改进的RRT算法更快找到狭窄通道中的最优路径。
An Improved Rapidly Exploring Random Tree Algorithm for Path Planning in Configuration Spaces with Narrow Channels
- 通过检测邻近点碰撞判断狭窄通道并主动偏向该区域采样
- 在狭窄通道场景下路径长度显著缩短，优于经典RRT及其变体
- 适合复杂狭窄环境下的机器人路径规划任务
快速扩展随机树（RRT）算法已成功应用于复杂的机器人运动规划和欠驱动非线性控制问题。然而，其在包含狭窄通道的配置空间中收敛缓慢，原因是生成测试点进入狭窄通道的概率极低。本文提出一种改进的RRT算法，通过检测初始状态与目标状态间是否存在狭窄通道（基于邻近点与不可行集的碰撞情况），并在该区域施加预设偏向策略以增加采样概率，从而更高效探索狭窄区域。该方法在多种基准规划问题上与经典RRT及其变体进行对比。仿真结果表明，所提算法在狭窄通道配置空间中能生成显著更短的路径。
原文摘要 · Abstract (English)
Rapidly-exploring Random Tree (RRT) algorithms have been applied successfully to challenging robot motion planning and under-actuated nonlinear control problems. However a fundamental limitation of the RRT approach is the slow convergence in configuration spaces with narrow channels because of the small probability of generating test points inside narrow channels. This paper presents an improved RRT algorithm that takes advantage of narrow channels between the initial and goal states to find shorter paths by improving the exploration of narrow regions in the configuration space. The proposed algorithm detects the presence of narrow channel by checking for collision of neighborhood points with the infeasible set and attempts to add points within narrow channels with a predetermined bias. This approach is compared with the classical RRT and its variants on a variety of benchmark planning problems. Simulation results indicate that the algorithm presented in this paper computes a significantly shorter path in spaces with narrow channels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。