Research Project Title:
Robust Perception for Robots
abstract:Perception algorithms based on deep learning have been on the rise recently. The algorithms work well most of the time, but there are few guarantees of results. This presents a large problem for self-driving cars and other autonomous systems that must be robust to failure. This research project is to better understand current computer vision algorithms and to prove robustness of neural networks. I hope to do so by creating and analyzing feedback systems with perception in the loop.
I'm participating in this SuperUROP because I'm eager to gain research experience as I prepare for graduate school. After doing robotics UROPs freshman and sophomore year, I'm excited to commit to this rigorous project with hopes of contributing to the fields of computer vision and robotics.