Multi-robot Cooperative Pathfinding: A Decentralized Approach

When robots perform teamwork in a shared workspace, they might be confronted with the risk of blocking each other’s ways, which will result in conflicts or interference among the robots. How to plan collision-free paths for all the robots is the major challenge issue in the multi-robot cooperative pathfinding problem, in which each robot has to navigate from its starting location to the destination while keeping avoiding stationary obstacles as well as its teammates. In this paper, we present a novel fully decentralized approach to this problem. Our approach allows the robots to make real-time responses to the dynamic environment and can resolve a set of benchmark deadlock situations subject to complex spatial constraints in the robots’ workspace. When confronted with conflicting situations, robots can employ waiting, dodging, retreating and turning-head strategies to make local adjustments. In addition, experimental results show that our proposed approach provides an efficient and competitive solution to this problem.