Building Internet of Vehicles with Cyber-Physical Resiliency: Stochastic Control, Fault-Tolerant Control, and Secure Control
Date: 2020/09/28 - 2020/09/28
Academic Seminar: Building Internet of Vehicles with Cyber-Physical Resiliency: Stochastic Control, Fault-Tolerant Control, and Secure Control
Speaker: Dr. Li Jin, New York University Tandon School of Engineering
Time: 9:00 -10:00, September 28th, 2020
Location: via Zoom (Meeting ID: 69010291306 Password: 1497)
We consider a class of resilient control problems for internet of vehicles (IoV). A resilient IoV is supposed to be adaptive to natural randomness, tolerant to cyber-physical faults, and survivable to malicious cyber attacks. However, we still lack systematic modeling, analysis, and design approaches to building resilient IoV. To address this challenge, we reinvent classical models to capture peculiar features of connected and autonomous vehicles. Using the reinvented models, we evaluate and optimize IoV performance in face of natural randomness. Our analysis is based on stochastic Lyapunov theory and dynamic programming. We propose novel models for a rather broad class of cyber-physical faults in IoV and design fault-tolerant control policies. In addition, we introduce game-theoretic models to evaluate security risk due to malicious attacks and to design protection/mitigation strategies. We focus on both theoretical stability/optimality guarantees and learning-based implementation. Our approaches are general and can be extended to a broader class of smart city applications.
Li Jin (金力) is an Assistant Professor in the Department of Civil and Urban Engineering at the New York University Tandon School of Engineering. He is also a core faculty member at the C2SMART Department of Transportation Center. He has a background in stochastic process, dynamic control, reinforcement learning, and optimization. He focuses on developing models, methods, and tools to address system design problems in connected and autonomous transportation systems. He is particularly interested in addressing operational/planning challenges due to either natural uncertainties or adversarial disruptions. Specific applications include vehicle platooning, smart intersections, ramp metering, and trip planning. Li joined NYU in Fall 2018 as a tenure-track assistant professor. He received the B.Eng. degree from Shanghai Jiao Tong University (上海交通大学), the M.S. degree from Purdue University, and the Ph.D. degree from the Massachusetts Institute of Technology. He is a recipient of the Ho-Ching and Hang-Ching Fund Award and Schoettler Scholarship Fund.