arXiv 2411.179022025-03-07cs.RO

使用全连接信息树（FCIT*）的无最近邻渐近最优运动规划

Nearest-Neighbourless Asymptotically Optimal Motion Planning with Fully Connected Informed Trees (FCIT*)

Estimation, Search, and Planning (ESP) Research Group, Queen’s University, Kingston ON, Canada（皇后大学估计、搜索与规划研究组）；Department of Computer Science, Rice University, Houston TX, USA（里士满大学计算机科学系）；Department of Computer Science, Purdue University, West Lafayette IN, USA（普渡大学计算机科学系）；Ken Kennedy Institute, Rice University, Houston TX, USA（里士满大学肯尼迪研究所）

Tyler S. Wilson, Wil Thomason, Zachary Kingston, Lydia E. Kavraki, Jonathan D. Gammell

备注：: IEEE International Conference on Robotics and Automation (ICRA) 2025, 6 + 1 pages, 3 figures, 1 table. A video of FCIT* can be found at https://www.youtube.com/watch?v=Lb_5Znpcleg . Information on the implementation of FCIT* is available at https://robotic-esp.com/code/fcitstar/
发表信息：: IEEE International Conference on Robotics and Automation (ICRA), pp. 14140-14146, 19-23 May 2025
DOI：: 10.1109/ICRA55743.2025.11127785

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出全连接信息树（FCIT*）算法，利用SIMD并行性降低边评估成本并消除最近邻结构，在MotionBenchMaker数据集上比现有ASAO和满足型算法更快找到初始解并渐近收敛到最优。

摘要：

提高高自由度机器人运动规划算法的性能通常需要降低计算昂贵操作的成本或频率。传统上，尤其是对于渐近最优的基于采样的运动规划器，最昂贵的操作是局部运动验证和查询配置的最近邻。最近的进展通过使用单指令/多数据（SIMD）并行性显著降低了运动验证的成本，从而改善了满足型运动规划问题的求解时间。这些进展尚未应用于渐近最优运动规划。本文提出了全连接信息树（FCIT*），这是第一个全连接、有信息、任意时间几乎必然渐近最优（ASAO）算法。FCIT*利用通过SIMD并行性大幅降低的边评估成本来构建和搜索全连接图。这消除了对最近邻结构的需求，而最近邻结构是许多基于采样的运动规划器的主要成本，并使其能够在MotionBenchMaker数据集上比最先进的ASAO（VAMP，OMPL）和满足型（OMPL）算法更快地找到初始解，同时以任意时间方式收敛到最优计划。

英文摘要：

Improving the performance of motion planning algorithms for high-degree-of-freedom robots usually requires reducing the cost or frequency of computationally expensive operations. Traditionally, and especially for asymptotically optimal sampling-based motion planners, the most expensive operations are local motion validation and querying the nearest neighbours of a configuration. Recent advances have significantly reduced the cost of motion validation by using single instruction/multiple data (SIMD) parallelism to improve solution times for satisficing motion planning problems. These advances have not yet been applied to asymptotically optimal motion planning. This paper presents Fully Connected Informed Trees (FCIT*), the first fully connected, informed, anytime almost-surely asymptotically optimal (ASAO) algorithm. FCIT* exploits the radically reduced cost of edge evaluation via SIMD parallelism to build and search fully connected graphs. This removes the need for nearest-neighbours structures, which are a dominant cost for many sampling-based motion planners, and allows it to find initial solutions faster than state-of-the-art ASAO (VAMP, OMPL) and satisficing (OMPL) algorithms on the MotionBenchMaker dataset while converging towards optimal plans in an anytime manner.

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。