Future autonomous systems will employ complex sensing, computation, and communication components for their perception, planning, control, and coordination. They could potentially operate in highly dynamic and uncertain environments with safety and security assurance.
To realize this vision, we have to better understand and address the challenges from the unknowns. Unexpected disturbances from component failures, environment interferences, and malicious attacks, the inherent uncertainties from system inputs and model inaccuracies, and the lack of analyzability of some machine learning techniques (particularly those based on neural networks) are all unknowns.
In this talk, Pro. Qi Zhu of Northwestern University will discuss these challenges and present some of his team’s recent work and open-source tools in this area. The talk will cover quantitative and formal methods for ensuring robust and safe application of neural networks in perception, decision making, and runtime adaptation, with the tools LayR, ReachNN, and POLAR; as well as cross-layer framework for mitigating execution disturbances (e.g., timing violations, soft errors, malicious attacks) using weakly-hard paradigm, with the tool SAW.
Qi Zhu is an Associate Professor at the ECE Department at Northwestern University. He received a 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 (CPS) and Internet of Things, safe and secure machine learning for CPS, cyber-physical security, and system-on-chip design, with applications in domains such as connected and autonomous vehicles, energy-efficient buildings, 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, and ACM TODAES 2016, best paper nominations at SIES 2016, ASP-DAC 2016, and ICCAD 2020. He is the Conference Chair of IEEE TCCPS, and VP of Young Professionals at IEEE CEDA.
He is an Associate Editor for IEEE TCAD, ACM TCPS, and IET Cyber-Physical Systems: Theory & Applications. He has served as a guest editor for the Proceedings of the IEEE, ACM TCPS, IEEE T-ASE, Elsevier JSA, and Elsevier Integration, the VLSI journal.