Scalable Multi-Robot Motion Planning Using Guidance-Informed Hypergraphs

In this work, we present a multi-robot planning framework that leverages guidance about the problem to efficiently search the planning space. This guidance captures when coordination between robots is necessary, allowing us to decompose the intractably large multi-robot search space while limiting risk of inter-robot conflicts by composing relevant robot groups together while planning. Our framework additionally supports planning with kinodynamic constraints through our conflict resolution structure. This structure also improves the scalability of our approach by eliminating unnecessary work during the construction of motion solutions. We also provide an application of this framework to multiple mobile robot motion planning in congested environments using topological guidance. Our previous work has explored using topological guidance, which utilizes information about the robots' environment, in these multi-robot settings where a high degree of coordination is required of the full robot group. In real-world scenarios, this high level of coordination is not always necessary and results in excessive computational overhead. Here, we leverage our novel framework to achieve a significant improvement in scalability and show that our method efficiently finds paths for robot teams up to an order of magnitude larger than existing state-of-the-art methods in congested settings with narrow passages in the environment.