Intelligent Planning for Large-Scale Multi-Robot Coordination

Robots will play a crucial role in the future and need to work as team increasingly more complex applications. Advances robotics have laid hardware foundations for building large-scale multi-robot systems. But how coordinate robots intelligently is difficult problem. We believe that graph-search-based planning can systematically exploit combinatorial structure of coordination problems efficiently generate solutions with rigorous guarantees on correctness, completeness, solution quality. started one problem central many Multi-Agent Path Finding (MAPF) an NP-hard collision-free paths agents while minimizing their travel times. addressed MAPF from both (1) theoretical perspective by developing efficient algorithms solve large instances completeness optimality via variety AI optimization technologies, such constraint reasoning, heuristic search, stochastic local machine learning, (2) applicational algorithmic techniques integrating task execution various systems, mobile robot coordination, traffic management, drone swarm control, multi-arm assembly, character control video games. This paper part AAAI-23 New Faculty Highlights.