Symmetry Breaking for k-Robust Multi-Agent Path Finding

During Multi-Agent Path Finding (MAPF) problems, agentscan be delayed by unexpected events. To address suchsituations recent work describes k-Robust Conflict-BasedSearch (k-CBS): an algorithm that produces coordinated andcollision-free plan is robust for up tokdelays. In thiswork we introducing a variety of pairwise symmetry break-ing constraints, specific tok-robust planning, can effi-ciently find compatible and optimal paths pairs con-flicting agents. We give thorough description the newconstraints report large improvements to success rate ina range domains including: (i) classic MAPF benchmarks;(ii) automated warehouse and; (iii) on maps fromthe 2019 Flatland Challenge, recently introduced railwaydomain wherek-robust planning fruitfully applied toschedule trains.