PRECISE's Safe Autonomy Seminar: Provably-Correct Neurosymbolic Controllers for Autonomous Cyber-Physical Systems

PRECISE's Safe Autonomy Seminar: Provably-Correct Neurosymbolic Controllers for Autonomous Cyber-Physical Systems
Tue, October 11, 2022 @ 2:00pm EDT
University of Pennsylvania
Levine Hall - Room 279
3330 Walnut Street
Philadelphia, PA 19104
Speaker
Yasser Shoukry
Electrical and Systems Engineering
University of California, Irvine
Abstract

While conventional reinforcement learning focuses on designing agents that can perform one task, meta-learning aims, instead, to solve the problem of designing agents that can generalize to different tasks (e.g., environments, obstacles, and goals) that were not considered during the design or the training of these agents. In this spirit, we consider the problem of training a provably safe Neural Network (NN) controller for uncertain nonlinear dynamical systems that can generalize to new tasks that were not present in the training data while preserving strong safety and correctness guarantees. I will present two complementary neurosymbolic approaches. In the first approach, I will show how to use ideas from symbolic control to provide guarantees on the training of NN controllers. In the second approach, I will show how to use NN to guide the design of symbolic controllers. I will discuss the theoretical guarantees governing the correctness and optimality of these neurosymbolic controllers and show experimental validation of our approach.

Speaker Bio

Yasser Shoukry is an Assistant Professor in Electrical Engineering and Computer Science at the University of California, Irvine, where he leads the Resilient Cyber-Physical Systems Lab. Before joining UCI, he spent two years as an assistant professor at the University of Maryland, College Park. His research focuses on the design and implementation of resilient, AI-enabled, cyber-physical systems and IoT. His work in this domain was recognized by the Early Career Award from the IEEE Technical Committee on Cyber-Physical Systems in 2021, the 2019 NSF CAREER Award, and the Distinguished Dissertation Award from UCLA EE department in 2016. He is also the recipient of the 2019 George Corcoran Memorial Award UMD for his contributions to teaching and educational leadership in the field of CPS and IoT.