"Learning Where to Trust Unreliable Models for Deformable Object Manipulation"

Thursday, Sept. 30 @ 11AM PST 

Zoom: https://ucsd.zoom.us/j/94406976474

Speaker:  Professor Dmitry Berenson


Seminar Abstract

The world outside our labs seldom conforms to the assumptions of our models. This is especially true for dynamics models used in control and motion planning for complex high-DOF systems like deformable objects. We must develop better models, but we must also accept that, no matter how powerful our simulators or how big our datasets, our models will sometimes be wrong. This talk will present our recent work on using unreliable dynamics models for the manipulation of deformable objects, such as rope. Given a dynamics model, our methods learn where that model can be trusted given either batch data or online experience. These approaches allow dynamics models to generalize to control and planning tasks in novel scenarios, while requiring much less data than baseline methods. This data-efficiency is a key requirement for scalable and flexible manipulation capabilities.

Bio: Dmitry Berenson is an Associate Professor in Electrical Engineering and Computer Science and the Robotics Institute at the University of Michigan, where he has been since 2016. Before coming to University of Michigan, he was an Assistant Professor at WPI (2012-2016). He received a BS in Electrical Engineering from Cornell University in 2005 and received his Ph.D. degree from the Robotics Institute at Carnegie Mellon University in 2011, where he was supported by an Intel PhD Fellowship. He was also a post-doc at UC Berkeley (2011-2012). He has received the IEEE RAS Early Career Award and the NSF CAREER award. His current research focuses on robotic manipulation, robot learning, and motion planning.