基于改进Informed-RRT^(*)算法的机器人路径规划  

Robot path planning based on improved informed-RRT^(*)algorithm

作　　者：代军[1] 李志明 李艳琴 赵俊伟[1] DAI Jun;LI Zhiming;LI Yanqin;ZHAO Junwei(School of Mechanical and Power Engineering,Henan Polytechnic University,Jiaozuo 454000,Henan,China)

机构地区：[1]河南理工大学机械与动力工程学院,河南焦作454000

出　　处：《河南理工大学学报（自然科学版）》2022年第4期95-100,共6页Journal of Henan Polytechnic University（Natural Science）

基　　金：国家自然科学基金资助项目(51505133);河南省科技攻关项目(182102310706);河南省博士后科研项目(166182);河南理工大学基本科研业务费专项项目(NSFRF180412);河南理工大学博士基金资助项目(B2016-22);河南省高等学校重点科研项目(22A460020)。

摘　　要：为了解决Informed-RRT^(*)算法在路径规划中目的性差、收敛速度慢、路径优化效率低等问题,提出一种基于贪心算法并改变其搜索对象的方法,对Informed-RRT^(*)算法进行优化。首先,在首次路径规划时引入贪心算法思想,当得到一个新节点时判断该节点能否直接到达目标点,增强路径规划的目的性;其次,将潜在最优父节点的搜索对象由路径规划构建的节点树替换为构建的路径,减少需要搜索的节点数量,提高规划效率。仿真结果表明,改进后的Informed-RRT^(*)算法规划路径长度比原算法的缩短了10%~20%,规划路径时间缩短了80%~90%。In order to solve the problems of poor purpose,slow convergence speed and low efficiency of path optimization of Informed-RRTalgorithm in path planning,a greedy algorithm based on changing the search object was proposed to optimize the Informed-RRTalgorithm.Firstly,the greedy algorithm was introduced in the first path planning.When a new node was obtained,whether the node could directly reach the target point was judged to enhance the purpose of path planning.Secondly,the search object of the potential optimal parent node was replaced by the node tree constructed by path planning to the constructed path,so as to reduce the number of nodes to be searched and to improve the planning efficiency.The simulation results showed that the improved Informed RRTalgorithm reduced the length of path planning by 10%~20%and the time of path planning by 80%~90%compared with the original algorithm.

关 键 词：Informed-RRT^(*)算法 路径规划 路径优化 机器人导航 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]