| 283 | 0 | 66 |
| 下载次数 | 被引频次 | 阅读次数 |
针对RRT~*算法在路径规划中面临搜索效率不高、易于陷入局部最优等问题，提出一种结合强化学习的Q-RRT~*算法。该算法将Q-Learning算法和RRT~*算法相融合，首先引入转角偏向策略增强路径搜索时的导向作用、减少无效节点的生成，提升算法的搜索效率；其次通过动R搜索算法动态地调整搜索半径，进一步优化路径的质量和冗余节点的产生；最后对生成的路径使用三次B样条插值法和冗余节点删除法进一步优化路径质量。在二维和三维环境下的仿真实验结果表明，改进后的Q-RRT~*算法和RRT、RRT~*和RL-RRT算法相比，路径规划时长平均快39.7%,迭代次数平均减低27.9%,路径长度平均缩短16.3%。
Abstract：In order to solve the problems of low search efficiency and tendency to fall into local optimum in RRT~* path planning, a Q-RRT~* algorithm combined with reinforcement learning was proposed, which fused the Q-Learning algorithm and the RRT~* algorithm.Firstly, the corner bias strategy was introduced to enhance the guiding effect of path search, reduce the generation of invalid nodes, and improve the search efficiency of the algorithm.Secondly, the search radius was dynamically adjusted by the dynamic R search algorithm to further optimize the quality of the path and the generation of redundant nodes.Finally the cubic B-spline interpolation method and the redundant node deletion method were used to further optimize the path quality of the generated path.Simulation results in 2D and 3D environments show that the improved Q-RRT~* algorithm is 39.7%faster on average, 27.9%less iteration and 16.3%shorter in path length than RRT,RRT~* and RL-RRT algorithms.
[1] TANG B,ZHU Z,LUO J.Hybridizing particle swarm optimization and differential evolution for the mobile robot global path planning[J].International Journal of Advanced Robotic Systems,2016,13(3):86.
[2] 林韩熙，向丹，欧阳剑，等.移动机器人路径规划算法的研究综述[J].计算机工程与应用，2021,57(18):38-48.LIN H X,XIANG D,OUYANG J,et al.Review of path planning algorithms for mobile robots[J].Computer Engineering and Applications,2021,57(18):38-48.(in Chinese)
[3] 鲍庆勇，李舜酩，沈峘，等.自主移动机器人局部路径规划综述[J].传感器与微系统，2009,28(9):1-4,11.BAO Q Y,LI S M,SHEN H,et al.Survey of local path planning of autonomous mobile robot[J].Transducer and Microsystem Technologies,2009,28(9):1-4,11.(in Chinese)
[4] 王梓强，胡晓光，李晓筱，等.移动机器人全局路径规划算法综述[J].计算机科学，2021,48(10):19-29.WANG Z Q,HU X G,LI X X,et al.Overview of global path planning algorithms for mobile robots[J].Computer Science,2021,48(10):19-29.(in Chinese)
[5] TANG X X,ZHOU H B,XU T Y.Obstacle avoidance path planning of 6-DOF robotic arm based on improved A* algorithm and artificial potential field method[J].Robotica,2023,42(2):457-481.
[6] 马新国，马希青.融合改进RRT和Dijkstra算法的机器人动态路径规划[J].组合机床与自动化加工技术，2023(2):5-9.MA X G,MA X Q.Robot path planning based on improve RRT and Dijkstra approach[J].Modular Machine Tool & Automatic Manufacturing Technique,2023(2):5-9.(in Chinese)
[7] GU X T,LIU L X,WANG L,et al.Energy-optimal adaptive artificial potential field method for path planning of free-flying space robots[J].Journal of the Franklin Institute,2024,361(2):978-993.
[8] YIN X,DONG W T,WANG X M,et al.Route planning of mobile robot based on improved RRT star and TEB algorithm[J].Scientific Reports,2024,14(1):8942.
[9] MISHRA R,BAJPAI M K.A novel multi-agent genetic algorithm for limited-view computed tomography[J].Expert Systems with Applications,2024,238:122195.
[10] LI X H,YU S H.Three-dimensional path planning for AUVs in ocean currents environment based on an improved compression factor particle swarm optimization algorithm[J].Ocean Engineering,2023,280:114610.
[11] 康振兴.基于路径规划和深度强化学习的机器人避障导航研究[J].计算机应用与软件，2024,41(1):297-303.KANG Z X.Robot obstacle avoidance navigation based on path planning and deep reinforcement learning[J].Computer Applications and Software,2024,41(1):297-303.(in Chinese)
[12] TU H Y,DENG Y Z,LI Q Y,et al.Improved RRT global path planning algorithm based on Bridge Test[J].Robotics and Autonomous Systems,2024,171:104570.
[13] 胡晓阳，赵杰，武炎明.基于改进RRT-Connect算法的路径规划研究[J].沈阳理工大学学报，2023,42(4):26-30,39.HU X Y,ZHAO J,WU Y M.Research on path planning based on improved RRT-connect algorithm[J].Journal of Shenyang Ligong University,2023,42(4):26-30,39.(in Chinese)
[14] 冯迎宾，赵子君，晏佳华.改进RRT算法的四旋翼无人机路径规划方法[J].沈阳理工大学学报，2024,43(1):9-15.FENG Y B,ZHAO Z J,YAN J H.An optimizing RRT algorithm for quadrotor UAV path planning[J].Journal of Shenyang Ligong University,2024,43(1):9-15.(in Chinese)
[15] QIU X Y,FENG C,SHEN Y.Obstacle avoidance planning combining reinforcement learning and RRT* applied to underwater operations[C]//OCEANS 2021.San Diego ,USA and Porto,Portugal:IEEE,2021:1-6.
[16] 罗国攀，张国良，杨敏豪.基于强化学习方法的RRT全局路径规划算法[J].四川轻化工大学学报(自然科学版),2024,37(2):57-63.LUO G P,ZHANG G L,YANG M H.RRT global path planning algorithm based on reinforcement learning method[J].Journal of Sichuan University of Science & Engineering(Natural Science Edition),2024,37(2):57-63.(in Chinese)
[17] KARAMAN S,FRAZZOLI E.Sampling-based algorithms for optimal motion planning[J].The International Journal of Robotics Research,2011,30(7):846-894.
基本信息:
DOI：
中图分类号:TP181;TP242
引用信息:
[1]张艳珠,侯亢钧,陈勇等.基于强化学习的改进RRT~*路径规划[J].沈阳理工大学学报,2025,44(04):1-6+12.
基金信息:
辽宁省教育厅高等学校基本科研项目(LJKZ0245)