10-10

Leveraging Physics and Data for Robust Autonomy in Dynamic Environments

Robots and autonomous systems are giving us unprecedented access to landscapes and habitats, both big and small.  They provide in-situ monitoring and can adapt their strategies to respond to various external stimuli.  These systems enable us to interact more richly and extensively with the world we live in, better our understanding of its complexities, and assist in the discovery of new processes and phenomena.   Nevertheless, the dynamics of the natural world is complex and ever-changing, which makes autonomy fundamentally difficult.  As such, high-fidelity models of the environment and of the interactions of robots with the environment are critical for achieving reliable and resilient autonomy.   Advances in data-driven methods have opened new pathways to better describe these complex environments and interactions and have enabled the synthesis of more robust behavioral strategies for robots.  However, these approaches have limited interpretability, generalizability, and resiliency, and require large amounts of training data that is often costly to obtain in a robotics context.  A way to address these shortcomings is to blend physics-based knowledge with empirical data.  In this talk, I will describe my group’s attempt to bridge the gap between physics-based and data-driven methods to improve model performance, increase sample efficiency, and enhance the generalizability of learned models.  

Bio: M. Ani Hsieh is an Associate Professor in the Department of Mechanical Engineering and Applied Mechanics at the University of Pennsylvania.  She is also the Deputy Director of the General Robotics, Automation, Sensing, and Perception (GRASP) Laboratory and Program Chair for the Robotics MSE Program.  Her research interests lie at the intersection of robotics, multi-agent systems, and dynamical systems theory.  She received her B.S. in Engineering and B.A. in Economics from Swarthmore College and her PhD in Mechanical Engineering from the University of Pennsylvania.  Prior to Penn, she was an Associate Professor in the Department of Mechanical Engineering and Mechanics at Drexel University.  Hsieh is the recipient of a 2012 Office of Naval Research (ONR) Young Investigator Award and a 2013 National Science Foundation (NSF) CAREER Award.