iCNS Distinguished Lecture: Adaptive BarrierNet for Safe and Scalable Robot Learning

ABSTRACT

Safety is central to autonomous systems/robots since a single failure could lead to catastrophic results. In unstructured complex environments where system states and environment information are not available, the safety-critical control problem is much more challenging. In this talk, I will first discuss safety from a control theoretic perspective with Control Barrier Functions (CBFs). CBFs capture the evolution of the safety requirements during the execution of a control system and can be used to guarantee safety for all times due to their forward invariance. Next, this talk will introduce an approach for extending the use of CBFs to machine learning-based control, using differentiable CBFs that are end-to-end trainable and adaptively guarantee safety using environmental dependencies. These novel safety layers give rise to new neural network (NN) architectures such as what we have termed the BarrierNet and Adaptive BarrierNet. The proposed methods have been applied to various robotic systems, both in simulations and in real robot experiments.

BIOGRAPHY

Wei Xiao is currently an assistant professor in the WPI robotics engineering department. He was a postdoctoral associate at the Computer Science and Artificial Intelligence lab (CSAIL), Massachusetts Institute of Technology. Before that, he received his Ph.D. degree from the Boston University in 2021. His research interests include safety-critical control theory and trustworthy machine learning, with a particular emphasis on robotics and multi-agent systems. He received an Outstanding Dissertation Award at Boston University, an Outstanding Student Paper Award at the 2020 IEEE Conference on Decision and Control, and a Best Paper Nomination at ACM/IEEE ICCPS 2021.