We consider a large-scale multi-robot path planning problem in a cluttered environment. Our approach achieves real-time replanning by dividing the workspace into cells and utilizing a hierarchical planner. Specifically, multi-commodity flow-based high-level planners route robots through the cells to reduce congestion, while an anytime low-level planner computes collision-free paths for robots within each cell in parallel. Despite resulting in longer paths compared to the baseline multi-agent pathfinding algorithm, our method produces a solution with significant improvement in computation time. Specifically, we show empirical results of a 500-times speedup in computation time compared to the baseline multi-agent pathfinding approach on the environments we study. We account for the robot's embodiment and support non-stop execution when replanning continuously. We demonstrate the real-time performance of our algorithm with up to 142 robots in simulation, and a representative 32 physical Crazyflie nano-quadrotor experiment.

翻译：本文研究杂乱环境中的大规模多机器人路径规划问题。我们通过将工作空间划分为单元并采用分层规划器实现实时重规划。具体而言，基于多商品流的高层规划器将机器人引导通过各单元以减少拥塞，而任意时间低层规划器则并行计算每个单元内机器人的无碰撞路径。尽管与基准多智能体路径规划算法相比会生成更长的路径，但本方法在计算时间上实现了显著改进。实验结果表明，在所研究环境中，本方法的计算速度比基准多智能体路径规划方法提升了500倍。我们考虑了机器人的具体形态特征，并在连续重规划时支持不间断执行。通过仿真中多达142个机器人以及具有代表性的32个实体Crazyflie纳米四旋翼飞行器实验，验证了本算法的实时性能。