Mihir Rao

I recently graduated from UC Berkeley with a BS in EECS. I was lucky to be advised by Roei Herzig and Prof. Trevor Darrell, with whom I broadly worked on robot manipulation and policy robustness. I'm now a researcher at Mind Robotics.

Previously, I spent two summers at NVIDIA Robotics where I built PyNITROS along with a framework for Sim2Real deployment of Isaac Lab RL policies. I've also spent time at AUTOLab, where I worked with Prof. Ken Goldberg on Reinforcement Learning for Quadruped Locomotion. I'm primarily interested in building and improving general-purpose foundation models for robotics.

I also enjoy working on other personal projects, watching movies, playing tennis, anything car related, and I love meeting new people — feel free to contact me.