arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.02846cs.ROcs.DC
收藏

Kino-PAX$^+$:近最优大规模并行运动规划器

Kino-PAX$^+$: Near-Optimal Massively Parallel Kinodynamic Sampling-based Motion Planner

Department of Aerospace Engineering Sciences, University of Colorado Boulder(航空航天工程科学系,科罗拉多大学博尔德分校);Department of Aerospace and Ocean Engineering, Virginia Tech(航空航天与海洋工程系,弗吉尼亚理工学院)

Nicolas Perrault, Qi Heng Ho, Morteza Lahijanian

AI总结:

Kino-PAX$^+$是一种具有渐近近最优保证的并行运动规划器,通过并行计算显著提高了速度和解决方案质量。

摘要:

基于采样的运动规划器(SBMPs)被广泛用于在高维空间中处理具有复杂运动动力学约束的机器人运动规划,但它们由于串行计算设计而难以实现实时性能。最近对SBMPs并行化的工作在寻找可行解方面取得了显著加速;然而,它们不提供优化目标函数的保证。我们引入了Kino-PAX$^+$,一种具有渐近近最优保证的大量并行运动规划器。Kino-PAX$^+$通过将传统串行操作分解为三个大量并行子程序,构建了一个动态可行轨迹的稀疏树。该算法在局部邻域内专注于最有希望的节点进行传播和细化,从而加快了解决方案成本的改进。我们证明,在保持概率δ-鲁棒完备性的同时,这种专注于有希望的节点确保了渐近δ-鲁棒近最优性。我们的结果表明,Kino-PAX$^+$比现有串行方法快多达三个数量级,且比最先进的GPU基于规划器达到更低的解决方案成本。

英文摘要:

Sampling-based motion planners (SBMPs) are widely used for robot motion planning with complex kinodynamic constraints in high-dimensional spaces, yet their serial computation design results in planning speeds that scale poorly with problem complexity. Recent efforts to parallelize SBMPs have achieved significant speedups in finding feasible solutions; however, they provide no guarantees of optimizing an objective function. We introduce Kino-PAX$^{+}$, a massively parallel kinodynamic SBMP with asymptotic near-optimal guarantees. Kino-PAX$^{+}$ builds a sparse tree of dynamically feasible trajectories by decomposing traditionally serial operations into three massively parallel subroutines. The algorithm focuses computation on the most promising nodes within local neighborhoods for propagation and refinement, enabling rapid improvement of solution cost. We prove that, while maintaining probabilistic $δ$-robust completeness, this focus on promising nodes ensures asymptotic $δ$-robust near-optimality. Our results show that Kino-PAX$^{+}$ finds solutions up to three orders of magnitude faster than existing serial methods and achieves lower solution costs

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑