MR. POP: Multi-Robot Parallel Optimizing Planner for Almost-Surely Asymptotically Optimal Planning

2026-09-24

AI Summary

This study addresses the challenge of simultaneously achieving global optimality, probabilistic completeness, and computational scalability in multi-robot motion planning. We propose dRRT and AO-x meta-algorithms built upon a GPU SIMT parallel architecture, which parallelizes roadmap construction, tree search, nearest-neighbor queries, and collision detection to overcome the scalability bottlenecks of conventional CPU-based methods in high-dimensional spaces. This work introduces the first GPU-parallel planning framework supporting almost-sure asymptotic optimality. Experimental results demonstrate that the proposed approach achieves a 100% success rate on systems with 35 degrees of freedom, outperforming state-of-the-art algorithms in computational speed while significantly increasing the success rate of downstream optimizers from 4% to 72%.

Abstract

Finding globally optimal paths remains a fundamental challenge in multi-robot motion planning. Despite acceleration of almost-surely asymptotically optimal (a.s.a.o.) planners via CPU-based parallelism, achieving both probabilistic convergence guarantees and strong computational performance, these algorithms still struggle to scale to multi-robot settings. As such, we introduce MR. POP, a GPU-based a.s.a.o. multi-robot planner based on dRRT and the AO-x meta-algorithm. MR. POP uses large-scale GPU-based SIMT-parallelism to simultaneously run hundreds of roadmap construction and tree search iterations with underlying parallel nearest neighbor search and collision checking operations. We show that this enables MR. POP to become the only planner achieving a 100% solve rate while being faster than state-of-the-art a.s.a.o. planners in multi-robot systems up to 35-DOF. MR. POP also raises the success rate of downstream motion optimizers (e.g., from 4% to 72%), by creating high-quality, diverse seeds that help avoid local minima.

Problem

• multi-robot motion planning
• globally optimal paths
• asymptotically optimal planning
• scalability
• local minima

Innovation

• Multi-robot motion planning
• GPU parallelism
• Asymptotically optimal planning
• dRRT
• Motion optimization