改进RRT-Connect与AFSA融合算法移动机器人路径规划

doi:10.6040/j.issn.1672-3961.0.2025.051

摘要/Abstract

摘要： 针对RRT-Connect算法在路径规划中搜索效率低、目标导向性弱、路径冗余节点多、平滑性不佳的问题,在改进RRT-Connect算法与人工鱼群算法基础上,提出ARRT-Connect融合算法。该算法引入中间节点,采用目标偏置策略、引力势场引导、自适应步长调节及剪枝优化,并结合B样条曲线平滑路径;改进人工鱼群算法步长与视野范围,增强全局搜索能力。试验表明,与RRT-Connect算法相比,ARRT-Connect融合算法在简单和复杂环境中平均耗时分别减少82.22%和76.92%,平均路径长度分别缩短17.41%和19.38%,平均节点数分别减少79.21%和77.84%。将其应用于现实场景,移动机器人路径长度和耗时明显缩短,路径转折更平缓,验证了该算法有效性、优越性与可行性。

关键词: 融合算法, 移动机器人, 路径规划, RRT-Connect, 人工鱼群算法

Abstract: Aiming at the problems of the RRT-Connect algorithm in path planning, such as low search efficiency, weak target orientation, redundant path nodes, and poor smoothness, the ARRT-Connect fusion algorithm was proposed based on the improvement of the RRT-Connect algorithm and the artificial fish swarm algorithm.The algorithm introduced intermediate nodes, adopted a target bias strategy, gravitational potential field guidance, adaptive step size adjustment and pruning optimization, and combined B-spline curves to smooth the path. It improved the step size and visual range of the artificial fish swarm algorithm to enhance the global search capability. Experiments showed that compared with the RRT-Connect algorithm, the ARRT-Connect algorithm reduced the average time consumption by 82.22% and 76.92% in simple and complex environments respectively, shortened the average path length by 17.41% and 19.38%, and decreased the average number of nodes by 79.21% and 77.84%. When applied to real-world scenarios, the path length and time consumption of mobile robots were significantly shortened, and path transitions became gentler, which verified the effectiveness, superiority and feasibility of the algorithm.

Key words: fusion algorithm, mobile robot, path planning, RRT-Connect, artificial fish swarm algorithm

中图分类号:

TP242.6

陈志澜,古春祥. 改进RRT-Connect与AFSA融合算法移动机器人路径规划[J]. 山东大学学报 (工学版), 2026, 56(3): 73-83.

CHEN Zhilan, GU Chunxiang. Improved RRT-Connect and AFSA fusion algorithm for mobile robot path planning[J]. Journal of Shandong University(Engineering Science), 2026, 56(3): 73-83.

参考文献

[1] 雷艳敏, 王帅. 基于遗传算法的机器人路径规划的仿真研究[J]. 长春大学学报, 2017, 27(4): 1-3. LEI Yanmin, WANG Shuai. Simulation study of robot path planning based on genetic algorithm[J]. Journal of Changchun University, 2017, 27(4): 1-3.
[2] 廖依伊. 正则化深度学习及其在机器人环境感知中的应用[D]. 杭州: 浙江大学, 2018: 4-5. LIAO Yiyi. Regularized deep learning and its application in robot environment perception[D]. Hangzhou: Zhejiang University, 2018: 4-5.
[3] 刘小松, 康磊, 单泽彪, 等. 基于双向目标偏置APF-informed-RRT^*算法的机械臂路径规划[J]. 电子测量与仪器学报, 2024, 38(6): 75-83. LIU Xiaosong, KANG Lei, SHAN Zebiao,et al.Path planning of robot arm based on APF-informed-RRT^* algorithm with bidirectional target bias[J]. Journal of Electronic Measurement and Instrumentation, 2024, 38(6): 75-83.
[4] 董炫良, 赵桂清. 人工势场引导蚁群算法的机器人导航路径规划[J]. 机械设计与制造, 2021(6): 169-173. DONG Xuanliang, ZHAO Guiqing. Robot navigation path planning based on ant colony algorithm guided by artificial potential field[J]. Machinery Design & Manufacture, 2021(6): 169-173.
[5] CHEN J G, ZHAO Y, XU X. Improved RRT-connect based path planning algorithm for mobile robots[J]. IEEE Access, 2021, 9: 145988-145999.
[6] 韦玉海, 张辉, 刘理, 等. 基于AMRRT-Connect算法的移动机器人路径规划[J]. 武汉大学学报(工学版), 2022, 55(5): 531-538. WEI Yuhai, ZHANG Hui, LIU Li, et al. Path planning of mobile robot based on AMRRT-Connect algorithm[J]. Engineering Journal of Wuhan University, 2022, 55(5): 531-538.
[7] ZHANG R, GUO H, ANDRIUKAITIS D, et al. Intelligent path planning by an improved RRT algorithm with dual grid map[J]. Alexandria Engineering Journal, 2024, 88: 91-104.
[8] HUYNH L Q, TRAN L V, PHAN P N K, et al. Inter-mediary RRT^*-PSO:a multi-directional hybrid fast convergence sampling based path planning algorithm[J]. Computers, Materials & Continua, 2023, 76(2): 2281-2300.
[9] WANG X Y, LI X J, GUAN Y, et al. Bidirectional potential guided RRT^* for motion planning[J]. IEEE Access, 2019, 7: 95046-95057.
[10] 李锦平. 机器人自主行走与空间作业路径规划方法研究[D]. 西安: 西安电子科技大学, 2021: 12. LI Jinping. Research on robot autonomous walking and spatial operation path planning method [D]. Xi'an: Xi'an Electronic Science and Technology University, 2021: 12.
[11] ZHANG L P, SHI X X, YI Y M, et al. Mobile robot path planning algorithm based on RRT-Connect[J]. Electronics, 2023, 12(11): 2456.
[12] 陈家贵. 农业移动机器人病害识别关键技术研究[D]. 杭州: 浙江科技学院, 2021: 63. CHEN Jiagui. Research on key technology of disease identification of agricultural mobile robot[D]. Hangzhou: Zhejiang Institute of Science and Technology, 2021: 63.
[13] WANG L N, YANG X, CHEN Z L, et al. Application of the improved rapidly exploring random tree algorithm to an insect-like mobile robot in a narrow environment[J]. Biomimetics, 2023, 8(4): 374.
[14] 王怀震, 高明, 王建华, 等. 基于改进RRT^*-Connect算法的机械臂多场景运动规划[J]. 农业机械学报, 2022, 53(4): 432-440. WANG Huaizhen, GAO Ming, WANG Jianhua, et al. Multiscene fast motion planning of manipulator based on improved RRT^*-Connect algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(4): 432-440.
[15] 骆海涛, 孙嘉泽, 高鹏宇, 等. 基于改进RRT^*算法的智能轮椅全局路径规划研究[J]. 仪器仪表学报, 2023, 44(10): 303-313. LUO Haitao, SUN Jiaze,GAO Pengyu,et al.Intelligent wheelchair global path planning research based on the improved RRT^* algorithm[J]. Chinese Journal of Scientific Instrument, 2023, 44(10): 303-313.
[16] 赵超力. 基于双目视觉的六自由度机械臂避障与路径规划研究[D]. 银川: 北方民族大学, 2022. ZHAO Chaoli. Research on obstacle avoidance and path planning of six degree of freedom robotic arm based on binocular vision[D]. Yinchuan: Northern Nationa-lities University, 2022.
[17] LI J, HUANG C W, PAN M Q. Path-planning algorithms for self-driving vehicles based on improved RRT-Connect[J]. Transportation Safety and Environment, 2023, 5(3): 95-104.
[18] 马晓群, 王昊, 刘磊, 等. 基于IRRT-Connect的自适应路径规划算法[J]. 电子测量技术, 2024, 47(15): 82-88. MA Xiaoqun, WANG Hao, LIU Lei, et al. Adaptive path planning algorithm based on IRRT-Connect[J]. Electronic Measurement Technology, 2024, 47(15): 82-88.
[19] 高文斌. 基于改进的RRT路径规划算法研究[D]. 天津: 河北工业大学, 2019: 33-36. GAO Wenbin. Research on improved RRT path planning algorithm[D]. Tianjin: Hebei University of Technology, 2019: 33-36.
[20] 杜传胜, 高焕兵, 侯宇翔, 等. 同根双向扩展的贪心RRT路径规划算法[J]. 计算机工程与应用, 2023, 59(21): 312-318. DU Chuansheng, GAO Huanbing, HOU Yuxiang, et al. Greedy RRT path planning algorithm with same root bidirectional extension[J]. Computer Engineering and Applications, 2023, 59(21): 312-318.
[21] 阳晓明. 含分布式电源和电动汽车的主动配电网络重构研究[D]. 上海: 上海电机学院, 2020: 23. YANG Xiaoming. Research on reconfiguration of active distribution network containing distributed power sources and electric vehicles[D]. Shanghai: Shanghai Institute of Electrical Engineering, 2020: 23.
[22] 赵志刚, 马习纹, 姬俊安. 基于AFSA与PSO混合算法的J-A动态磁滞模型参数辨识及验证[J]. 仪器仪表学报, 2020, 41(1): 26-34. ZHAO Zhigang, MA Xiwen, JI Jun'an. Parameter identification and verification of J-A dynamic hysteresis model based on hybrid algorithms of AFSA and PSO[J]. Chinese Journal of Scientific Instrument, 2020, 41(1): 26-34.
[23] LEE S H, CHENG C H, LIN C C, et al. Target positioning and tracking in WSNs based on AFSA[J]. Information, 2023, 14(4): 246.
[24] 郭阳,石博博,衣正尧,等.基于改进人工鱼群算法的AUV路径规划[J]. 舰船科学技术, 2026, 48(6):141-149. GUO Yang, SHI Bobo, YI Zhengyao, et al. AUV path planning based on an improved artificial fish school algorithm [J]. Ship Science and Technology, 2026, 48(6): 141-149.
[25] 田玉冬, 徐传征. 结合人工鱼群和RRT算法的机械臂路径规划[J]. 机械科学与技术, 2026, 45(1): 44-56. TIAN Yudong, XU Chuanzheng. Robotic arm path planning combined artificial fish swarming and RRT algorithms[J]. Mechanical Science and Technology for Aerospace Engineering, 2026, 45(1): 44-56.

相关文章 15

[1]	李晓辉,刘小飞,孙炜桐,赵毅,董媛,靳引利. 基于车辆与无人机协同的巡检任务分配与路径规划算法[J]. 山东大学学报 (工学版), 2025, 55(5): 101-109.
[2]	韩毅,刘毅超,关甜,兰理文,汤宁业. 改进A^*和动态窗口法的无人车路径规划[J]. 山东大学学报 (工学版), 2025, 55(3): 16-24.
[3]	赵红专,张鑫,张蓓聆,展新,李文勇,袁泉,王涛,周旦. 基于改进人工势场的智能车动态安全椭圆路径规划方法[J]. 山东大学学报 (工学版), 2025, 55(3): 46-57.
[4]	张飞凯,夏拥军,秦剑,游溢,彭飞. 基于A^*算法的输电线路组塔施工吊装路径规划方法[J]. 山东大学学报 (工学版), 2024, 54(3): 141-148.
[5]	黄健堃,薛钢,刘延俊,王雨,李厚池,白发刚. 基于改进Bi-RRT算法的机器鱼路径规划方法[J]. 山东大学学报 (工学版), 2024, 54(1): 74-82.
[6]	张海森,张煌,王常顺. 基于多机器人编队控制的大件物品协同搬运[J]. 山东大学学报 (工学版), 2023, 53(4): 157-162.
[7]	赵天怀,王目树,潘为刚,康超,秦石铭,徐飞. 挖掘机智能辅助施工系统设计[J]. 山东大学学报 (工学版), 2023, 53(4): 163-172.
[8]	张迪,徐德. 面向移动机器人的室外环境多层次地图构建[J]. 山东大学学报 (工学版), 2023, 53(2): 34-41.
[9]	王雨,刘延俊,贾华,薛钢. 基于强化RRT算法的机械臂路径规划[J]. 山东大学学报 (工学版), 2022, 52(6): 123-130.
[10]	张飞凯,黄永忠,李连茂,秦剑,刘晨. 基于Dijkstra算法的货运索道路径规划方法[J]. 山东大学学报 (工学版), 2022, 52(6): 176-182.
[11]	肖浩,廖祝华,刘毅志,刘思林,刘建勋. 实际环境中基于深度Q学习的无人车路径规划[J]. 山东大学学报 (工学版), 2021, 51(1): 100-107.
[12]	李彩虹,方春,王志强,夏斌,王凤英. 基于超混沌同步控制的移动机器人全覆盖路径规划[J]. 山东大学学报 (工学版), 2019, 49(6): 63-72.
[13]	刘美珍,周风余,李铭,王玉刚,陈科. 基于模型不确定补偿的轮式移动机器人反演复合控制[J]. 山东大学学报 (工学版), 2019, 49(6): 36-44.
[14]	周风余, 万方, 焦建成, 边钧健. 家庭陪护机器人自主充电系统研究与设计[J]. 山东大学学报 (工学版), 2019, 49(1): 55-65.
[15]	张强. 核环境多关节蛇形机械臂的运动控制系统设计[J]. 山东大学学报 (工学版), 2018, 48(6): 122-131.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed