Research
Research
Seminars
Events Calendar
Seminars
Data-Driven Formal Methods for Assured Cyber-Physical Systems in Contested Environments
3:30 pm
ASE 1.126
Abstract: Recent advances in computing have led to the emergence of autonomous cyber-physical systems (e.g., self-driving cars and unmanned aerial vehicles) that can profoundly benefit human society. These systems are frequently deployed to perform complex tasks in critical applications. A common approach to assure their functionality is to use formal methods, i.e., express the control tasks in formal languages (e.g., temporal logic) and design/verify the controllers with automated and mathematically rigorous computer algorithms. However, traditional formal methods require full knowledge of the system model and thus are unsuitable for systems working in unknown and contested environments. This talk will introduce recent progress in data-driving methods for formal design and verification with unknown system models. We will discuss how to 1) use reinforcement learning to design controllers for temporal logic tasks and 2) verify their functionality (e.g., robustness and resiliency) with statistical model checking. We will close with thoughts on generalizing these works to complex systems using physics-informed deep learning.
Bio: Yu Wang is an Assistant Professor in the Department of Mechanical and Aerospace Engineering of the University of Florida (UF) and the Group Lead in Autonomous and Connected Vehicles of UF Transportation Institute. He was a Postdoctoral Associate at the Department of Electrical and Computer Engineering at Duke University. He received his Ph.D. degree in Mechanical Engineering and M.S. in Statistics and Mathematics from the University of Illinois at Urbana-Champaign (UIUC). His research focuses on cyber-physical systems, assured autonomy, formal methods, and machine learning. His work on statistical model checking was a Best Paper Finalist at the ACM SIGBED International Conference on Embedded Software (EMSOFT) in 2019.
Sign Up for Seminar Announcements
To sign up for our weekly seminar announcements, send an email to sympa@utlists.utexas.edu with the subject line: Subscribe ase-em-seminars.