Date: November 18, 2021
Time: 3:00pm
Register for this online seminar.
Abstract:
This talk will discuss the deployment of autonomous robots to perform long-term tasks in unknown and partially known environments. We will consider two different problems in this domain. The first is in improving robot performance over repeated executions of a task. This is achieved by learning the underlying structure and traversability patterns in the environment. The second is in adapting robot behaviour to user preferences. This is done through actively querying a user with different robot behaviours to elicit their preferences. For both these problems this talk will describe solution methods that combine learning, control and optimization to improve robot capabilities. The talk will conclude with a discussion of some of the fundamental challenges that remain to achieve long-term autonomy.
Biography:
Stephen L. Smith received his B.Sc. degree from Queen’s University, Canada, in 2003, his M.A.Sc. degree from the University of Toronto, Canada, in 2005, and his Ph.D. degree from the University of California, Santa Barbara, USA, in 2009. He is currently an Associate Professor in the Department of Electrical and Computer Engineering at the University of Waterloo, Canada, where he holds a Canada Research Chair in Autonomous Systems. He is also a faculty affiliate with the Vector Institute, in Toronto, Canada. From 2009 to 2011 he was a Postdoctoral Associate in the Computer Science and Artificial Intelligence Laboratory at the Massachusetts Institute of Technology.
Prof. Smith has received several awards including the Early Researcher Award from the Ontario Ministry of Research and Innovation in 2016, the NSERC Discovery Accelerator Supplement Award in 2015, and two Outstanding Performance Awards from the University of Waterloo. He is a licensed Professional Engineer (PEng) with the Professional Engineers Ontario, a Senior Member of the IEEE, an associate editor of the IEEE Transactions on Control of Networks Systems, and a General Chair of the 2021 30th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). His main research interests lie in control and optimization for autonomous systems, with a particular emphasis on robotic motion planning and coordination.