My research interests lie at the intersection of multi-agent systems and motion planning in robotics. During my undergraduate studies, I have focused primarily on Multi-Agent Path Finding (MAPF)—an NP-hard problem that poses significant challenges due to the curse of dimensionality. MAPF has important real-world applications, particularly in warehouse logistics systems such as those used by Amazon and Symbotic. My work aims to bridge the gap between abstract planning and real-world execution by developing MAPF algorithms that account for practical constraints. These include handling agents with heterogeneous speeds (MAPF with Asynchronous Actions), meeting time-sensitive requirements (MAPF with Deadlines), and incorporating kinematic constraints (Execution-Aware MAPF). I am open to collaborations in the MAPF domain, as well as in extending its techniques to other areas of robotics.

My previous and ongoing projects have all focused on search-based methods. While I value the theoretical guarantees and interpretability these approaches provide, I am also eager to explore the potential of learning-based methods. For instance, I am particularly interested in using learning techniques—such as reinforcement learning or imitation learning—as heuristics to guide decision-making in high dimension planning problems. At the same time, I am actively broadening my knowledge in areas such as multi-agent motion planning, multi-robot arm coordination, and emerging paradigms like diffusion models. I am curious whether insights from search-based MAPF methods could inspire new ideas or serve as strong priors in these related domains. I am always open to discussion and collaboration across these intersections.

I am seeking a Ph.D. position starting in Fall 2026 and plan to apply to programs in Robotics, Computer Science, Electrical Engineering, Mechanical Engineering, or Aerospace Engineering. Some of the above are questions I would like to explore during my PhD.