Efficient Multi-Robot Motion Planning with Precomputed Translation-Invariant Edge Bundles

2026-05-10

AI Summary

This work addresses the inefficiency and poor scalability of multi-robot motion planning under dense spatiotemporal constraints by introducing KiTE-Extend, a novel mechanism that leverages an offline-constructed library of translation-invariant trajectory segments to guide online action selection. By incorporating translation-invariant edge bundles into multi-robot kinodynamic planning for the first time, KiTE-Extend significantly enhances the search efficiency of sampling-based kinodynamic planners without altering state propagation or collision checking procedures and without compromising theoretical guarantees. Experimental results demonstrate that KiTE-Extend consistently reduces planning time and substantially improves both scalability and success rates across diverse kinodynamic models and environments, benefiting the three dominant planning paradigms: centralized, prioritized, and conflict-based approaches.

Abstract

Solving multi-robot motion planning (MRMP) requires generating collision-free kinodynamically feasible trajectories for multiple interacting robots. We introduce Kinodynamic Translation-Invariant Edge Bundles or KiTE-Extend, a planner-agnostic action selection mechanism for sampling-based kinodynamic motion planning. KiTE-Extend uses a library of trajectory segments computed offline to guide action selection during online planning, improving the ability of existing planners to identify feasible motion segments without altering state propagation, collision checking, or cost evaluation, and without changing their theoretical guarantees. While KiTE-Extend can modestly improve single-agent planners, its benefits are most clear in the multi-agent setting, where it is able to explore more effectively and significantly improve planning through the dense spatiotemporal constraints introduced by robot-robot interaction. Through experiments on multiple kinodynamic systems and environments, we show that KiTE-Extend reduces planning time and improves scalability across the three most common MRMP paradigms: centralized, prioritized, and conflict-based.

Problem

• multi-robot motion planning
• kinodynamic feasibility
• collision-free trajectories
• spatiotemporal constraints
• planning scalability

Innovation

• multi-robot motion planning
• kinodynamic planning
• precomputed edge bundles
• translation-invariant
• planner-agnostic