement
Implementation Add output devices to microcontroller boards and successfully control them
Assignments
Group Assignment Measure the power consumption of an output device
Individual Assignment Add an output device to a microcontroller board you've designed, and program it to do something
Tools & Materials
Microcontroller Boards
Output Devices (LEDs, displays, motors)
Power Supply
Joulescope Energy Analyzer
Multimeter
Training Documentation
Training materials and documentation for output devices and multi-axis machining.
Multi-Axis Machining
How to multi-axis mill (almost) anything. Understanding the capabilities and limitations of 3-axis and 5-axis machining for complex part fabrication.
Human fabrication techniques are inherently more 5-axis than 3-axis—consider using a Dremel to carve a pumpkin. Additional axes are decreasing in cost, making 5-axis machining increasingly accessible. Modern 5-axis machines (e.g., UMC series) now cost around $100k USD, similar to robotic arms with 3–6 degrees of freedom.
3-Axis Machining
3-axis machining removes material through shearing. The load is applied to a bending beam from spindle to tool, where the rake angle determines tool sharpness and cutting efficiency.
Feed (inches per tooth, IPT) and surface speed (SFM) determine the processing window, balancing:
Tool breakage (high feed) — above maximum force
Overheating (high feed/high speed) — above maximum heat load
Buildup/edge formation (low speed) — material adhesion
Workholding options include clamping, vacuum, adhesives, electrostatic, and magnetic methods. Roughing removes material quickly (can take up to 3 hours), limited by moving the part relative to the machine. Parts need to cool, and thermal expansion must be accounted for. The most accurate approach uses the largest tool that fits, not the smallest. Endmill entry is not flat (helical entry into material), and extra stock is used to account for beam bending of the endmill.
Roughing strategies use adaptive/pocket clearing with simulated stepdowns to balance time vs. inconsistencies. Maximum roughing time should be limited to ~30 minutes before moving on. Surfacing creates surface finishes using toolpath options: steep/shallow, scallop, or contour (you can bound the tool to specific areas in Fusion 360). Larger endmills are faster for surfacing operations.
Multi-Axis (5-Axis) Machining
5-axis machining enables reaching and positioning tools, repositioning workpieces for time and accuracy (without manual intervention), and improved surface finishing. The system is always limited by contact at every point in space.
There are two main approaches:
3+2 machining — repositioning then 3-axis cutting
Simultaneous 5-axis — moving more than 3 axes at once, including advanced swarf, multi-axis contour (perpendicular to surface), or multi-axis finishing with ball mills or circle-shaped end mills
Limitations include CAM software processing speed (single-threaded operations), complexity of simulating tool movement relative to workholding and part interference, and managing remaining stock (Fusion 360) or rest material (Mastercam).
Understanding machine kinematics is critical—see the MAS.865 mechanical design resources for detailed analysis of how machines move in space.
Flexibility
With 5-axis capability, the distinction between mills and lathes becomes blurred. Mills hold the workpiece while the tool spins; lathes hold the tool stationary while spinning the workpiece. This flexibility reduces design limitations. Think of systems in terms of three components: the tool, workholding, and axes.
Axes: different spindle configurations, different head designs
Summary
3-axis and 5-axis machining each have their place. The key is understanding which to use when, and how 5-axis capability breaks down barriers between traditional tool classifications, enabling more flexible and creative fabrication approaches.
Useful Documentation
Essential resources for output devices and actuator integration.
Comprehensive resource covering all output device categories including LEDs, displays (LCD, OLED, TFT), motors (DC, stepper, servo, brushless), speakers, solenoids, and more. Includes detailed tutorials, code examples, and implementation guides for various output device types.
Group Assignment: Measuring Power Consumption of Output Devices
Measuring power consumption of motors, servos, and stepper motors using adjustable power supplies and precision energy analyzers to understand performance characteristics and when to use each type.
Measurement Setup
We used an adjustable power supply set to 15V and measured quiescent power consumption of 450 mW (0.03 A, where P=IV) before connecting any motors. Power measurements were conducted using the Joulescope (JS220) Precision Energy Analyzer to measure current, voltage, power, charge, and energy in real-time.
Power supply set to 15V for motor testing
Joulescope JS220 Precision Energy Analyzer
Joulescope software interface
Using a potentiometer to change motor speed, we observed that below a certain threshold, the motor doesn't have enough power to spin (no mechanical work, just electrical losses). Above this threshold, speed increases with power. The dI/dt (rate of current change) cannot change instantly—it takes time. The PWM signal from the microcontroller (roughly 50% duty cycle) is smoothed after passing through the motor driver, with more linear behavior on the rising edge than the falling edge.
Motor circuit connections
Complete motor testing setup
50% duty cycle PWM from microcontroller
Smoothed PWM signal after motor driver
Zoomed-in power measurement
Zoomed-out power measurement
Motor Comparison Results
All motors tested at 15V supply, 2A current limit, with the same potentiometer value for comparison. The potentiometer determines speed and power for DC motors, and position for servos.
DC Motors (Voltage-Controlled)
DC Brushed Motor (Large)
Characteristics: Low-speed, high torque, no positional control
Current: 57 mA
Voltage: 14.49 V
Power: 0.8 W
Large DC brushed motor measurement
DC Brushed Motor (Small)
Characteristics: High speed, medium torque, no positional control
Current: 0.34 A
Voltage: 14.47 V
Power: 4.86 W
Small DC brushed motor measurement and operation
DC Stepper Motor (Current-Controlled)
Characteristics: Medium speed, medium torque, zero absolute positional control (relative positioning only)
Current: 2.0 A
Voltage: 10.93 V
Power: 22.33 W
Stepper motor measurement and operation
Servo Motors (5V Supply, Position-Controlled)
All servos tested at 5V supply, 2A current limit. Potentiometer determines position; power consumption remains relatively constant.
Characteristics: Absolute positional control, slower response, lower power
Current: 5.04 mA
Voltage: 4.99 V
Power: 25.05 mW
Micro servo motor measurement
Motor Comparison Summary Tables
Constant Voltage Comparison (15V Supply, 2A Current Limit)
DC brushed and stepper motors tested at 15V. Potentiometer controls speed for brushed motors, and step rate for stepper motor.
Motor Type
Size
Current
Voltage
Power
Characteristics
DC Brushed
Large
57 mA
14.49 V
0.8 W
Low-speed, high torque, no positional control
DC Brushed
Small
0.34 A
14.47 V
4.86 W
High speed, medium torque, no positional control
Stepper
N/A
2.0 A
10.93 V
22.33 W
Medium speed, medium torque, relative positioning only
Constant Current Comparison (5V Supply, 2A Current Limit)
Servo motors tested at 5V. Potentiometer controls position; power consumption remains relatively constant regardless of position.
Motor Type
Size
Current
Voltage
Power
Characteristics
Servo
Large
10.6 mA
4.99 V
53.4 mW
Absolute positional control, slower response
Servo
Micro
5.04 mA
4.99 V
25.05 mW
Absolute positional control, slower response, lower power
Summary: When to Use Each Motor Type
DC Brushed Motors: Simple applications requiring variable speed and torque, where positional control is not needed
Stepper Motors: Applications requiring precise relative positioning with medium power consumption
Servo Motors: Applications requiring absolute positional control with low power consumption, especially in battery-powered systems
Individual Assignment: Output Devices
Adding simple and complex output devices to the custom development board designed in Week 4, including a bright LED and OLED display for sensor visualization.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Measure the power consumption of an output device
Individual Assignment Add an output device to a microcontroller board you've designed, and program it to do something
Tools & Materials
Microcontroller Boards
Output Devices (LEDs, displays, motors)
Power Supply
Joulescope Energy Analyzer
Multimeter
Training Documentation
Training materials and documentation for output devices and multi-axis machining.
Multi-Axis Machining
How to multi-axis mill (almost) anything. Understanding the capabilities and limitations of 3-axis and 5-axis machining for complex part fabrication.
Human fabrication techniques are inherently more 5-axis than 3-axis—consider using a Dremel to carve a pumpkin. Additional axes are decreasing in cost, making 5-axis machining increasingly accessible. Modern 5-axis machines (e.g., UMC series) now cost around $100k USD, similar to robotic arms with 3–6 degrees of freedom.
3-Axis Machining
3-axis machining removes material through shearing. The load is applied to a bending beam from spindle to tool, where the rake angle determines tool sharpness and cutting efficiency.
Feed (inches per tooth, IPT) and surface speed (SFM) determine the processing window, balancing:
Tool breakage (high feed) — above maximum force
Overheating (high feed/high speed) — above maximum heat load
Buildup/edge formation (low speed) — material adhesion
Workholding options include clamping, vacuum, adhesives, electrostatic, and magnetic methods. Roughing removes material quickly (can take up to 3 hours), limited by moving the part relative to the machine. Parts need to cool, and thermal expansion must be accounted for. The most accurate approach uses the largest tool that fits, not the smallest. Endmill entry is not flat (helical entry into material), and extra stock is used to account for beam bending of the endmill.
Roughing strategies use adaptive/pocket clearing with simulated stepdowns to balance time vs. inconsistencies. Maximum roughing time should be limited to ~30 minutes before moving on. Surfacing creates surface finishes using toolpath options: steep/shallow, scallop, or contour (you can bound the tool to specific areas in Fusion 360). Larger endmills are faster for surfacing operations.
Multi-Axis (5-Axis) Machining
5-axis machining enables reaching and positioning tools, repositioning workpieces for time and accuracy (without manual intervention), and improved surface finishing. The system is always limited by contact at every point in space.
There are two main approaches:
3+2 machining — repositioning then 3-axis cutting
Simultaneous 5-axis — moving more than 3 axes at once, including advanced swarf, multi-axis contour (perpendicular to surface), or multi-axis finishing with ball mills or circle-shaped end mills
Limitations include CAM software processing speed (single-threaded operations), complexity of simulating tool movement relative to workholding and part interference, and managing remaining stock (Fusion 360) or rest material (Mastercam).
Understanding machine kinematics is critical—see the MAS.865 mechanical design resources for detailed analysis of how machines move in space.
Flexibility
With 5-axis capability, the distinction between mills and lathes becomes blurred. Mills hold the workpiece while the tool spins; lathes hold the tool stationary while spinning the workpiece. This flexibility reduces design limitations. Think of systems in terms of three components: the tool, workholding, and axes.
Axes: different spindle configurations, different head designs
Summary
3-axis and 5-axis machining each have their place. The key is understanding which to use when, and how 5-axis capability breaks down barriers between traditional tool classifications, enabling more flexible and creative fabrication approaches.
Useful Documentation
Essential resources for output devices and actuator integration.
Comprehensive resource covering all output device categories including LEDs, displays (LCD, OLED, TFT), motors (DC, stepper, servo, brushless), speakers, solenoids, and more. Includes detailed tutorials, code examples, and implementation guides for various output device types.
Group Assignment: Measuring Power Consumption of Output Devices
Measuring power consumption of motors, servos, and stepper motors using adjustable power supplies and precision energy analyzers to understand performance characteristics and when to use each type.
Measurement Setup
We used an adjustable power supply set to 15V and measured quiescent power consumption of 450 mW (0.03 A, where P=IV) before connecting any motors. Power measurements were conducted using the Joulescope (JS220) Precision Energy Analyzer to measure current, voltage, power, charge, and energy in real-time.
Power supply set to 15V for motor testing
Joulescope JS220 Precision Energy Analyzer
Joulescope software interface
Using a potentiometer to change motor speed, we observed that below a certain threshold, the motor doesn't have enough power to spin (no mechanical work, just electrical losses). Above this threshold, speed increases with power. The dI/dt (rate of current change) cannot change instantly—it takes time. The PWM signal from the microcontroller (roughly 50% duty cycle) is smoothed after passing through the motor driver, with more linear behavior on the rising edge than the falling edge.
Motor circuit connections
Complete motor testing setup
50% duty cycle PWM from microcontroller
Smoothed PWM signal after motor driver
Zoomed-in power measurement
Zoomed-out power measurement
Motor Comparison Results
All motors tested at 15V supply, 2A current limit, with the same potentiometer value for comparison. The potentiometer determines speed and power for DC motors, and position for servos.
DC Motors (Voltage-Controlled)
DC Brushed Motor (Large)
Characteristics: Low-speed, high torque, no positional control
Current: 57 mA
Voltage: 14.49 V
Power: 0.8 W
Large DC brushed motor measurement
DC Brushed Motor (Small)
Characteristics: High speed, medium torque, no positional control
Current: 0.34 A
Voltage: 14.47 V
Power: 4.86 W
Small DC brushed motor measurement and operation
DC Stepper Motor (Current-Controlled)
Characteristics: Medium speed, medium torque, zero absolute positional control (relative positioning only)
Current: 2.0 A
Voltage: 10.93 V
Power: 22.33 W
Stepper motor measurement and operation
Servo Motors (5V Supply, Position-Controlled)
All servos tested at 5V supply, 2A current limit. Potentiometer determines position; power consumption remains relatively constant.
Characteristics: Absolute positional control, slower response, lower power
Current: 5.04 mA
Voltage: 4.99 V
Power: 25.05 mW
Micro servo motor measurement
Motor Comparison Summary Tables
Constant Voltage Comparison (15V Supply, 2A Current Limit)
DC brushed and stepper motors tested at 15V. Potentiometer controls speed for brushed motors, and step rate for stepper motor.
Motor Type
Size
Current
Voltage
Power
Characteristics
DC Brushed
Large
57 mA
14.49 V
0.8 W
Low-speed, high torque, no positional control
DC Brushed
Small
0.34 A
14.47 V
4.86 W
High speed, medium torque, no positional control
Stepper
N/A
2.0 A
10.93 V
22.33 W
Medium speed, medium torque, relative positioning only
Constant Current Comparison (5V Supply, 2A Current Limit)
Servo motors tested at 5V. Potentiometer controls position; power consumption remains relatively constant regardless of position.
Motor Type
Size
Current
Voltage
Power
Characteristics
Servo
Large
10.6 mA
4.99 V
53.4 mW
Absolute positional control, slower response
Servo
Micro
5.04 mA
4.99 V
25.05 mW
Absolute positional control, slower response, lower power
Summary: When to Use Each Motor Type
DC Brushed Motors: Simple applications requiring variable speed and torque, where positional control is not needed
Stepper Motors: Applications requiring precise relative positioning with medium power consumption
Servo Motors: Applications requiring absolute positional control with low power consumption, especially in battery-powered systems
Individual Assignment: Output Devices
Adding simple and complex output devices to the custom development board designed in Week 4, including a bright LED and OLED display for sensor visualization.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for output devices and multi-axis machining.
Multi-Axis Machining
How to multi-axis mill (almost) anything. Understanding the capabilities and limitations of 3-axis and 5-axis machining for complex part fabrication.
Human fabrication techniques are inherently more 5-axis than 3-axis—consider using a Dremel to carve a pumpkin. Additional axes are decreasing in cost, making 5-axis machining increasingly accessible. Modern 5-axis machines (e.g., UMC series) now cost around $100k USD, similar to robotic arms with 3–6 degrees of freedom.
3-Axis Machining
3-axis machining removes material through shearing. The load is applied to a bending beam from spindle to tool, where the rake angle determines tool sharpness and cutting efficiency.
Feed (inches per tooth, IPT) and surface speed (SFM) determine the processing window, balancing:
Tool breakage (high feed) — above maximum force
Overheating (high feed/high speed) — above maximum heat load
Buildup/edge formation (low speed) — material adhesion
Workholding options include clamping, vacuum, adhesives, electrostatic, and magnetic methods. Roughing removes material quickly (can take up to 3 hours), limited by moving the part relative to the machine. Parts need to cool, and thermal expansion must be accounted for. The most accurate approach uses the largest tool that fits, not the smallest. Endmill entry is not flat (helical entry into material), and extra stock is used to account for beam bending of the endmill.
Roughing strategies use adaptive/pocket clearing with simulated stepdowns to balance time vs. inconsistencies. Maximum roughing time should be limited to ~30 minutes before moving on. Surfacing creates surface finishes using toolpath options: steep/shallow, scallop, or contour (you can bound the tool to specific areas in Fusion 360). Larger endmills are faster for surfacing operations.
Multi-Axis (5-Axis) Machining
5-axis machining enables reaching and positioning tools, repositioning workpieces for time and accuracy (without manual intervention), and improved surface finishing. The system is always limited by contact at every point in space.
There are two main approaches:
3+2 machining — repositioning then 3-axis cutting
Simultaneous 5-axis — moving more than 3 axes at once, including advanced swarf, multi-axis contour (perpendicular to surface), or multi-axis finishing with ball mills or circle-shaped end mills
Limitations include CAM software processing speed (single-threaded operations), complexity of simulating tool movement relative to workholding and part interference, and managing remaining stock (Fusion 360) or rest material (Mastercam).
Understanding machine kinematics is critical—see the MAS.865 mechanical design resources for detailed analysis of how machines move in space.
Flexibility
With 5-axis capability, the distinction between mills and lathes becomes blurred. Mills hold the workpiece while the tool spins; lathes hold the tool stationary while spinning the workpiece. This flexibility reduces design limitations. Think of systems in terms of three components: the tool, workholding, and axes.
Axes: different spindle configurations, different head designs
Summary
3-axis and 5-axis machining each have their place. The key is understanding which to use when, and how 5-axis capability breaks down barriers between traditional tool classifications, enabling more flexible and creative fabrication approaches.
Useful Documentation
Essential resources for output devices and actuator integration.
Comprehensive resource covering all output device categories including LEDs, displays (LCD, OLED, TFT), motors (DC, stepper, servo, brushless), speakers, solenoids, and more. Includes detailed tutorials, code examples, and implementation guides for various output device types.
Group Assignment: Measuring Power Consumption of Output Devices
Measuring power consumption of motors, servos, and stepper motors using adjustable power supplies and precision energy analyzers to understand performance characteristics and when to use each type.
Measurement Setup
We used an adjustable power supply set to 15V and measured quiescent power consumption of 450 mW (0.03 A, where P=IV) before connecting any motors. Power measurements were conducted using the Joulescope (JS220) Precision Energy Analyzer to measure current, voltage, power, charge, and energy in real-time.
Power supply set to 15V for motor testing
Joulescope JS220 Precision Energy Analyzer
Joulescope software interface
Using a potentiometer to change motor speed, we observed that below a certain threshold, the motor doesn't have enough power to spin (no mechanical work, just electrical losses). Above this threshold, speed increases with power. The dI/dt (rate of current change) cannot change instantly—it takes time. The PWM signal from the microcontroller (roughly 50% duty cycle) is smoothed after passing through the motor driver, with more linear behavior on the rising edge than the falling edge.
Motor circuit connections
Complete motor testing setup
50% duty cycle PWM from microcontroller
Smoothed PWM signal after motor driver
Zoomed-in power measurement
Zoomed-out power measurement
Motor Comparison Results
All motors tested at 15V supply, 2A current limit, with the same potentiometer value for comparison. The potentiometer determines speed and power for DC motors, and position for servos.
DC Motors (Voltage-Controlled)
DC Brushed Motor (Large)
Characteristics: Low-speed, high torque, no positional control
Current: 57 mA
Voltage: 14.49 V
Power: 0.8 W
Large DC brushed motor measurement
DC Brushed Motor (Small)
Characteristics: High speed, medium torque, no positional control
Current: 0.34 A
Voltage: 14.47 V
Power: 4.86 W
Small DC brushed motor measurement and operation
DC Stepper Motor (Current-Controlled)
Characteristics: Medium speed, medium torque, zero absolute positional control (relative positioning only)
Current: 2.0 A
Voltage: 10.93 V
Power: 22.33 W
Stepper motor measurement and operation
Servo Motors (5V Supply, Position-Controlled)
All servos tested at 5V supply, 2A current limit. Potentiometer determines position; power consumption remains relatively constant.
Characteristics: Absolute positional control, slower response, lower power
Current: 5.04 mA
Voltage: 4.99 V
Power: 25.05 mW
Micro servo motor measurement
Motor Comparison Summary Tables
Constant Voltage Comparison (15V Supply, 2A Current Limit)
DC brushed and stepper motors tested at 15V. Potentiometer controls speed for brushed motors, and step rate for stepper motor.
Motor Type
Size
Current
Voltage
Power
Characteristics
DC Brushed
Large
57 mA
14.49 V
0.8 W
Low-speed, high torque, no positional control
DC Brushed
Small
0.34 A
14.47 V
4.86 W
High speed, medium torque, no positional control
Stepper
N/A
2.0 A
10.93 V
22.33 W
Medium speed, medium torque, relative positioning only
Constant Current Comparison (5V Supply, 2A Current Limit)
Servo motors tested at 5V. Potentiometer controls position; power consumption remains relatively constant regardless of position.
Motor Type
Size
Current
Voltage
Power
Characteristics
Servo
Large
10.6 mA
4.99 V
53.4 mW
Absolute positional control, slower response
Servo
Micro
5.04 mA
4.99 V
25.05 mW
Absolute positional control, slower response, lower power
Summary: When to Use Each Motor Type
DC Brushed Motors: Simple applications requiring variable speed and torque, where positional control is not needed
Stepper Motors: Applications requiring precise relative positioning with medium power consumption
Servo Motors: Applications requiring absolute positional control with low power consumption, especially in battery-powered systems
Individual Assignment: Output Devices
Adding simple and complex output devices to the custom development board designed in Week 4, including a bright LED and OLED display for sensor visualization.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
How to multi-axis mill (almost) anything. Understanding the capabilities and limitations of 3-axis and 5-axis machining for complex part fabrication.
Human fabrication techniques are inherently more 5-axis than 3-axis—consider using a Dremel to carve a pumpkin. Additional axes are decreasing in cost, making 5-axis machining increasingly accessible. Modern 5-axis machines (e.g., UMC series) now cost around $100k USD, similar to robotic arms with 3–6 degrees of freedom.
3-Axis Machining
3-axis machining removes material through shearing. The load is applied to a bending beam from spindle to tool, where the rake angle determines tool sharpness and cutting efficiency.
Feed (inches per tooth, IPT) and surface speed (SFM) determine the processing window, balancing:
Tool breakage (high feed) — above maximum force
Overheating (high feed/high speed) — above maximum heat load
Buildup/edge formation (low speed) — material adhesion
Workholding options include clamping, vacuum, adhesives, electrostatic, and magnetic methods. Roughing removes material quickly (can take up to 3 hours), limited by moving the part relative to the machine. Parts need to cool, and thermal expansion must be accounted for. The most accurate approach uses the largest tool that fits, not the smallest. Endmill entry is not flat (helical entry into material), and extra stock is used to account for beam bending of the endmill.
Roughing strategies use adaptive/pocket clearing with simulated stepdowns to balance time vs. inconsistencies. Maximum roughing time should be limited to ~30 minutes before moving on. Surfacing creates surface finishes using toolpath options: steep/shallow, scallop, or contour (you can bound the tool to specific areas in Fusion 360). Larger endmills are faster for surfacing operations.
Multi-Axis (5-Axis) Machining
5-axis machining enables reaching and positioning tools, repositioning workpieces for time and accuracy (without manual intervention), and improved surface finishing. The system is always limited by contact at every point in space.
There are two main approaches:
3+2 machining — repositioning then 3-axis cutting
Simultaneous 5-axis — moving more than 3 axes at once, including advanced swarf, multi-axis contour (perpendicular to surface), or multi-axis finishing with ball mills or circle-shaped end mills
Limitations include CAM software processing speed (single-threaded operations), complexity of simulating tool movement relative to workholding and part interference, and managing remaining stock (Fusion 360) or rest material (Mastercam).
Understanding machine kinematics is critical—see the MAS.865 mechanical design resources for detailed analysis of how machines move in space.
Flexibility
With 5-axis capability, the distinction between mills and lathes becomes blurred. Mills hold the workpiece while the tool spins; lathes hold the tool stationary while spinning the workpiece. This flexibility reduces design limitations. Think of systems in terms of three components: the tool, workholding, and axes.
Axes: different spindle configurations, different head designs
Summary
3-axis and 5-axis machining each have their place. The key is understanding which to use when, and how 5-axis capability breaks down barriers between traditional tool classifications, enabling more flexible and creative fabrication approaches.
Useful Documentation
Essential resources for output devices and actuator integration.
Comprehensive resource covering all output device categories including LEDs, displays (LCD, OLED, TFT), motors (DC, stepper, servo, brushless), speakers, solenoids, and more. Includes detailed tutorials, code examples, and implementation guides for various output device types.
Group Assignment: Measuring Power Consumption of Output Devices
Measuring power consumption of motors, servos, and stepper motors using adjustable power supplies and precision energy analyzers to understand performance characteristics and when to use each type.
Measurement Setup
We used an adjustable power supply set to 15V and measured quiescent power consumption of 450 mW (0.03 A, where P=IV) before connecting any motors. Power measurements were conducted using the Joulescope (JS220) Precision Energy Analyzer to measure current, voltage, power, charge, and energy in real-time.
Power supply set to 15V for motor testing
Joulescope JS220 Precision Energy Analyzer
Joulescope software interface
Using a potentiometer to change motor speed, we observed that below a certain threshold, the motor doesn't have enough power to spin (no mechanical work, just electrical losses). Above this threshold, speed increases with power. The dI/dt (rate of current change) cannot change instantly—it takes time. The PWM signal from the microcontroller (roughly 50% duty cycle) is smoothed after passing through the motor driver, with more linear behavior on the rising edge than the falling edge.
Motor circuit connections
Complete motor testing setup
50% duty cycle PWM from microcontroller
Smoothed PWM signal after motor driver
Zoomed-in power measurement
Zoomed-out power measurement
Motor Comparison Results
All motors tested at 15V supply, 2A current limit, with the same potentiometer value for comparison. The potentiometer determines speed and power for DC motors, and position for servos.
DC Motors (Voltage-Controlled)
DC Brushed Motor (Large)
Characteristics: Low-speed, high torque, no positional control
Current: 57 mA
Voltage: 14.49 V
Power: 0.8 W
Large DC brushed motor measurement
DC Brushed Motor (Small)
Characteristics: High speed, medium torque, no positional control
Current: 0.34 A
Voltage: 14.47 V
Power: 4.86 W
Small DC brushed motor measurement and operation
DC Stepper Motor (Current-Controlled)
Characteristics: Medium speed, medium torque, zero absolute positional control (relative positioning only)
Current: 2.0 A
Voltage: 10.93 V
Power: 22.33 W
Stepper motor measurement and operation
Servo Motors (5V Supply, Position-Controlled)
All servos tested at 5V supply, 2A current limit. Potentiometer determines position; power consumption remains relatively constant.
Characteristics: Absolute positional control, slower response, lower power
Current: 5.04 mA
Voltage: 4.99 V
Power: 25.05 mW
Micro servo motor measurement
Motor Comparison Summary Tables
Constant Voltage Comparison (15V Supply, 2A Current Limit)
DC brushed and stepper motors tested at 15V. Potentiometer controls speed for brushed motors, and step rate for stepper motor.
Motor Type
Size
Current
Voltage
Power
Characteristics
DC Brushed
Large
57 mA
14.49 V
0.8 W
Low-speed, high torque, no positional control
DC Brushed
Small
0.34 A
14.47 V
4.86 W
High speed, medium torque, no positional control
Stepper
N/A
2.0 A
10.93 V
22.33 W
Medium speed, medium torque, relative positioning only
Constant Current Comparison (5V Supply, 2A Current Limit)
Servo motors tested at 5V. Potentiometer controls position; power consumption remains relatively constant regardless of position.
Motor Type
Size
Current
Voltage
Power
Characteristics
Servo
Large
10.6 mA
4.99 V
53.4 mW
Absolute positional control, slower response
Servo
Micro
5.04 mA
4.99 V
25.05 mW
Absolute positional control, slower response, lower power
Summary: When to Use Each Motor Type
DC Brushed Motors: Simple applications requiring variable speed and torque, where positional control is not needed
Stepper Motors: Applications requiring precise relative positioning with medium power consumption
Servo Motors: Applications requiring absolute positional control with low power consumption, especially in battery-powered systems
Individual Assignment: Output Devices
Adding simple and complex output devices to the custom development board designed in Week 4, including a bright LED and OLED display for sensor visualization.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Comprehensive resource covering all output device categories including LEDs, displays (LCD, OLED, TFT), motors (DC, stepper, servo, brushless), speakers, solenoids, and more. Includes detailed tutorials, code examples, and implementation guides for various output device types.
Group Assignment: Measuring Power Consumption of Output Devices
Measuring power consumption of motors, servos, and stepper motors using adjustable power supplies and precision energy analyzers to understand performance characteristics and when to use each type.
Measurement Setup
We used an adjustable power supply set to 15V and measured quiescent power consumption of 450 mW (0.03 A, where P=IV) before connecting any motors. Power measurements were conducted using the Joulescope (JS220) Precision Energy Analyzer to measure current, voltage, power, charge, and energy in real-time.
Power supply set to 15V for motor testing
Joulescope JS220 Precision Energy Analyzer
Joulescope software interface
Using a potentiometer to change motor speed, we observed that below a certain threshold, the motor doesn't have enough power to spin (no mechanical work, just electrical losses). Above this threshold, speed increases with power. The dI/dt (rate of current change) cannot change instantly—it takes time. The PWM signal from the microcontroller (roughly 50% duty cycle) is smoothed after passing through the motor driver, with more linear behavior on the rising edge than the falling edge.
Motor circuit connections
Complete motor testing setup
50% duty cycle PWM from microcontroller
Smoothed PWM signal after motor driver
Zoomed-in power measurement
Zoomed-out power measurement
Motor Comparison Results
All motors tested at 15V supply, 2A current limit, with the same potentiometer value for comparison. The potentiometer determines speed and power for DC motors, and position for servos.
DC Motors (Voltage-Controlled)
DC Brushed Motor (Large)
Characteristics: Low-speed, high torque, no positional control
Current: 57 mA
Voltage: 14.49 V
Power: 0.8 W
Large DC brushed motor measurement
DC Brushed Motor (Small)
Characteristics: High speed, medium torque, no positional control
Current: 0.34 A
Voltage: 14.47 V
Power: 4.86 W
Small DC brushed motor measurement and operation
DC Stepper Motor (Current-Controlled)
Characteristics: Medium speed, medium torque, zero absolute positional control (relative positioning only)
Current: 2.0 A
Voltage: 10.93 V
Power: 22.33 W
Stepper motor measurement and operation
Servo Motors (5V Supply, Position-Controlled)
All servos tested at 5V supply, 2A current limit. Potentiometer determines position; power consumption remains relatively constant.
Characteristics: Absolute positional control, slower response, lower power
Current: 5.04 mA
Voltage: 4.99 V
Power: 25.05 mW
Micro servo motor measurement
Motor Comparison Summary Tables
Constant Voltage Comparison (15V Supply, 2A Current Limit)
DC brushed and stepper motors tested at 15V. Potentiometer controls speed for brushed motors, and step rate for stepper motor.
Motor Type
Size
Current
Voltage
Power
Characteristics
DC Brushed
Large
57 mA
14.49 V
0.8 W
Low-speed, high torque, no positional control
DC Brushed
Small
0.34 A
14.47 V
4.86 W
High speed, medium torque, no positional control
Stepper
N/A
2.0 A
10.93 V
22.33 W
Medium speed, medium torque, relative positioning only
Constant Current Comparison (5V Supply, 2A Current Limit)
Servo motors tested at 5V. Potentiometer controls position; power consumption remains relatively constant regardless of position.
Motor Type
Size
Current
Voltage
Power
Characteristics
Servo
Large
10.6 mA
4.99 V
53.4 mW
Absolute positional control, slower response
Servo
Micro
5.04 mA
4.99 V
25.05 mW
Absolute positional control, slower response, lower power
Summary: When to Use Each Motor Type
DC Brushed Motors: Simple applications requiring variable speed and torque, where positional control is not needed
Stepper Motors: Applications requiring precise relative positioning with medium power consumption
Servo Motors: Applications requiring absolute positional control with low power consumption, especially in battery-powered systems
Individual Assignment: Output Devices
Adding simple and complex output devices to the custom development board designed in Week 4, including a bright LED and OLED display for sensor visualization.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Channel Sharing: TDMA, FDMA, CSMA/CD, CSMA/CA, CDMA, MIMO
Group Assignment: Measuring Power Consumption of Output Devices
Measuring power consumption of motors, servos, and stepper motors using adjustable power supplies and precision energy analyzers to understand performance characteristics and when to use each type.
Measurement Setup
We used an adjustable power supply set to 15V and measured quiescent power consumption of 450 mW (0.03 A, where P=IV) before connecting any motors. Power measurements were conducted using the Joulescope (JS220) Precision Energy Analyzer to measure current, voltage, power, charge, and energy in real-time.
Power supply set to 15V for motor testing
Joulescope JS220 Precision Energy Analyzer
Joulescope software interface
Using a potentiometer to change motor speed, we observed that below a certain threshold, the motor doesn't have enough power to spin (no mechanical work, just electrical losses). Above this threshold, speed increases with power. The dI/dt (rate of current change) cannot change instantly—it takes time. The PWM signal from the microcontroller (roughly 50% duty cycle) is smoothed after passing through the motor driver, with more linear behavior on the rising edge than the falling edge.
Motor circuit connections
Complete motor testing setup
50% duty cycle PWM from microcontroller
Smoothed PWM signal after motor driver
Zoomed-in power measurement
Zoomed-out power measurement
Motor Comparison Results
All motors tested at 15V supply, 2A current limit, with the same potentiometer value for comparison. The potentiometer determines speed and power for DC motors, and position for servos.
DC Motors (Voltage-Controlled)
DC Brushed Motor (Large)
Characteristics: Low-speed, high torque, no positional control
Current: 57 mA
Voltage: 14.49 V
Power: 0.8 W
Large DC brushed motor measurement
DC Brushed Motor (Small)
Characteristics: High speed, medium torque, no positional control
Current: 0.34 A
Voltage: 14.47 V
Power: 4.86 W
Small DC brushed motor measurement and operation
DC Stepper Motor (Current-Controlled)
Characteristics: Medium speed, medium torque, zero absolute positional control (relative positioning only)
Current: 2.0 A
Voltage: 10.93 V
Power: 22.33 W
Stepper motor measurement and operation
Servo Motors (5V Supply, Position-Controlled)
All servos tested at 5V supply, 2A current limit. Potentiometer determines position; power consumption remains relatively constant.
Characteristics: Absolute positional control, slower response, lower power
Current: 5.04 mA
Voltage: 4.99 V
Power: 25.05 mW
Micro servo motor measurement
Motor Comparison Summary Tables
Constant Voltage Comparison (15V Supply, 2A Current Limit)
DC brushed and stepper motors tested at 15V. Potentiometer controls speed for brushed motors, and step rate for stepper motor.
Motor Type
Size
Current
Voltage
Power
Characteristics
DC Brushed
Large
57 mA
14.49 V
0.8 W
Low-speed, high torque, no positional control
DC Brushed
Small
0.34 A
14.47 V
4.86 W
High speed, medium torque, no positional control
Stepper
N/A
2.0 A
10.93 V
22.33 W
Medium speed, medium torque, relative positioning only
Constant Current Comparison (5V Supply, 2A Current Limit)
Servo motors tested at 5V. Potentiometer controls position; power consumption remains relatively constant regardless of position.
Motor Type
Size
Current
Voltage
Power
Characteristics
Servo
Large
10.6 mA
4.99 V
53.4 mW
Absolute positional control, slower response
Servo
Micro
5.04 mA
4.99 V
25.05 mW
Absolute positional control, slower response, lower power
Summary: When to Use Each Motor Type
DC Brushed Motors: Simple applications requiring variable speed and torque, where positional control is not needed
Stepper Motors: Applications requiring precise relative positioning with medium power consumption
Servo Motors: Applications requiring absolute positional control with low power consumption, especially in battery-powered systems
Individual Assignment: Output Devices
Adding simple and complex output devices to the custom development board designed in Week 4, including a bright LED and OLED display for sensor visualization.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Channel Sharing: TDMA, FDMA, CSMA/CD, CSMA/CA, CDMA, MIMO
Group Assignment: Send a Message Between Two Projects
[Placeholder: Group assignment documentation will be added here. The assignment requires sending a message between two projects.]
Assignment Description
Send a message between two projects. This assignment will demonstrate inter-project communication using wired or wireless networking protocols.
[Placeholder: Detailed documentation, images, videos, and results will be added here after completing the group assignment.]
Measurement Setup
We used an adjustable power supply set to 15V and measured quiescent power consumption of 450 mW (0.03 A, where P=IV) before connecting any motors. Power measurements were conducted using the Joulescope (JS220) Precision Energy Analyzer to measure current, voltage, power, charge, and energy in real-time.
Power supply set to 15V for motor testing
Joulescope JS220 Precision Energy Analyzer
Joulescope software interface
Using a potentiometer to change motor speed, we observed that below a certain threshold, the motor doesn't have enough power to spin (no mechanical work, just electrical losses). Above this threshold, speed increases with power. The dI/dt (rate of current change) cannot change instantly—it takes time. The PWM signal from the microcontroller (roughly 50% duty cycle) is smoothed after passing through the motor driver, with more linear behavior on the rising edge than the falling edge.
Motor circuit connections
Complete motor testing setup
50% duty cycle PWM from microcontroller
Smoothed PWM signal after motor driver
Zoomed-in power measurement
Zoomed-out power measurement
Motor Comparison Results
All motors tested at 15V supply, 2A current limit, with the same potentiometer value for comparison. The potentiometer determines speed and power for DC motors, and position for servos.
DC Motors (Voltage-Controlled)
DC Brushed Motor (Large)
Characteristics: Low-speed, high torque, no positional control
Current: 57 mA
Voltage: 14.49 V
Power: 0.8 W
Large DC brushed motor measurement
DC Brushed Motor (Small)
Characteristics: High speed, medium torque, no positional control
Current: 0.34 A
Voltage: 14.47 V
Power: 4.86 W
Small DC brushed motor measurement and operation
DC Stepper Motor (Current-Controlled)
Characteristics: Medium speed, medium torque, zero absolute positional control (relative positioning only)
Current: 2.0 A
Voltage: 10.93 V
Power: 22.33 W
Stepper motor measurement and operation
Servo Motors (5V Supply, Position-Controlled)
All servos tested at 5V supply, 2A current limit. Potentiometer determines position; power consumption remains relatively constant.
Characteristics: Absolute positional control, slower response, lower power
Current: 5.04 mA
Voltage: 4.99 V
Power: 25.05 mW
Micro servo motor measurement
Motor Comparison Summary Tables
Constant Voltage Comparison (15V Supply, 2A Current Limit)
DC brushed and stepper motors tested at 15V. Potentiometer controls speed for brushed motors, and step rate for stepper motor.
Motor Type
Size
Current
Voltage
Power
Characteristics
DC Brushed
Large
57 mA
14.49 V
0.8 W
Low-speed, high torque, no positional control
DC Brushed
Small
0.34 A
14.47 V
4.86 W
High speed, medium torque, no positional control
Stepper
N/A
2.0 A
10.93 V
22.33 W
Medium speed, medium torque, relative positioning only
Constant Current Comparison (5V Supply, 2A Current Limit)
Servo motors tested at 5V. Potentiometer controls position; power consumption remains relatively constant regardless of position.
Motor Type
Size
Current
Voltage
Power
Characteristics
Servo
Large
10.6 mA
4.99 V
53.4 mW
Absolute positional control, slower response
Servo
Micro
5.04 mA
4.99 V
25.05 mW
Absolute positional control, slower response, lower power
Summary: When to Use Each Motor Type
DC Brushed Motors: Simple applications requiring variable speed and torque, where positional control is not needed
Stepper Motors: Applications requiring precise relative positioning with medium power consumption
Servo Motors: Applications requiring absolute positional control with low power consumption, especially in battery-powered systems
Individual Assignment: Output Devices
Adding simple and complex output devices to the custom development board designed in Week 4, including a bright LED and OLED display for sensor visualization.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Channel Sharing: TDMA, FDMA, CSMA/CD, CSMA/CA, CDMA, MIMO
Group Assignment: Send a Message Between Two Projects
[Placeholder: Group assignment documentation will be added here. The assignment requires sending a message between two projects.]
Assignment Description
Send a message between two projects. This assignment will demonstrate inter-project communication using wired or wireless networking protocols.
[Placeholder: Detailed documentation, images, videos, and results will be added here after completing the group assignment.]
Power supply set to 15V for motor testing
Joulescope JS220 Precision Energy Analyzer
Joulescope software interface
Using a potentiometer to change motor speed, we observed that below a certain threshold, the motor doesn't have enough power to spin (no mechanical work, just electrical losses). Above this threshold, speed increases with power. The dI/dt (rate of current change) cannot change instantly—it takes time. The PWM signal from the microcontroller (roughly 50% duty cycle) is smoothed after passing through the motor driver, with more linear behavior on the rising edge than the falling edge.
Motor circuit connections
Complete motor testing setup
50% duty cycle PWM from microcontroller
Smoothed PWM signal after motor driver
Zoomed-in power measurement
Zoomed-out power measurement
Motor Comparison Results
All motors tested at 15V supply, 2A current limit, with the same potentiometer value for comparison. The potentiometer determines speed and power for DC motors, and position for servos.
DC Motors (Voltage-Controlled)
DC Brushed Motor (Large)
Characteristics: Low-speed, high torque, no positional control
Current: 57 mA
Voltage: 14.49 V
Power: 0.8 W
Large DC brushed motor measurement
DC Brushed Motor (Small)
Characteristics: High speed, medium torque, no positional control
Current: 0.34 A
Voltage: 14.47 V
Power: 4.86 W
Small DC brushed motor measurement and operation
DC Stepper Motor (Current-Controlled)
Characteristics: Medium speed, medium torque, zero absolute positional control (relative positioning only)
Current: 2.0 A
Voltage: 10.93 V
Power: 22.33 W
Stepper motor measurement and operation
Servo Motors (5V Supply, Position-Controlled)
All servos tested at 5V supply, 2A current limit. Potentiometer determines position; power consumption remains relatively constant.
Characteristics: Absolute positional control, slower response, lower power
Current: 5.04 mA
Voltage: 4.99 V
Power: 25.05 mW
Micro servo motor measurement
Motor Comparison Summary Tables
Constant Voltage Comparison (15V Supply, 2A Current Limit)
DC brushed and stepper motors tested at 15V. Potentiometer controls speed for brushed motors, and step rate for stepper motor.
Motor Type
Size
Current
Voltage
Power
Characteristics
DC Brushed
Large
57 mA
14.49 V
0.8 W
Low-speed, high torque, no positional control
DC Brushed
Small
0.34 A
14.47 V
4.86 W
High speed, medium torque, no positional control
Stepper
N/A
2.0 A
10.93 V
22.33 W
Medium speed, medium torque, relative positioning only
Constant Current Comparison (5V Supply, 2A Current Limit)
Servo motors tested at 5V. Potentiometer controls position; power consumption remains relatively constant regardless of position.
Motor Type
Size
Current
Voltage
Power
Characteristics
Servo
Large
10.6 mA
4.99 V
53.4 mW
Absolute positional control, slower response
Servo
Micro
5.04 mA
4.99 V
25.05 mW
Absolute positional control, slower response, lower power
Summary: When to Use Each Motor Type
DC Brushed Motors: Simple applications requiring variable speed and torque, where positional control is not needed
Stepper Motors: Applications requiring precise relative positioning with medium power consumption
Servo Motors: Applications requiring absolute positional control with low power consumption, especially in battery-powered systems
Individual Assignment: Output Devices
Adding simple and complex output devices to the custom development board designed in Week 4, including a bright LED and OLED display for sensor visualization.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Channel Sharing: TDMA, FDMA, CSMA/CD, CSMA/CA, CDMA, MIMO
Group Assignment: Send a Message Between Two Projects
[Placeholder: Group assignment documentation will be added here. The assignment requires sending a message between two projects.]
Assignment Description
Send a message between two projects. This assignment will demonstrate inter-project communication using wired or wireless networking protocols.
[Placeholder: Detailed documentation, images, videos, and results will be added here after completing the group assignment.]
Individual Assignment: Output Devices
Adding simple and complex output devices to the custom development board designed in Week 4, including a bright LED and OLED display for sensor visualization.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
Replacing the individual assignment section with networking content. Creating a comprehensive section summarizing both projects. Starting with the header and introduction:
Finding where the individual assignment section ends:
Replacing the individual assignment section header and introduction, then building the rest:
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s). This assignment demonstrates two networked systems: an ESP-NOW multiplayer game and a Wi-Fi camera streaming system with edge AI processing.
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s). This assignment demonstrates two networked systems: an ESP-NOW multiplayer game and a Wi-Fi camera streaming system with edge AI processing.
Networked System 1: CircleSquareShapeSongSwingalong (ESP-NOW)
Implementing a bright LED output using the MP-3014-1100-50-80 from the Fab Lab inventory. This high-power LED requires careful current limiting to achieve maximum brightness while maintaining safe operating conditions.
Current Limiting Resistor Calculation
For maximum brightness, we calculated the current limiting resistor for a 3.3 V supply driving an LED with a forward voltage (Vf) of 2.85 V. Using a 5 Ω resistor (the smallest available in the shop):
Step-by-Step Calculation
Step 1: Voltage across resistor
VR = Vsupply - Vf = 3.3 V - 2.85 V = 0.45 V
Step 2: LED current
I = VR / R = 0.45 V / 5 Ω = 0.09 A = 90 mA
Step 3: Resistor power dissipation
PR = VR × I = 0.45 V × 0.09 A = 0.0405 W
Step 4: LED power dissipation
PLED = Vf × I = 2.85 V × 0.09 A = 0.2565 W
Result: At 3.3 V with a 5 Ω resistor, the LED draws approximately 90 mA, which is well below the 150 mA maximum rating. This provides slightly reduced brightness compared to maximum, but significantly extends lifespan and reduces heat generation.
Resistor (Ω)
LED Current (mA)
Power in Resistor (W)
Notes
3.0 Ω
150 mA
0.0675 W
Max brightness, close to rated max current (hot)
3.9 Ω
~115–120 mA
~0.055 W
Good balance: bright but less stress
4.5 Ω
~100 mA
~0.045 W
Cooler, longer life
5.0 Ω
~90 mA
~0.0405 W
Selected: even cooler, ~0.26 W in LED, very safe thermally
Bright LED test demonstration
Bright LED circuit on development board
Complex Output Device: OLED Display
Implementing an SSD1306 OLED display for visualizing sensor data. The I²C interface requires two 10 kΩ pull-up resistors—one between 3.3 V and SDA, and one between 3.3 V and SCL. These were soldered onto the connectors of the development board to enable proper I²C communication, which was previously failing in earlier weeks without these pull-up resistors.
Development board with OLED display connected, showing pull-up resistors soldered to I²C connectors
Standard OLED connections: VCC to 3.3 V on ESP32S3, GND to GND, SDA to SDA (pin 5), and SCL to SCL (pin 6).
Accelerometer Data Display
Displaying real-time accelerometer data from the MPU6050 sensor on the OLED screen. This implementation required working SDA and SCL connections with proper pull-up resistors, which were finally fixed this week after troubleshooting I²C communication issues.
Accelerometer data displayed on OLED screen showing acceleration and gyroscope values
Camera Output Display
Displaying camera capture output on the OLED screen with Edge AI inference results. SDA and SCL were not working in previous weeks without the pull-up resistors. While troubleshooting, camera output was verified through the serial monitor, and the input device functionality was confirmed by testing on Quentin's board. With the pull-up resistors now in place, the OLED display successfully shows camera frames and inference results.
Camera output with Edge AI inference displayed on OLED screen showing TTD (time-to-death) prediction
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s). This assignment demonstrates two networked systems: an ESP-NOW multiplayer game and a Wi-Fi camera streaming system with edge AI processing.
Networked System 1: CircleSquareShapeSongSwingalong (ESP-NOW)
A collaborative multiplayer game featuring geometric shape interactions, synchronized gameplay between two ESP32-S3 devices using ESP-NOW wireless communication. The system uses MAC address-based player identification and real-time state synchronization for coordinated gameplay. See Week 2 documentation and design files for complete details.
Design & Build
The system consists of two XIAO ESP32-S3 development boards, each with an SSD1306 OLED display (128x64) and capacitive touch sensors. The boards communicate wirelessly using ESP-NOW protocol, enabling low-latency peer-to-peer communication without requiring a Wi-Fi access point.
Network Type & Protocol
Network Type: Wireless peer-to-peer (ESP-NOW) Protocol: ESP-NOW (Espressif's proprietary low-power wireless communication protocol) Addressing Scheme: MAC address-based device identification
Input & Output Devices
Input Devices: Capacitive touch sensors (6 touch pads per device) for player controls (left, right, jump)
Output Devices: SSD1306 OLED display (128x64, I²C address 0x3C) for game rendering and player state visualization
Shape Song Swing Along educational content integration and gameplay
Circle and square shape interaction gameplay mechanics
Connections
Each ESP32-S3 board connects to an OLED display via I²C (SDA pin 5, SCL pin 6) and reads touch sensor inputs from GPIO pins. The ESP-NOW communication is handled entirely through the ESP32-S3's built-in Wi-Fi radio, requiring no external hardware connections.
Networked System 2: Camera Livestream & Edge AI (Wi-Fi)
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s). This assignment demonstrates two networked systems: an ESP-NOW multiplayer game and a Wi-Fi camera streaming system with edge AI processing.
Networked System 1: CircleSquareShapeSongSwingalong (ESP-NOW)
A collaborative multiplayer game featuring geometric shape interactions, synchronized gameplay between two ESP32-S3 devices using ESP-NOW wireless communication. The system uses MAC address-based player identification and real-time state synchronization for coordinated gameplay. See Week 2 documentation and design files for complete details.
Design & Build
The system consists of two XIAO ESP32-S3 development boards, each with an SSD1306 OLED display (128x64) and capacitive touch sensors. The boards communicate wirelessly using ESP-NOW protocol, enabling low-latency peer-to-peer communication without requiring a Wi-Fi access point.
Network Type & Protocol
Network Type: Wireless peer-to-peer (ESP-NOW) Protocol: ESP-NOW (Espressif's proprietary low-power wireless communication protocol) Addressing Scheme: MAC address-based device identification
Input & Output Devices
Input Devices: Capacitive touch sensors (6 touch pads per device) for player controls (left, right, jump)
Output Devices: SSD1306 OLED display (128x64, I²C address 0x3C) for game rendering and player state visualization
Shape Song Swing Along educational content integration and gameplay
Circle and square shape interaction gameplay mechanics
Connections
Each ESP32-S3 board connects to an OLED display via I²C (SDA pin 5, SCL pin 6) and reads touch sensor inputs from GPIO pins. The ESP-NOW communication is handled entirely through the ESP32-S3's built-in Wi-Fi radio, requiring no external hardware connections.
Networked System 2: Camera Livestream & Edge AI (Wi-Fi)
A Wi-Fi-enabled camera system using ESP32-S3's built-in camera and HTTP server capabilities to stream JPEG frames over Wi-Fi using MJPEG (Motion JPEG) protocol. The system also includes edge AI face detection using a FOMO (Faster Objects, More Objects) model from Edge Impulse for real-time person tracking. See Week 10 documentation and design files for complete details.
Design & Build
The system uses a XIAO ESP32-S3 Sense development board with an integrated camera module. The camera captures frames at QQVGA (160x120) or QVGA resolution, processes them through an Edge AI inference pipeline, and streams the results over Wi-Fi via HTTP multipart response. The system can also display camera output and inference results on an OLED display connected via I²C.
Network Type & Protocol
Network Type: Wireless local area network (Wi-Fi) Protocol: HTTP over Wi-Fi (802.11), MJPEG streaming Addressing Scheme: IP address (DHCP-assigned) and MAC address (hardware identifier)
Input & Output Devices
Input Devices: Camera module (integrated on XIAO ESP32-S3 Sense) for image capture, button for capture trigger
Output Devices: OLED display (SSD1306, 128x64, I²C address 0x3C) for displaying camera frames and inference results, Wi-Fi HTTP server for remote streaming
Wi-Fi livestream interfaceCamera feed accessible over Wi-Fi for remote monitoring and control during operation.
Wi-Fi livestream testInitial Wi-Fi livestream test demonstrating remote camera access and feed quality.MIT Wi-Fi livestreamLivestream working on MIT network, confirming network compatibility and stability.Edge AI face detectionReal-time face detection running on-device using edge AI models for person tracking and interaction.
Connections
The camera module is integrated directly on the XIAO ESP32-S3 Sense board, connected via parallel data bus (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). The OLED display connects via I²C (SDA pin 5, SCL pin 6) with pull-up resistors. Wi-Fi connection is established through the ESP32-S3's built-in Wi-Fi radio.
Download Design Files
camera_stream.zip — Complete camera stream project (includes .ino and .h files)
Complete network addressing information for all connected devices, including MAC addresses (hardware identifiers) and IP addresses (network identifiers) for Wi-Fi-connected devices.
ESP-NOW Network (CircleSquareShapeSongSwingalong)
Device
Component
MAC Address
Network Type
Input Device
Output Device
Player 1
XIAO ESP32-S3
D8:3B:DA:75:05:AC
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Player 2
XIAO ESP32-S3
D8:3B:DA:75:E1:9C
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Wi-Fi Network (Camera Livestream System)
Device
Component
MAC Address
IP Address
Network Type
Input Device
Output Device
Camera Node
XIAO ESP32-S3 Sense
[Device MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
Camera module, Button
OLED (SSD1306, 0x3C), HTTP Server
Client Device
Web Browser
[Client MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
N/A
Display (receives MJPEG stream)
Note: MAC addresses are hardware identifiers unique to each ESP32-S3 device. IP addresses are assigned dynamically via DHCP when connecting to a Wi-Fi network. For ESP-NOW communication, only MAC addresses are used (no IP addresses required). The camera system's IP address is printed to the Serial Monitor upon Wi-Fi connection establishment.
Design Files
Complete design files for sensors display and camera dev board implementations including Arduino firmware and configuration files.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s). This assignment demonstrates two networked systems: an ESP-NOW multiplayer game and a Wi-Fi camera streaming system with edge AI processing.
Networked System 1: CircleSquareShapeSongSwingalong (ESP-NOW)
A collaborative multiplayer game featuring geometric shape interactions, synchronized gameplay between two ESP32-S3 devices using ESP-NOW wireless communication. The system uses MAC address-based player identification and real-time state synchronization for coordinated gameplay. See Week 2 documentation and design files for complete details.
Design & Build
The system consists of two XIAO ESP32-S3 development boards, each with an SSD1306 OLED display (128x64) and capacitive touch sensors. The boards communicate wirelessly using ESP-NOW protocol, enabling low-latency peer-to-peer communication without requiring a Wi-Fi access point.
Network Type & Protocol
Network Type: Wireless peer-to-peer (ESP-NOW) Protocol: ESP-NOW (Espressif's proprietary low-power wireless communication protocol) Addressing Scheme: MAC address-based device identification
Input & Output Devices
Input Devices: Capacitive touch sensors (6 touch pads per device) for player controls (left, right, jump)
Output Devices: SSD1306 OLED display (128x64, I²C address 0x3C) for game rendering and player state visualization
Shape Song Swing Along educational content integration and gameplay
Circle and square shape interaction gameplay mechanics
Connections
Each ESP32-S3 board connects to an OLED display via I²C (SDA pin 5, SCL pin 6) and reads touch sensor inputs from GPIO pins. The ESP-NOW communication is handled entirely through the ESP32-S3's built-in Wi-Fi radio, requiring no external hardware connections.
Networked System 2: Camera Livestream & Edge AI (Wi-Fi)
A Wi-Fi-enabled camera system using ESP32-S3's built-in camera and HTTP server capabilities to stream JPEG frames over Wi-Fi using MJPEG (Motion JPEG) protocol. The system also includes edge AI face detection using a FOMO (Faster Objects, More Objects) model from Edge Impulse for real-time person tracking. See Week 10 documentation and design files for complete details.
Design & Build
The system uses a XIAO ESP32-S3 Sense development board with an integrated camera module. The camera captures frames at QQVGA (160x120) or QVGA resolution, processes them through an Edge AI inference pipeline, and streams the results over Wi-Fi via HTTP multipart response. The system can also display camera output and inference results on an OLED display connected via I²C.
Network Type & Protocol
Network Type: Wireless local area network (Wi-Fi) Protocol: HTTP over Wi-Fi (802.11), MJPEG streaming Addressing Scheme: IP address (DHCP-assigned) and MAC address (hardware identifier)
Input & Output Devices
Input Devices: Camera module (integrated on XIAO ESP32-S3 Sense) for image capture, button for capture trigger
Output Devices: OLED display (SSD1306, 128x64, I²C address 0x3C) for displaying camera frames and inference results, Wi-Fi HTTP server for remote streaming
Wi-Fi livestream interfaceCamera feed accessible over Wi-Fi for remote monitoring and control during operation.
Wi-Fi livestream testInitial Wi-Fi livestream test demonstrating remote camera access and feed quality.MIT Wi-Fi livestreamLivestream working on MIT network, confirming network compatibility and stability.Edge AI face detectionReal-time face detection running on-device using edge AI models for person tracking and interaction.
Connections
The camera module is integrated directly on the XIAO ESP32-S3 Sense board, connected via parallel data bus (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). The OLED display connects via I²C (SDA pin 5, SCL pin 6) with pull-up resistors. Wi-Fi connection is established through the ESP32-S3's built-in Wi-Fi radio.
Download Design Files
camera_stream.zip — Complete camera stream project (includes .ino and .h files)
Complete network addressing information for all connected devices, including MAC addresses (hardware identifiers) and IP addresses (network identifiers) for Wi-Fi-connected devices.
ESP-NOW Network (CircleSquareShapeSongSwingalong)
Device
Component
MAC Address
Network Type
Input Device
Output Device
Player 1
XIAO ESP32-S3
D8:3B:DA:75:05:AC
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Player 2
XIAO ESP32-S3
D8:3B:DA:75:E1:9C
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Wi-Fi Network (Camera Livestream System)
Device
Component
MAC Address
IP Address
Network Type
Input Device
Output Device
Camera Node
XIAO ESP32-S3 Sense
[Device MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
Camera module, Button
OLED (SSD1306, 0x3C), HTTP Server
Client Device
Web Browser
[Client MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
N/A
Display (receives MJPEG stream)
Note: MAC addresses are hardware identifiers unique to each ESP32-S3 device. IP addresses are assigned dynamically via DHCP when connecting to a Wi-Fi network. For ESP-NOW communication, only MAC addresses are used (no IP addresses required). The camera system's IP address is printed to the Serial Monitor upon Wi-Fi connection establishment.
Design Files
Complete design files for networked systems including ESP-NOW multiplayer game and Wi-Fi camera streaming implementations with Arduino firmware and configuration files.
ESP-NOW Multiplayer Game (CircleSquareShapeSongSwingalong)
Arduino code for ESP-NOW wireless multiplayer game with MAC address-based player identification and synchronized game state management.
Sensors Display Code
The sensors display script reads data from multiple sensors (MPU6050 accelerometer/gyroscope and HX711 load cell) and displays the values on both the OLED screen and Serial Monitor. The system activates data collection when a button is pressed.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure button pin (INPUT_PULLUP) and LED pin (OUTPUT)
Initialize I2C bus (SDA=5, SCL=6) at 100kHz
Initialize OLED display (SSD1306, 128x64, I2C address 0x3C)
Initialize MPU6050 accelerometer/gyroscope (try 0x68, then 0x69)
Initialize HX711 load cell amplifier
Set calibration factor and tare (zero) the scale
Display "Setup complete!" message on OLED
END Setup
BEGIN Loop
Read button state
IF button pressed THEN
Turn LED ON
IF not already collecting THEN
Start data collection mode
Print "=== START DATA COLLECTION ===" to Serial
ENDIF
IF 500ms have passed since last read THEN
Read accelerometer/gyroscope data (acceleration x,y,z, gyro x,y,z, temperature)
Read load cell data (raw value and weight in grams)
Print all sensor values to Serial Monitor
Clear OLED display
Display formatted sensor data on OLED:
- Acceleration X, Y
- Acceleration Z, Temperature
- Gyroscope X, Y
- Weight (grams)
Update OLED display
Update last read timestamp
ENDIF
ELSE
IF was collecting THEN
Stop data collection mode
Print "=== STOP DATA COLLECTION ===" to Serial
Display "Data collection stopped." on OLED
ENDIF
The camera dev board script captures images from the ESP32S3 camera module, processes them through an Edge AI model, and displays both the camera feed and inference results on the OLED screen. The code requires the camera_pins.h header file which defines GPIO pin mappings for the XIAO ESP32S3 Sense camera module.
How It Works (Pseudocode):
BEGIN Setup
Initialize Serial communication (115200 baud)
Configure LED and button pins
Initialize OLED display (SSD1306, 128x64, I2C on pins 5, 6)
Display "OLED Ready!" message
Configure camera module:
- Load camera pin definitions from camera_pins.h
- Set frame size to QQVGA (160x120)
- Set pixel format to grayscale
- Configure frame buffer location (PSRAM)
- Set JPEG quality and frame count
- Configure grab mode (LATEST)
Initialize camera with configuration
Apply vertical flip and horizontal mirror settings
IF camera initialization successful THEN
Set camera_ready flag
Display "Camera Ready - Press Button" on OLED
Set initial capture timestamp
ELSE
Display "Camera init failed" on OLED
ENDIF
END Setup
BEGIN Loop
IF camera not ready THEN
Delay and return
ENDIF
Read button state
IF button pressed (edge triggered) THEN
Set capture trigger flag
ENDIF
Control LED based on button state
IF capture triggered OR 60 seconds elapsed THEN
Reset capture trigger
Update last capture timestamp
Turn LED ON
Display "Capturing..." on OLED
Capture image frame from camera
Turn LED OFF
IF capture successful THEN
Print capture info to Serial (width, height, bytes)
Process and display image on OLED:
- Scale 160x120 image to 128x64 OLED size
- Apply contrast enhancement
- Apply Floyd-Steinberg dithering
- Draw dithered image to OLED
Convert grayscale frame to RGB888 format
Prepare input buffer for Edge AI model
Run Edge Impulse classifier
Get inference result (TTD value in years)
Draw TTD result box overlay on OLED
Print TTD value to Serial Monitor
Return frame buffer to camera driver
ELSE
Print "Capture failed" to Serial
Display "Capture failed" on OLED
ENDIF
ENDIF
Small delay (30ms)
END Loop
Note on camera_pins.h
The camera_pins.h header file defines GPIO pin mappings for various ESP32 camera models. For the XIAO ESP32S3 Sense, it configures pins for the camera data lines (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). You need to ensure this file is in a side-tab or included in your Arduino project.
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s). This assignment demonstrates two networked systems: an ESP-NOW multiplayer game and a Wi-Fi camera streaming system with edge AI processing.
Networked System 1: CircleSquareShapeSongSwingalong (ESP-NOW)
A collaborative multiplayer game featuring geometric shape interactions, synchronized gameplay between two ESP32-S3 devices using ESP-NOW wireless communication. The system uses MAC address-based player identification and real-time state synchronization for coordinated gameplay. See Week 2 documentation and design files for complete details.
Design & Build
The system consists of two XIAO ESP32-S3 development boards, each with an SSD1306 OLED display (128x64) and capacitive touch sensors. The boards communicate wirelessly using ESP-NOW protocol, enabling low-latency peer-to-peer communication without requiring a Wi-Fi access point.
Network Type & Protocol
Network Type: Wireless peer-to-peer (ESP-NOW) Protocol: ESP-NOW (Espressif's proprietary low-power wireless communication protocol) Addressing Scheme: MAC address-based device identification
Input & Output Devices
Input Devices: Capacitive touch sensors (6 touch pads per device) for player controls (left, right, jump)
Output Devices: SSD1306 OLED display (128x64, I²C address 0x3C) for game rendering and player state visualization
Shape Song Swing Along educational content integration and gameplay
Circle and square shape interaction gameplay mechanics
Connections
Each ESP32-S3 board connects to an OLED display via I²C (SDA pin 5, SCL pin 6) and reads touch sensor inputs from GPIO pins. The ESP-NOW communication is handled entirely through the ESP32-S3's built-in Wi-Fi radio, requiring no external hardware connections.
Networked System 2: Camera Livestream & Edge AI (Wi-Fi)
A Wi-Fi-enabled camera system using ESP32-S3's built-in camera and HTTP server capabilities to stream JPEG frames over Wi-Fi using MJPEG (Motion JPEG) protocol. The system also includes edge AI face detection using a FOMO (Faster Objects, More Objects) model from Edge Impulse for real-time person tracking. See Week 10 documentation and design files for complete details.
Design & Build
The system uses a XIAO ESP32-S3 Sense development board with an integrated camera module. The camera captures frames at QQVGA (160x120) or QVGA resolution, processes them through an Edge AI inference pipeline, and streams the results over Wi-Fi via HTTP multipart response. The system can also display camera output and inference results on an OLED display connected via I²C.
Network Type & Protocol
Network Type: Wireless local area network (Wi-Fi) Protocol: HTTP over Wi-Fi (802.11), MJPEG streaming Addressing Scheme: IP address (DHCP-assigned) and MAC address (hardware identifier)
Input & Output Devices
Input Devices: Camera module (integrated on XIAO ESP32-S3 Sense) for image capture, button for capture trigger
Output Devices: OLED display (SSD1306, 128x64, I²C address 0x3C) for displaying camera frames and inference results, Wi-Fi HTTP server for remote streaming
Wi-Fi livestream interfaceCamera feed accessible over Wi-Fi for remote monitoring and control during operation.
Wi-Fi livestream testInitial Wi-Fi livestream test demonstrating remote camera access and feed quality.MIT Wi-Fi livestreamLivestream working on MIT network, confirming network compatibility and stability.Edge AI face detectionReal-time face detection running on-device using edge AI models for person tracking and interaction.
Connections
The camera module is integrated directly on the XIAO ESP32-S3 Sense board, connected via parallel data bus (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). The OLED display connects via I²C (SDA pin 5, SCL pin 6) with pull-up resistors. Wi-Fi connection is established through the ESP32-S3's built-in Wi-Fi radio.
Download Design Files
camera_stream.zip — Complete camera stream project (includes .ino and .h files)
Complete network addressing information for all connected devices, including MAC addresses (hardware identifiers) and IP addresses (network identifiers) for Wi-Fi-connected devices.
ESP-NOW Network (CircleSquareShapeSongSwingalong)
Device
Component
MAC Address
Network Type
Input Device
Output Device
Player 1
XIAO ESP32-S3
D8:3B:DA:75:05:AC
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Player 2
XIAO ESP32-S3
D8:3B:DA:75:E1:9C
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Wi-Fi Network (Camera Livestream System)
Device
Component
MAC Address
IP Address
Network Type
Input Device
Output Device
Camera Node
XIAO ESP32-S3 Sense
[Device MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
Camera module, Button
OLED (SSD1306, 0x3C), HTTP Server
Client Device
Web Browser
[Client MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
N/A
Display (receives MJPEG stream)
Note: MAC addresses are hardware identifiers unique to each ESP32-S3 device. IP addresses are assigned dynamically via DHCP when connecting to a Wi-Fi network. For ESP-NOW communication, only MAC addresses are used (no IP addresses required). The camera system's IP address is printed to the Serial Monitor upon Wi-Fi connection establishment.
Design Files
Complete design files for networked systems including ESP-NOW multiplayer game and Wi-Fi camera streaming implementations with Arduino firmware and configuration files.
ESP-NOW Multiplayer Game (CircleSquareShapeSongSwingalong)
Arduino code for ESP-NOW wireless multiplayer game with MAC address-based player identification and synchronized game state management.
Key Features:
ESP-NOW wireless peer-to-peer communication
MAC address-based player identification (D8:3B:DA:75:05:AC and D8:3B:DA:75:E1:9C)
Arduino code for ESP32-S3 camera livestreaming over Wi-Fi using MJPEG protocol and Edge AI face detection using FOMO models from Edge Impulse.
Camera Livestream Pseudocode:
SETUP:
1. Initialize Serial communication (115200 baud)
2. Configure camera pins (from camera_pins.h)
3. Create camera_config_t structure
4. Initialize camera with esp_camera_init()
5. Connect to Wi-Fi network
6. Start HTTP server with stream handler
STREAM_HANDLER:
1. Set HTTP response type to "multipart/x-mixed-replace"
2. Enter loop: capture frame, send via HTTP, repeat
Key insights and learnings from working with output devices and power measurement.
Contributions
Acknowledgements and team roles for output devices work.
Group Assignment
Power measurement of motors, servos, and stepper motors conducted together by the week 8 team with guidance from instructors.
LED Current Limiting Calculation
ChatGPT assisted with the LED current limiting resistor calculation, with correction from Anthony when the initial calculation assumed 5V instead of 3.3V. View ChatGPT conversation
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s). This assignment demonstrates two networked systems: an ESP-NOW multiplayer game and a Wi-Fi camera streaming system with edge AI processing.
Networked System 1: CircleSquareShapeSongSwingalong (ESP-NOW)
A collaborative multiplayer game featuring geometric shape interactions, synchronized gameplay between two ESP32-S3 devices using ESP-NOW wireless communication. The system uses MAC address-based player identification and real-time state synchronization for coordinated gameplay. See Week 2 documentation and design files for complete details.
Design & Build
The system consists of two XIAO ESP32-S3 development boards, each with an SSD1306 OLED display (128x64) and capacitive touch sensors. The boards communicate wirelessly using ESP-NOW protocol, enabling low-latency peer-to-peer communication without requiring a Wi-Fi access point.
Network Type & Protocol
Network Type: Wireless peer-to-peer (ESP-NOW) Protocol: ESP-NOW (Espressif's proprietary low-power wireless communication protocol) Addressing Scheme: MAC address-based device identification
Input & Output Devices
Input Devices: Capacitive touch sensors (6 touch pads per device) for player controls (left, right, jump)
Output Devices: SSD1306 OLED display (128x64, I²C address 0x3C) for game rendering and player state visualization
Shape Song Swing Along educational content integration and gameplay
Circle and square shape interaction gameplay mechanics
Connections
Each ESP32-S3 board connects to an OLED display via I²C (SDA pin 5, SCL pin 6) and reads touch sensor inputs from GPIO pins. The ESP-NOW communication is handled entirely through the ESP32-S3's built-in Wi-Fi radio, requiring no external hardware connections.
Networked System 2: Camera Livestream & Edge AI (Wi-Fi)
A Wi-Fi-enabled camera system using ESP32-S3's built-in camera and HTTP server capabilities to stream JPEG frames over Wi-Fi using MJPEG (Motion JPEG) protocol. The system also includes edge AI face detection using a FOMO (Faster Objects, More Objects) model from Edge Impulse for real-time person tracking. See Week 10 documentation and design files for complete details.
Design & Build
The system uses a XIAO ESP32-S3 Sense development board with an integrated camera module. The camera captures frames at QQVGA (160x120) or QVGA resolution, processes them through an Edge AI inference pipeline, and streams the results over Wi-Fi via HTTP multipart response. The system can also display camera output and inference results on an OLED display connected via I²C.
Network Type & Protocol
Network Type: Wireless local area network (Wi-Fi) Protocol: HTTP over Wi-Fi (802.11), MJPEG streaming Addressing Scheme: IP address (DHCP-assigned) and MAC address (hardware identifier)
Input & Output Devices
Input Devices: Camera module (integrated on XIAO ESP32-S3 Sense) for image capture, button for capture trigger
Output Devices: OLED display (SSD1306, 128x64, I²C address 0x3C) for displaying camera frames and inference results, Wi-Fi HTTP server for remote streaming
Wi-Fi livestream interfaceCamera feed accessible over Wi-Fi for remote monitoring and control during operation.
Wi-Fi livestream testInitial Wi-Fi livestream test demonstrating remote camera access and feed quality.MIT Wi-Fi livestreamLivestream working on MIT network, confirming network compatibility and stability.Edge AI face detectionReal-time face detection running on-device using edge AI models for person tracking and interaction.
Connections
The camera module is integrated directly on the XIAO ESP32-S3 Sense board, connected via parallel data bus (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). The OLED display connects via I²C (SDA pin 5, SCL pin 6) with pull-up resistors. Wi-Fi connection is established through the ESP32-S3's built-in Wi-Fi radio.
Download Design Files
camera_stream.zip — Complete camera stream project (includes .ino and .h files)
Complete network addressing information for all connected devices, including MAC addresses (hardware identifiers) and IP addresses (network identifiers) for Wi-Fi-connected devices.
ESP-NOW Network (CircleSquareShapeSongSwingalong)
Device
Component
MAC Address
Network Type
Input Device
Output Device
Player 1
XIAO ESP32-S3
D8:3B:DA:75:05:AC
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Player 2
XIAO ESP32-S3
D8:3B:DA:75:E1:9C
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Wi-Fi Network (Camera Livestream System)
Device
Component
MAC Address
IP Address
Network Type
Input Device
Output Device
Camera Node
XIAO ESP32-S3 Sense
[Device MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
Camera module, Button
OLED (SSD1306, 0x3C), HTTP Server
Client Device
Web Browser
[Client MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
N/A
Display (receives MJPEG stream)
Note: MAC addresses are hardware identifiers unique to each ESP32-S3 device. IP addresses are assigned dynamically via DHCP when connecting to a Wi-Fi network. For ESP-NOW communication, only MAC addresses are used (no IP addresses required). The camera system's IP address is printed to the Serial Monitor upon Wi-Fi connection establishment.
Design Files
Complete design files for networked systems including ESP-NOW multiplayer game and Wi-Fi camera streaming implementations with Arduino firmware and configuration files.
ESP-NOW Multiplayer Game (CircleSquareShapeSongSwingalong)
Arduino code for ESP-NOW wireless multiplayer game with MAC address-based player identification and synchronized game state management.
Key Features:
ESP-NOW wireless peer-to-peer communication
MAC address-based player identification (D8:3B:DA:75:05:AC and D8:3B:DA:75:E1:9C)
Arduino code for ESP32-S3 camera livestreaming over Wi-Fi using MJPEG protocol and Edge AI face detection using FOMO models from Edge Impulse.
Camera Livestream Pseudocode:
SETUP:
1. Initialize Serial communication (115200 baud)
2. Configure camera pins (from camera_pins.h)
3. Create camera_config_t structure
4. Initialize camera with esp_camera_init()
5. Connect to Wi-Fi network
6. Start HTTP server with stream handler
STREAM_HANDLER:
1. Set HTTP response type to "multipart/x-mixed-replace"
2. Enter loop: capture frame, send via HTTP, repeat
Key insights and learnings from working with networking and communications protocols.
Contributions
Acknowledgements and team roles for networking and communications work.
ESP-NOW Multiplayer Game
Developed CircleSquareShapeSongSwingalong multiplayer game with ESP-NOW wireless communication during Week 2. See Week 2 documentation for details.
Wi-Fi Camera Streaming System
Developed camera livestreaming and Edge AI face detection system during Week 10. See Week 10 documentation for details.
Ethical AI Use
Transparent documentation of AI assistance used in this week's output devices work.
AI-Assisted Week 8 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 8 documentation page, including the multi-axis machining training section, group assignment power measurement documentation, individual assignment sections for bright LED and OLED display implementations, motor comparison tables, and all formatting and styling. The AI helped refine and organize raw notes into professional, succinct content while preserving key technical details.
ChatGPT assisted with calculating the current limiting resistor for the bright LED. Initially, the AI assumed a 5V supply, but after correcting it to 3.3V with Anthony's guidance, it provided accurate calculations for voltage drop, current, and power dissipation. This helped determine that a 5Ω resistor (the smallest available in the shop) would safely drive the LED at ~90mA, below the 150mA maximum rating.
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s). This assignment demonstrates two networked systems: an ESP-NOW multiplayer game and a Wi-Fi camera streaming system with edge AI processing.
Networked System 1: CircleSquareShapeSongSwingalong (ESP-NOW)
A collaborative multiplayer game featuring geometric shape interactions, synchronized gameplay between two ESP32-S3 devices using ESP-NOW wireless communication. The system uses MAC address-based player identification and real-time state synchronization for coordinated gameplay. See Week 2 documentation and design files for complete details.
Design & Build
The system consists of two XIAO ESP32-S3 development boards, each with an SSD1306 OLED display (128x64) and capacitive touch sensors. The boards communicate wirelessly using ESP-NOW protocol, enabling low-latency peer-to-peer communication without requiring a Wi-Fi access point.
Network Type & Protocol
Network Type: Wireless peer-to-peer (ESP-NOW) Protocol: ESP-NOW (Espressif's proprietary low-power wireless communication protocol) Addressing Scheme: MAC address-based device identification
Input & Output Devices
Input Devices: Capacitive touch sensors (6 touch pads per device) for player controls (left, right, jump)
Output Devices: SSD1306 OLED display (128x64, I²C address 0x3C) for game rendering and player state visualization
Shape Song Swing Along educational content integration and gameplay
Circle and square shape interaction gameplay mechanics
Connections
Each ESP32-S3 board connects to an OLED display via I²C (SDA pin 5, SCL pin 6) and reads touch sensor inputs from GPIO pins. The ESP-NOW communication is handled entirely through the ESP32-S3's built-in Wi-Fi radio, requiring no external hardware connections.
Networked System 2: Camera Livestream & Edge AI (Wi-Fi)
A Wi-Fi-enabled camera system using ESP32-S3's built-in camera and HTTP server capabilities to stream JPEG frames over Wi-Fi using MJPEG (Motion JPEG) protocol. The system also includes edge AI face detection using a FOMO (Faster Objects, More Objects) model from Edge Impulse for real-time person tracking. See Week 10 documentation and design files for complete details.
Design & Build
The system uses a XIAO ESP32-S3 Sense development board with an integrated camera module. The camera captures frames at QQVGA (160x120) or QVGA resolution, processes them through an Edge AI inference pipeline, and streams the results over Wi-Fi via HTTP multipart response. The system can also display camera output and inference results on an OLED display connected via I²C.
Network Type & Protocol
Network Type: Wireless local area network (Wi-Fi) Protocol: HTTP over Wi-Fi (802.11), MJPEG streaming Addressing Scheme: IP address (DHCP-assigned) and MAC address (hardware identifier)
Input & Output Devices
Input Devices: Camera module (integrated on XIAO ESP32-S3 Sense) for image capture, button for capture trigger
Output Devices: OLED display (SSD1306, 128x64, I²C address 0x3C) for displaying camera frames and inference results, Wi-Fi HTTP server for remote streaming
Wi-Fi livestream interfaceCamera feed accessible over Wi-Fi for remote monitoring and control during operation.
Wi-Fi livestream testInitial Wi-Fi livestream test demonstrating remote camera access and feed quality.MIT Wi-Fi livestreamLivestream working on MIT network, confirming network compatibility and stability.Edge AI face detectionReal-time face detection running on-device using edge AI models for person tracking and interaction.
Connections
The camera module is integrated directly on the XIAO ESP32-S3 Sense board, connected via parallel data bus (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). The OLED display connects via I²C (SDA pin 5, SCL pin 6) with pull-up resistors. Wi-Fi connection is established through the ESP32-S3's built-in Wi-Fi radio.
Download Design Files
camera_stream.zip — Complete camera stream project (includes .ino and .h files)
Complete network addressing information for all connected devices, including MAC addresses (hardware identifiers) and IP addresses (network identifiers) for Wi-Fi-connected devices.
ESP-NOW Network (CircleSquareShapeSongSwingalong)
Device
Component
MAC Address
Network Type
Input Device
Output Device
Player 1
XIAO ESP32-S3
D8:3B:DA:75:05:AC
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Player 2
XIAO ESP32-S3
D8:3B:DA:75:E1:9C
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Wi-Fi Network (Camera Livestream System)
Device
Component
MAC Address
IP Address
Network Type
Input Device
Output Device
Camera Node
XIAO ESP32-S3 Sense
[Device MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
Camera module, Button
OLED (SSD1306, 0x3C), HTTP Server
Client Device
Web Browser
[Client MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
N/A
Display (receives MJPEG stream)
Note: MAC addresses are hardware identifiers unique to each ESP32-S3 device. IP addresses are assigned dynamically via DHCP when connecting to a Wi-Fi network. For ESP-NOW communication, only MAC addresses are used (no IP addresses required). The camera system's IP address is printed to the Serial Monitor upon Wi-Fi connection establishment.
Design Files
Complete design files for networked systems including ESP-NOW multiplayer game and Wi-Fi camera streaming implementations with Arduino firmware and configuration files.
ESP-NOW Multiplayer Game (CircleSquareShapeSongSwingalong)
Arduino code for ESP-NOW wireless multiplayer game with MAC address-based player identification and synchronized game state management.
Key Features:
ESP-NOW wireless peer-to-peer communication
MAC address-based player identification (D8:3B:DA:75:05:AC and D8:3B:DA:75:E1:9C)
Arduino code for ESP32-S3 camera livestreaming over Wi-Fi using MJPEG protocol and Edge AI face detection using FOMO models from Edge Impulse.
Camera Livestream Pseudocode:
SETUP:
1. Initialize Serial communication (115200 baud)
2. Configure camera pins (from camera_pins.h)
3. Create camera_config_t structure
4. Initialize camera with esp_camera_init()
5. Connect to Wi-Fi network
6. Start HTTP server with stream handler
STREAM_HANDLER:
1. Set HTTP response type to "multipart/x-mixed-replace"
2. Enter loop: capture frame, send via HTTP, repeat
Key insights and learnings from working with networking and communications protocols.
Contributions
Acknowledgements and team roles for networking and communications work.
ESP-NOW Multiplayer Game
Developed CircleSquareShapeSongSwingalong multiplayer game with ESP-NOW wireless communication during Week 2. See Week 2 documentation for details.
Wi-Fi Camera Streaming System
Developed camera livestreaming and Edge AI face detection system during Week 10. See Week 10 documentation for details.
Ethical AI Use
Transparent documentation of AI assistance used in this week's networking and communications work.
AI-Assisted Week 11 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 11 documentation page, including networking protocols overview, group assignment placeholder, individual assignment sections summarizing ESP-NOW multiplayer game and Wi-Fi camera streaming systems, network address tables, and all formatting and styling. The AI helped refine and organize content from Week 2 and Week 10 into professional, succinct networking documentation while preserving key technical details.
[Placeholder: Complete AI assistance transcript will be added here after page completion]
This week focuses on connecting devices through wired and wireless networks. We'll explore communication protocols, network addressing, and how to build networked systems with local input and output devices.
Understanding wired and wireless communication protocols
Learning network addressing and bus architectures
Implementing networked nodes with input and output devices
This Week's Goals
Network Protocols Learn about ESP-NOW, Wi-Fi, I²C, SPI, UART, and other communication protocols
Network Addressing Understand MAC addresses, IP addresses, and bus addressing schemes
Networked Systems Design, build, and connect wired or wireless nodes with local I/O devices
Assignments
Group Assignment Send a message between two projects
Individual Assignment Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s)
Tools & Materials
ESP32-S3 Microcontroller Boards
Wi-Fi Access Point
OLED Displays (SSD1306)
Camera Modules
Touch Sensors
Training Documentation
Training materials and documentation for networking and communications protocols.
Recitation Notes
[Placeholder: Recitation notes will be added here]
Networking Protocols Overview
Networking and communications enable devices to exchange data through wired and wireless connections. Understanding different protocols helps select the right communication method for each application.
Wired Communication
UART/USART — Asynchronous serial communication (RS-232, RS-422, RS-485)
I²C/TWI — Two-wire interface with SCL/SDA, requires pull-up resistors
SPI — Serial Peripheral Interface with MISO/MOSI/CS/SCK lines
USB — Universal Serial Bus for device communication
Ethernet — Wired network communication
Wireless Communication
ESP-NOW — Low-power peer-to-peer communication for ESP32 devices
Design, build, and connect wired or wireless node(s) with network or bus addresses and local input &/or output device(s). This assignment demonstrates two networked systems: an ESP-NOW multiplayer game and a Wi-Fi camera streaming system with edge AI processing.
Networked System 1: CircleSquareShapeSongSwingalong (ESP-NOW)
A collaborative multiplayer game featuring geometric shape interactions, synchronized gameplay between two ESP32-S3 devices using ESP-NOW wireless communication. The system uses MAC address-based player identification and real-time state synchronization for coordinated gameplay. See Week 2 documentation and design files for complete details.
Design & Build
The system consists of two XIAO ESP32-S3 development boards, each with an SSD1306 OLED display (128x64) and capacitive touch sensors. The boards communicate wirelessly using ESP-NOW protocol, enabling low-latency peer-to-peer communication without requiring a Wi-Fi access point.
Network Type & Protocol
Network Type: Wireless peer-to-peer (ESP-NOW) Protocol: ESP-NOW (Espressif's proprietary low-power wireless communication protocol) Addressing Scheme: MAC address-based device identification
Input & Output Devices
Input Devices: Capacitive touch sensors (6 touch pads per device) for player controls (left, right, jump)
Output Devices: SSD1306 OLED display (128x64, I²C address 0x3C) for game rendering and player state visualization
Shape Song Swing Along educational content integration and gameplay
Circle and square shape interaction gameplay mechanics
Connections
Each ESP32-S3 board connects to an OLED display via I²C (SDA pin 5, SCL pin 6) and reads touch sensor inputs from GPIO pins. The ESP-NOW communication is handled entirely through the ESP32-S3's built-in Wi-Fi radio, requiring no external hardware connections.
Networked System 2: Camera Livestream & Edge AI (Wi-Fi)
A Wi-Fi-enabled camera system using ESP32-S3's built-in camera and HTTP server capabilities to stream JPEG frames over Wi-Fi using MJPEG (Motion JPEG) protocol. The system also includes edge AI face detection using a FOMO (Faster Objects, More Objects) model from Edge Impulse for real-time person tracking. See Week 10 documentation and design files for complete details.
Design & Build
The system uses a XIAO ESP32-S3 Sense development board with an integrated camera module. The camera captures frames at QQVGA (160x120) or QVGA resolution, processes them through an Edge AI inference pipeline, and streams the results over Wi-Fi via HTTP multipart response. The system can also display camera output and inference results on an OLED display connected via I²C.
Network Type & Protocol
Network Type: Wireless local area network (Wi-Fi) Protocol: HTTP over Wi-Fi (802.11), MJPEG streaming Addressing Scheme: IP address (DHCP-assigned) and MAC address (hardware identifier)
Input & Output Devices
Input Devices: Camera module (integrated on XIAO ESP32-S3 Sense) for image capture, button for capture trigger
Output Devices: OLED display (SSD1306, 128x64, I²C address 0x3C) for displaying camera frames and inference results, Wi-Fi HTTP server for remote streaming
Wi-Fi livestream interfaceCamera feed accessible over Wi-Fi for remote monitoring and control during operation.
Wi-Fi livestream testInitial Wi-Fi livestream test demonstrating remote camera access and feed quality.MIT Wi-Fi livestreamLivestream working on MIT network, confirming network compatibility and stability.Edge AI face detectionReal-time face detection running on-device using edge AI models for person tracking and interaction.
Connections
The camera module is integrated directly on the XIAO ESP32-S3 Sense board, connected via parallel data bus (Y2-Y9), control signals (XCLK, PCLK, VSYNC, HREF), and I²C interface (SIOD, SIOC). The OLED display connects via I²C (SDA pin 5, SCL pin 6) with pull-up resistors. Wi-Fi connection is established through the ESP32-S3's built-in Wi-Fi radio.
Download Design Files
camera_stream.zip — Complete camera stream project (includes .ino and .h files)
Complete network addressing information for all connected devices, including MAC addresses (hardware identifiers) and IP addresses (network identifiers) for Wi-Fi-connected devices.
ESP-NOW Network (CircleSquareShapeSongSwingalong)
Device
Component
MAC Address
Network Type
Input Device
Output Device
Player 1
XIAO ESP32-S3
D8:3B:DA:75:05:AC
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Player 2
XIAO ESP32-S3
D8:3B:DA:75:E1:9C
ESP-NOW (P2P)
Touch sensors (6 pads)
OLED (SSD1306, 0x3C)
Wi-Fi Network (Camera Livestream System)
Device
Component
MAC Address
IP Address
Network Type
Input Device
Output Device
Camera Node
XIAO ESP32-S3 Sense
[Device MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
Camera module, Button
OLED (SSD1306, 0x3C), HTTP Server
Client Device
Web Browser
[Client MAC]
192.168.x.x (DHCP)
Wi-Fi (802.11)
N/A
Display (receives MJPEG stream)
Note: MAC addresses are hardware identifiers unique to each ESP32-S3 device. IP addresses are assigned dynamically via DHCP when connecting to a Wi-Fi network. For ESP-NOW communication, only MAC addresses are used (no IP addresses required). The camera system's IP address is printed to the Serial Monitor upon Wi-Fi connection establishment.
Design Files
Complete design files for networked systems including ESP-NOW multiplayer game and Wi-Fi camera streaming implementations with Arduino firmware and configuration files.
ESP-NOW Multiplayer Game (CircleSquareShapeSongSwingalong)
Arduino code for ESP-NOW wireless multiplayer game with MAC address-based player identification and synchronized game state management.
Key Features:
ESP-NOW wireless peer-to-peer communication
MAC address-based player identification (D8:3B:DA:75:05:AC and D8:3B:DA:75:E1:9C)
Arduino code for ESP32-S3 camera livestreaming over Wi-Fi using MJPEG protocol and Edge AI face detection using FOMO models from Edge Impulse.
Camera Livestream Pseudocode:
SETUP:
1. Initialize Serial communication (115200 baud)
2. Configure camera pins (from camera_pins.h)
3. Create camera_config_t structure
4. Initialize camera with esp_camera_init()
5. Connect to Wi-Fi network
6. Start HTTP server with stream handler
STREAM_HANDLER:
1. Set HTTP response type to "multipart/x-mixed-replace"
2. Enter loop: capture frame, send via HTTP, repeat
Key insights and learnings from working with networking and communications protocols.
Contributions
Acknowledgements and team roles for networking and communications work.
ESP-NOW Multiplayer Game
Developed CircleSquareShapeSongSwingalong multiplayer game with ESP-NOW wireless communication during Week 2. See Week 2 documentation for details.
Wi-Fi Camera Streaming System
Developed camera livestreaming and Edge AI face detection system during Week 10. See Week 10 documentation for details.
Ethical AI Use
Transparent documentation of AI assistance used in this week's networking and communications work.
AI-Assisted Week 11 Page Creation and Assignment Documentation
Cursor AI assisted with creating the complete Week 11 documentation page, including networking protocols overview, group assignment placeholder, individual assignment sections summarizing ESP-NOW multiplayer game and Wi-Fi camera streaming systems, network address tables, and all formatting and styling. The AI helped refine and organize content from Week 2 and Week 10 into professional, succinct networking documentation while preserving key technical details.
[Placeholder: Complete AI assistance transcript will be added here after page completion]
Verifying the highlights section links are correct:
Verifying the file structure is complete. Summary of what's been created:
1. Created week11.html from week8.html template
2. Updated title and headers for Networking & Communications
3. Added networking resources from the MIT Academy page
4. Created recitation card placeholder
5. Created group assignment placeholder
6. Created individual assignment with summaries of both projects
7. Added network address tables
8. Embedded images and videos
9. Added download links for design files
10. Updated all sections (Reflections, Contributions, AI Use)
11. Verified index.html link
The file should be complete. Verifying the structure one more time:
Summary
Created week11.html for Networking & Communications with:
1. Created week11.html — copied from week8.html template
2. Updated all content — changed from Output Devices to Networking & Communications
3. Added networking resources — populated from the MIT Academy networking page
4. Created recitation card — placeholder section added
5. Group assignment — placeholder for "send a message between two projects"
6. Individual assignment — includes:
- CircleSquareShapeSongSwingalong summary (ESP-NOW network) with links to Week 2
- Camera Stream/System Code summary (Wi-Fi network) with links to Week 10
- Design, build, connections details
- Input/output devices listed
- Network type and protocol information
- Network address tables with MAC addresses and IP addresses for both networks
- All relevant images and videos embedded
- Download links for all design files
7. Updated all sections — Reflections, Contributions, AI Use sections updated
8. Verified index.html — link to week11.html is already present
The page is complete and ready. You can fill in the group assignment details and any additional network address information in the morning. All images, videos, and download links are properly embedded and linked.
Download Options
For the complete technical details and full conversation transcript:
![[Profile Image Placeholder]](profile.jpg)
This work is licensed under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
