Problem
Research questions and friction points this paper is trying to address.
multi-robot motion planning
parallel planning
subproblem independence
conflict resolution
scalability
P-ARC: Exploiting Subproblem Independence for Parallel Multi-Robot Motion Planning
🤖 AI Summary
This work addresses the challenges of low computational efficiency and poor scalability in multi-robot motion planning by proposing OR-P-ARC, a hybrid parallelization framework that achieves end-to-end parallelism within the Adaptive Robot Coordination (ARC) paradigm for the first time. By parallelizing the three core stages—individual path generation, conflict detection, and resolution—and incorporating an OR-parallel multi-start strategy to exploit independence among subproblems, the method substantially enhances planning efficiency and real-time performance in large-scale scenarios. Experimental results demonstrate that OR-P-ARC enables real-time planning for 128 Panda robotic arms on a 16-core CPU, achieving nearly a fourfold speedup over the baseline approach.
📝 Abstract
This paper presents Parallel ARC (P-ARC), a parallel variant of the Adaptive Robot Coordination (ARC) approach to multi-robot motion planning (MRMP). P-ARC proposes a parallel variant for each of the three main stages in ARC: initial individual solutions, conflict detection, and conflict resolution, exploiting the independence created by ARC's decomposition of the MRMP problem. Additionally, we employ an OR-parallel multi-start strategy to both ARC and P-ARC, creating a hybrid parallel strategy OR-P-ARC. We evaluate the impact of the different parallel strategies for ARC using a set of scaling 2D mobile and planar manipulator scenarios with up to 128 robots to control for conflicts and work distribution across the stages of ARC. Additionally, we demonstrate planning time speedups approaching 4X over the sequential version for large Panda multi-manipulator teams in real-world inspired scenarios when deploying 16 CPU cores.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Parallel Multi-Robot Motion Planning
Subproblem Independence
Conflict Resolution
OR-Parallel Strategy
Adaptive Robot Coordination
🔎 Similar Papers
No similar papers found.
