Latest News

Excited to announce that I have stepped up as Team Lead for Caltech Racer's Indy Autonomous Challenge team. This is a full sized autonomous IndyNXT racecar capable of reaching speeds exceeding 155 mph that we have been using as a research platform. In addition to leading the design of the car's control systems, as lead I am now responsible with managing the project and pushing the team towards cool research ideas on multiple fronts. You can find some coverage in anticipation of an upcoming race in Caltech Magazine. The video below shows a fully autonomous lap at the legendary Laguna Seca Raceway, where our race will take place.


Also, in collaboration with my colleague Allison Pinosky, I will be presenting some recent work at the IEEE Conference on Automation Science and Engineering (CASE) on what it takes to make reinforcement algorithms learn from scratch in real-time on hardware. This work is an extension of my reinforcement learning work published in Nature Machine Intelligence, where I introduced a novel framework called MaxDiff RL.

About Me

I am an interdisciplinary roboticist interested in exploring how physics can inform and complicate robot learning. I combine insights from optimal control, reinforcement learning, and statistical physics to develop reliable real-time autonomy for hardware systems.

I am a Postdoctoral Scholar at the California Institute of Technology in the Autonomous Robotics and Control Lab, where I am advised by Profs. Soon-Jo Chung and Fred Hadaegh. I received a Ph.D. and M.S. in Mechanical Engineering from Northwestern University in 2024, where I was a Presidential Fellow under the supervision of Prof. Todd Murphey. I also received a B.S. in Engineering from Harvey Mudd College in 2017.