Xiaopan Zhang

Hello 👋! I am Xiaopan Zhang (张晓攀), a third-year Ph.D. student in Machine Learning at the Georgia Institute of Technology, advised by Professor Jiachen Li. My research interests include embodied AI agents, multi-robot systems, and reinforcement learning for robotics. I develop trustworthy algorithms for generalizable multi-robot coordination and robot-human collaboration in real-world environments.

My current research focuses on intervention-guided mobile manipulation: tracing failures across navigation, perception, and contact, coordinating physical recovery, and selectively adapting robot skills, residual controllers, and vision-language-action policies. I also work on foundation-model rewards for object-goal navigation and reliable communication and planning for heterogeneous robot teams.

I joined Georgia Tech in August 2026 after studying Electrical Engineering as a Ph.D. student at the University of California, Riverside from March 2024 to August 2026. During summer 2026, I was a Student Associate at Honda Research Institute USA, where I developed SituLaMP for multi-robot planning and recovery during execution. Previously, I was a Robotics Research Intern at AlphaZ, Inc., working on StratMamba for LiDAR-based obstacle avoidance and sim-to-real deployment.

I earned my M.S. in Computer Science from the University of Southern California in 2023, where I conducted research on quadruped robot teams in the Dynamic Robotics and Control Laboratory under Professor Quan Nguyen. I received my B.S. in Computer Science from the University of Michigan, Ann Arbor in 2021.

You can find more about my work on the projects, publications, and CV pages. Beyond research, I contribute to open-source projects and enjoy photography and travel.