CBS-HT: Prioritized Safe Interval Path-Planning Algorithm for Heterogeneous Agricultural Robot Team

Existing multi-agent path-finding (MAPF) methods either assume homogeneous robots or require inter-robot communication, limiting their deployment in large-scale agricultural settings. We present conflict-based search for heterogeneous tasks (CBS-HT), a fixed-priority path planner for unpiloted ground vehicles (UGVs) performing monitoring, harvesting, and transportation. CBS-HT assigns initial priorities according to robot type and inter-workspace movement (e.g., field, sorting, warehouse) and integrates this priority scheme directly into a CBS-inspired high-level search, constraining only the lower-priority agent at each conflict. By design, CBS-HT relaxes strict completeness and optimality guarantees in exchange for practical real-time performance on large robot teams, reducing search complexity while preserving collision-free coordination. Three evaluation tiers–simulation, lab-scale, and orchard—test scalability, mission-level efficiency, and real-world robustness. Compared with an uncoordinated baseline, CBS-HT shortens high-priority robots’ travel distance by up to 19.1 m (13.5 %) and mission time by 28.4 s (13.2 %), while maintaining a 100 % collision-free success rate for tested instances. These results demonstrate that priority-aware safe-interval planning can deliver practical, communication-free coordination of heterogeneous UGV fleets in commercial orchards and is adaptable to diverse multi-robot agricultural operations.