Title: Computational Symmetry and Learning for Robotics

Maani Ghaffari | U. Michigan Robotics

Abstract: Forthcoming mobile robots require efficient generalizable algorithms to operate in challenging and unknown environments without human intervention while collaborating with humans. Today, despite the rapid progress in robotics and autonomy, no robot can deliver human-level performance in everyday tasks and missions such as search and rescue, exploration, and environmental monitoring and conservation. In this talk, I will put forward a vision for enabling efficiency and generalization requirements of real-world robotics via computational symmetry and learning. I will walk you through structures that arise from combining symmetry, geometry, and learning in various foundational problems in robotics and showcase their performance in experiments ranging from perception to control. In the end, I will share my thoughts on promising future directions and opportunities based on lessons learned on the field and campus.

Bio: Maani Ghaffari received the Ph.D. degree from the Centre for Autonomous Systems (CAS), University of Technology Sydney, NSW, Australia, in 2017. He is currently an Assistant Professor at the Department of Naval Architecture and Marine Engineering and the Department of Robotics, University of Michigan, Ann Arbor, MI, USA, where he directs the Computational Autonomy and Robotics Laboratory (CURLY). His work on sparse, globally optimal kinodynamic motion planning on Lie groups received the best paper award finalist title at the 2023 Robotics: Science and Systems conference. He is the recipient of the 2021 Amazon Research Awards. His research interests lie in the theory and applications of robotics and autonomous systems. He has expertise in developing efficient generalizable algorithms for robot autonomy operating in unstructured, dynamic, and uncertain environments. He has developed geometric state estimation, geometric control methods, geometric deep neural network architectures (LieNeuron), information-theoretic motion planning, and mapping algorithms for mobile robots.