Vegetation Classification UGV

Acknowledgements

Karl Iagnemma for being a great mentor, Matt McDaniel for tackling every problem with ease, Chris Brooks for his guidance, Takayuki Nishihata for helping test and develop the robotic platform and the rest of the Robotic Mobility Group for their support as well.

Related Links

Internal Project Website (Password Required)
MIT Robotic Mobility Lab

“When a robot dies, you don’t have to write a letter to its mother.”

- P.W. Singer
Unmanned ground vehicles (UGVs) will play an important role in the nation’s next-generation ground forces. Unmanned systems need to be able to detect obstacles and gather environmental data in dangerous environments all while moving autonomously. This project focuses on the classification and characterization of unstructured, vegetated environments from UGV platforms, specifically, the problem of segmenting tree stems from surrounding foliage and calculating stem diameter and spacing.

What I did

As a group, largely due to Matt McDaniel’s work, we were able to develop three unique classification capabilities for our UGV. The first was a ground plane estimation algorithm that is capable of accurately identifying the ground plane when given a LIDAR scan of a forest. Second, we developed a method for estimating stem diameters accurately and incorporated that into our previous work. Third, we created an algorithm able to determine stem spacing and use this data product for motion planning.