I am a Ph.D. candidate in Computer Science and Engineering at the University of Connecticut. I received my M.S. degree in Statistics at UC Irvine in 2019 and my B.E. degree in Financial Mathematics in 2017 at Sothern University of Science and Technology. My research goal is to lay the foundations for AI-powered CPS, including ensuring efficiency, robustness, safety, and security for CPS through learning and optimization methods. My work has provided practical robust and efficient decision-making strategies for a variety of CPS including Intelligent Transportation, Connected Autonomous Vehicles, and Smart Cities. I published my work in several top conferences and journals including TMLR, IEEE TITS, IROS, ICRA, TCPS, and TMC. I have also been honored with Rising Stars in AI (KAUST AI Initiative), the NC State Building Future Faculty Program Fellow, the Synchrony Fellowship, the Predoctoral Prize for Research Excellence, the GE Advanced Manufacturing Fellowship, and the Cigna Graduate Scholarship.
Cyber-physical systems typically involve the tight integration between distributed computational intelligence, communication networks, and the physical world. Their performance and efficiency largely depend on the collaborative efforts of individual entities in the system. However, due to the increasing model complexity, ever-changing external environments, unpredictable internal dynamics, and high expectations of collective intelligence, these highly interconnected and integrated CPS pose new challenges and concerns about efficiency, robustness, safety, and security. The primary objective of my work is to establish a foundation for the collective intelligent decision-making of CPS (e.g. intelligent transportation systems, connected autonomous vehicles, and power networks), with a focus on efficiency, robustness, safety, and security. My approach involves: Developing robust multi-agent reinforcement learning-based decision-making strategies for interconnected CPS. Proposing data-driven distributionally robust optimization decision-making strategies for mobile CPS. Enhancing the safety and security of CPS by integrated learning and control mechanisms, e.g., federated and constrained reinforcement learning.