Control barrier functions and neural networks for handling risk and uncertainty in autonomous systems

Abstract:  Autonomous Cyber-Physical Systems (CPS) typically operate in environments which are characterized by various forms of uncertainty. Nevertheless, safety of these systems needs to be quantified and guaranteed to the desired degree. In this talk, we build upon the theory of Control Barrier Functions (CBF) to address the challenges in operating in uncertain environments. First, we introduce a new notion of risk-aware CBF for stochastic dynamical systems. Then, we discuss the need for learning enabled CBF to address robustness, high level-mission requirements, and real-time operation. We demonstrate the applicability of our methods to simulated highway driving scenarios, and to simulated mobile robots navigating in confined environments.

Bio:  Georgios Fainekos (aka Dr. ΓΦ) is a Senior Principal Scientist at Toyota Motor North America R&D (within TRINA a division of AMRD). He received his Ph.D. in Computer and Information Science from the University of Pennsylvania in 2008 where he was affiliated with the GRASP laboratory. He holds a Diploma degree (B.Sc. & M.Sc.) in Mechanical Engineering from the National Technical University of Athens. Among other professional roles, he has been a tenured faculty of Computer Science and Computer Engineering at Arizona State University, and a Postdoctoral Researcher at NEC Laboratories America in the System Analysis & Verification Group. He is currently working on Cyber-Physical Systems (CPS) and robotics with a focus on Automated Driving Systems (ADS). His technical expertise is on applied logic, formal verification & requirements, testing, control theory, artificial intelligence, and optimization. In 2013, Dr. Fainekos received the NSF CAREER award and the ASU SCIDSE Best Researcher Junior Faculty Award. He has also been recognized with the top 5% teacher award in 2019 and 2021. His research has received several awards and nominations (e.g., IEEE CASE 2021, IEEE ITSC 2019, ACM HSCC 2019, IEEE/ACM MEMOCODE 2019), and the 2008 Frank Anger Memorial ACM SIGBED/SIGSOFT Student Award. In 2016, Dr. Fainekos was the program co-Chair for the ACM International Conference on Hybrid Systems: Computation and Control (HSCC).

***Event will take place in hybrid format. The location for in-person attendance will be room 1311 EECS.   Attendance will also be possible via Zoom. Zoom link and password will be distributed to the Controls Group e-mail list-serv.

To join this list-serv, please send an (empty) email message to [email protected] with the word “subscribe” in the subject line. To cancel your subscription, send an (empty) email to the same address with the word “unsubscribe” in the subject line.  Zoom information is also available upon request to Michele Feldkamp (careymrz@umich.edu).