This week, Pulkit Katare who is part of the Human Centered Autonomy Lab will present!
Please join us, and stay afterwards to socialize with the other attendees (and eat cookies)!
Pulkit Katdare is a fourth year Ph.D Student in the Human Centered Autonomy Lab under Prof. Katherine Driggs-Campbell. In this talk, he is going to be talking about their recent submission to ICRA 2022 titled Off Environment Evaluation Using Convex Risk Minimization. While using robot learning, researchers often use simulators to train the robot and then deploy them on the real world. Robots trained in this manner tend to perform suboptimally in the real world. The reason behind this mismatch is because the simulators don’t generally capture un-certainties of the real world robot, a fact commonly referred to as the Sim2Real gap. In his work, he attempts to bridge this Sim2Real gap by estimating the difference between the simulator and the real world and uses it to augment the RL cost function to be much more reflective of the real world robots.