基于变概率约束的移动机器人路径回溯规划  

Path Backtracking Planning of Mobile Robot Based on Variable Probability Constraints

作　　者：岳亮 王卫东 YUE Liang;WANG Weidong(School of Computer,Jiangsu University of Science and Technology,Zhenjiang 212100)

机构地区：[1]江苏科技大学计算机学院,镇江212100

出　　处：《计算机与数字工程》2024年第12期3595-3600,共6页Computer & Digital Engineering

摘　　要：为解决Informed RRT*-Connect算法不具备高效搜索近优路径的问题,提出了一种基于变概率约束采样目标的优化算法。首先将目标偏置机制引入到采样的过程中,其目的是加快首条路径的收敛从而快速生成椭圆采样子集。其次,采用回溯机制对搜索到的路径进行优化,进一步缩短路径长度。为验证改进算法的有效性,在Python平台上与经典路径规划算法在不同的场景下进行对比实验,结果表明改进算法可以有效地提升搜索效率、减少搜索时间,并保证搜索到的路径是近优路径。In order to solve the problem that the Informed RRT*-Connect algorithm does not have the ability to search the near optimal path efficiently,an optimization algorithm based on variable probability constrained sampling target is proposed.First-ly,the target offset mechanism is introduced into the sampling process.Its purpose is to accelerate the convergence of the first path and generate the ellipse sample set quickly.Secondly,backtracking mechanism is used to optimize the searched path and further shorten the path length.In order to verify the effectiveness of the improved algorithm,a comparative experiment with the classical path planning algorithm is carried out on the Python plaform in dfferent scenarios.The results show that the improved algorithm can improve the search efficiency effectively,reduce the search time,and ensure that the search path is a near optimal path.

关 键 词：移动机器人 路径规划 快速搜索随机树 搜索速度 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]