基于海马优化的改进Informed-RRT^(*)的路径规划算法  

Path planning algorithm based on the improved Informed-RRT^(*)using the sea-horse optimizer

作　　者：严贵僧 杨洁[1] YAN Guiseng;YANG Jie(College of Mechanical and Transportation Engineering,Southwest Forestry University,Kunming 650224,China)

机构地区：[1]西南林业大学机械与交通学院,昆明650224

出　　处：《机械传动》2025年第2期93-100,共8页Journal of Mechanical Transmission

基　　金：云南省教育厅科学研究基金项目(0111723084)。

摘　　要：【目的】为了解决传统Informed-RRT^(*)算法在复杂环境中面临随机性采样、低效搜索和难以提供最优路径等问题,提出了一种基于海马优化(Sea-Horse Optimizer,SHO)的改进Informed-RRT^(*)的路径规划算法。【方法】该算法结合了Informed-RRT^(*)和SHO的优势,引入适应度函数,用于评估采样节点的适应性,从而增强对采样目标的引导;此外,采用自适应步长和随机扰动,以适应环境中的障碍物,并选择最佳个体来引导随机树的扩展方向。【结果】通过多组仿真和样机试验对比表明,改进后的Informed-RRT^(*)算法具有更快的收敛速度、更高的搜索效率以及更出色的路径规划性能,为复杂环境中的路径规划提供一种高效的解决方案。[Objective]In order to solve the problems of random sampling,inefficient search,and difficulty in providing optimal paths in complex environments faced by traditional Informed-RRT^(*)algorithms,an improved Informed-RRT^(*)path plan‐ning algorithm based on the sea-horse optimizer(SHO)was proposed.[Methods]This algorithm combined the strengths of Informed-RRT^(*)and SHO.An adaptability function was introduced to evaluate the suitability of sampled nodes,thereby enhancing guidance towards sampling objectives.Additionally,adaptive step sizes and random perturbations were employed to adapt to obstacles in the environment,and the best individuals were chosen to guide the expansion direction of the random tree.[Results]Through multiple sets of simulation and prototype tests,it is demonstrated that the improved Informed-RRT^(*)algorithm exhibits faster convergence speed,higher search efficiency,and superior path planning performance,providing an efficient solution for path planning in complex environments.

关 键 词：SHO算法 Informed-RRT^(*)算法 路径规划 采样导向性 自主避障 

分 类 号：TP241[自动化与计算机技术—检测技术与自动化装置]