Title: Building Safe Embodied AI Systems

Abstract: Embodied AI systems are cyber-physical systems that employ advanced machine learning techniques to perceive, analyze, and interact with their environment. As these systems become more prevalent in fields such as self-driving cars and robotics, ensuring their safety has become a critical but challenging requirement. In this talk, I will discuss key challenges in building safe embodied AI systems, particularly those arising from uncertainties in system inputs, model inaccuracies, and the lack of analyzability in neural network-based components. I will present our work on tackling these challenges with a verification, design, and adaptation framework that ensures end-to-end, system-level safety. I will also briefly discuss our recent work on safety for foundation model-driven embodied AI systems.

Bio: Qi Zhu is a Professor in the ECE Department at Northwestern University. He earned his Ph.D. in EECS from the University of California, Berkeley in 2008 and a B.E. in CS from Tsinghua University in 2003. His research interests include design automation for cyber-physical systems (CPSs) and Internet of Things (IoTs), safe and robust machine learning for embodied AI systems, energy-efficient CPSs, cyber-physical security, and system-on-chip design, with applications in domains such as connected and autonomous vehicles, smart buildings, advanced manufacturing, wearable computing, and robotic systems. He is a recipient of the NSF CAREER award, the IEEE TCCPS Early-Career Award, and the Humboldt Research Fellowship for Experienced Researchers. He received best paper awards at DAC 2006, DAC 2007, ICCPS 2013, ACM TODAES 2016, and DATE 2022. He is the VP of Initiatives for IEEE CEDA and Conference Chair for IEEE TCCPS. He is an Associate Editor for IEEE TCAD, IEEE TCASAI, and ACM TCPS, and has served as a Guest Editor for the Proceedings of the IEEE, ACM TCPS, IEEE T-ASE, IEEE IoT Journal, Elsevier JSA, and Elsevier VLSI Integration.