"Computational Symmetry and Learning for Robotics", Chien Erh Lin, Tzu-Yuan Lin, and Maani Ghaffari

This talk was given as part of the workshop "Equivariant Robotics: The Role of Symmetry Across Perception, Estimation, and Control" at IROS 2024. For the full workshop details, visit https://equirob2024.github.io/

Keynote Talk: "Computational Symmetry and Learning for Robotics" by Chien Erh (Cynthia) Lin and Tzu-Yuan (Justin) Lin, on behalf of Maani Ghaffari

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: Chien Erh (Cynthia) Lin and Tzu-Yuan (Justin) Lin are both senior PhD candidates in Robotics at the University of Michigan, working in the Computational Autonomy and Robotics Laboratory directed by their advisor Maani Ghaffari, on whose behalf they give this talk today, since he unfortunately could not be here in person. Dr. Ghaffari is an Assistant Professor in Naval Architecture and Marine Engineering and Robotics at The University of Michigan in Ann Arbor. He received his Ph.D. from the Centre for Autonomous Systems (CAS) at the University of Technology Sydney in 2017. His research interests lie in the theory and applications of robotics and autonomous systems. In particular, Cynthia focuses on robot perception and SLAM, and Justin’s work has explored robot state estimation, representation learning, geometric deep learning, and dynamics modeling using neural networks.