Dmitry Berenson (UMichigan)
Title: Where to Trust and How to Adapt Learned Models for Motion Planning
Abstract: The world outside our labs seldom conforms to the assumptions used to train our models. No matter how powerful our simulators or how big our datasets, our models will sometimes be wrong because they will eventually encounter states or environments that are outside the distribution of the training data. This talk will present our recent work on determining where learned models can be trusted and how to adapt learned models to new scenarios. Focusing on dynamics models and sampling distributions for trajectory optimization, these methods are designed for motion planning for a wide range of robotic systems. Our methods provide statistical guarantees on where learned dynamics models can be trusted and strong empirical performance on adapting sampling distributions for trajectory optimization to environments that are radically different from those used in training.
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.