Learning, introspection, and anticipation for effective and reliable task planning under uncertainty: towards household robots comfortable with missing knowledge

Title: Learning, introspection, and anticipation for effective and reliable task planning under uncertainty: towards household robots comfortable with missing knowledge
 
Abstract: The next generation of service and assistive robots will need to operate under uncertainty, expected to complete tasks and perform well despite missing information about the state of the world or the future needs of itself and other agents. Many existing approaches turn to learning to overcome the challenges of planning under uncertainty, yet are often brittle or myopic, limiting their effectiveness. Our work introduces a family of model-based approaches to long-horizon planning under uncertainty that augment (rather than replaces) planning with estimates from learning, allowing for both high-performance and reliability-by-design.

In this talk, I will present a number of recent and ongoing projects that improve long-horizon navigation and task planning in uncertain home-like environments. First, I will discuss our recent developments that improve performance and reliability in unfamiliar environments—environments potentially dissimilar from any seen during training—with a technique we call "offline alt-policy replay," which enables fast and reliable deployment-time policy selection despite uncertainty. Second, I will discuss "anticipatory planning," by which our robot anticipates and avoids side effects of its actions on undetermined future tasks it may later be assigned; our approach guides the robot towards behaviors that encourage preparation and organization, improving its performance over lengthy deployments.

Bio: Greg is an Assistant Professor of Computer Science at George Mason University, where he runs the Robotic Anticipatory Intelligence & Learning (RAIL) Group and is the director of the GMU Autonomous Robotics Lab. His research, at the intersection of robotics, planning, and machine learning, is centered around developing representations for planning and learning that allow robots to better understand the impact of their actions, so that they may plan quickly, intelligently, and reliably in a dynamic and uncertain world. Before joining Mason, he received his PhD in 2020 from MIT’s Department of Electrical Engineering and Computer Science and previously graduated summa cum laude from Cornell University with a B.S. in Applied and Engineering Physics. His work was a finalist for Best Paper at the 2018 Conference on Robot Learning, at which he was additionally awarded Best Oral Presentation.