I am a postdoctoral researcher at the Stanford Intelligent Systems Lab (SISL) in the Aeronautics and Astronautics Engineering department, mentored by Mykel Kochenderfer. I earned my Ph.D. in Mechanical Engineering from Carnegie Mellon University, where I was advised by Ding Zhao in the Safe AI Lab. My doctoral research focused on integrating machine learning with rare-event theory to simulate rare, safety-critical events in CPS. At SISL, I am involved in several industry-sponsored projects aimed at seamlessly integrating AI into CPS, with a focus on enhancing safety and adaptability in planning and navigation tasks under uncertainty across various applications in robotics, transportation, and sustainability.
My research focuses on more closely integrating AI with cyber-physical systems (CPS) to create systems that are not just efficient and powerful, but also safe and trustworthy. This involves making these systems resilient to a wide range of environmental challenges, safeguarding them against security threats, and ensuring transparency for both the people who build them and those who use them. To this end, my research is built on three main thrusts: embedding trustworthiness directly into the CPS development process, safely adapting these systems in real-time, and applying rigorous probabilistic methods for validation. These strategies incorporate advanced AI, simulation, and engineering techniques right from the start of the development process. Looking ahead, I plan to extend these techniques throughout the entire lifecycle of CPS, develop systems that can assist experts in performing safety-critical tasks, and use AI to enhance safety measures in critical sectors such as healthcare, critical mineral mining, and renewable energy management. By emphasizing trustworthiness, I believe CPS can rapidly evolve to meet emerging challenges and drive future innovations across various industries.