Resolving Head-On Conflicts for Multi-Agent Path Finding with Conflict-Based Search
This work addresses an incremental improvement for researchers and practitioners in multi-agent path planning by enhancing conflict resolution efficiency in CBS-based solvers.
The paper tackles the problem of efficiently resolving foreseeable conflicts in Conflict-Based Search for Multi-Agent Path Finding by introducing a head-on technique that processes conflicts and potential conflicts together in one split, resulting in improved performance for the CBSH solver.
Conflict-Based Search (CBS) is a popular framework for solving the Multi-Agent Path Finding problem. Some of the conflicts incur a foreseeable conflict in one or both of the children nodes when splitting on them. This paper introduces a new technique, namely the head-on technique that finds out such conflicts, so they can be processed more efficiently by resolving the conflict with the potential conflict all together in one split. The proposed technique applies to all CBS-based solvers. Experimental results show that the head-on technique improves the state-of-the-art MAPF solver CBSH.