The authors propose a novel algorithm, Space-Order CBS, that can directly plan a Temporal Planning Graph (TPG) by reinterpreting a TPG as a set of space-visitation order paths. This allows them to explicitly minimize coordination between agents during the planning process.
Developing an efficient algorithm selection framework that considers both runtime and solution quality for suboptimal multi-agent path finding solvers.
Learnt local MAPF policies can be significantly improved in terms of success rate and scalability by using them in conjunction with heuristic search techniques like PIBT and LaCAM.