CKSRI Seminar Series 2023 "Towards Rigorous Use of Neural Networks in Nonlinear Control"

Thank you to everyone who joined us today at CKSRI Seminar!

It’s been our great pleasure to have Prof. Sicun Gao sharing more on his research about nonlinear control design, including model-based stabilization, model-free reinforcement learning, and imitation learning from limited observations.

Abstract: Data-driven and learning-based approaches have become an indispensable part of automation and autonomous systems. Control and planning components that are neural network models challenge existing principled methods for ensuring the reliability and safety of these systems. By taking a numerical and statistical perspective on synthesis and verification, it is possible to still prove strong properties for highly nonlinear systems with neural control policies. To do so, we need to find value certificates, such as Lyapunov and barrier functions, that are themselves neural networks to capture the highly nonlinear value landscape of these systems. I will describe some of our work in this direction in different settings of nonlinear control design, including model-based stabilization, model-free reinforcement learning, and imitation learning from limited observations.

Short Bio: Sicun Gao is an Associate Professor in Computer Science and Engineering at the University of California, San Diego. He works on search and optimization algorithms for improving the quality of automation and autonomous systems. He is a recipient of the Air Force Young Investigator Award, Amazon Research Award, NSF Career Award, and Silver Medal for the Kurt Godel Research Prize. He received his PhD from Carnegie Mellon University and was a postdoctoral researcher at CMU and MIT.