This project proposes to push the limits of autonomous vehicles in terms of speed, precision handling, and safety. Autonomous controllers must manage both path planning and vehicle control under extreme conditions. We aim to model and simulate the dynamical vehicle system, while using system identification capabilities based on real-data from transportation databases, and planning and control algorithms for the model. Compared to existing systems, which are based solely on physics based models, our use of models derived from real world driving conditions will provide a more realistic simulation of the complex variety of variables encountered in a street race driving scenario.

I am a 6-2 and 18 double major with two years of research experience in CSAIL & Senseable City Lab. In my last UROP, I worked on optimizing gradient descent algorithms in the context of deep learning. My expertise is machine learning, real-time data analysis & modeling. I am also fascinated with the rapid advances in robotics, so I was thrilled to be accepted into RLG to work on contact- aware state estimation algorithms.