发表机构
Columbia College, Columbia University; Department of Computer Science, Dartmouth College; Department of Computer Science, Purdue University（哥伦比亚大学哥伦比亚学院; 达特茅斯学院计算机科学系; 普渡大学计算机科学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出MR. POP，一种基于GPU并行和dRRT的a.s.a.o.多机器人规划器，实现100%求解率且速度优于现有方法，并提升下游优化器成功率。
AI 中文摘要
在多机器人运动规划中，寻找全局最优路径仍然是一个基本挑战。尽管通过基于CPU的并行性加速了几乎必然渐近最优（a.s.a.o.）规划器，并实现了概率收敛保证和强大的计算性能，但这些算法仍然难以扩展到多机器人场景。为此，我们提出了MR. POP，一种基于dRRT和AO-x元算法的GPU加速的a.s.a.o.多机器人规划器。MR. POP利用大规模GPU的SIMT并行性，同时运行数百条路线图构建和树搜索迭代，并辅以底层的并行最近邻搜索和碰撞检测操作。我们证明，这使得MR. POP成为唯一在高达35自由度（35-DOF）的多机器人系统中，比最先进的a.s.a.o.规划器更快的同时实现100%求解率的规划器。此外，MR. POP通过生成高质量、多样化的种子来帮助避免局部最小值，从而提高了下游运动优化器的成功率（例如，从4%提升至72%）。
英文摘要
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.
