基于强化RRT算法的机械臂路径规划

doi:10.6040/j.issn.1672-3961.0.2022.036

山东大学学报 (工学版) ›› 2022, Vol. 52 ›› Issue (6): 123-130.doi: 10.6040/j.issn.1672-3961.0.2022.036

• 机器学习与数据挖掘 • 上一篇

基于强化RRT算法的机械臂路径规划

王雨^1,2,3,刘延俊^1,2,3,4*,贾华^1,2,3,薛钢^2,3,4

1.山东大学机械工程学院, 山东济南 250061;2.山东大学高效洁净机械制造教育部重点实验室, 山东济南 250061;3.山东大学机械工程国家级实验教学示范中心, 山东济南 250061;4.山东大学海洋研究院, 山东青岛 266237

发布日期:2022-12-23
作者简介:王雨(1998— ),男,山东临沂人,硕士研究生,主要研究方向为机械臂路径规划算法. E-mail:yu5723@163.com. *通信作者简介:刘延俊(1965— ),男,山东济南人,教授,博士生导师,主要研究方向为自动化机械系统、流体动力控制、波浪能发电技术、深海探测技术与装备. E-mail:lyj111ky@163.com
基金资助:
国家自然科学基金项目(52001186);山东省自然科学基金项目(ZR2020QE292)

Path planning of mechanical arm based on intensified RRT algorithm

WANG Yu^1,2,3, LIU Yanjun^1,2,3,4*, JIA Hua^1,2,3, XUE Gang^2,3,4

1. School of Mechanical Engineering, Shandong University, Jinan 250061, Shandong, China;
2. Key Laboratory of High-Efficiency and Clean Mechanical Manufacture of Ministry of Education, Shandong University, Jinan 250061, Shandong, China;
3. National Demonstration Center for Experimental Mechanical Engineering Education, Shandong University, Jinan 250061, Shandong, China;
4. Institute of Marine Science and Technology, Shandong University, Qingdao 266237, Shandong, China

Published:2022-12-23

摘要/Abstract

摘要： 针对快速拓展随机树算法(rapidly-exploring random trees, RRT)存在采样随机、重复搜索、偏离目标点和节点冗余等问题,提出一种强化快速拓展随机树算法(intensity-guide rapidly-exploring random trees, IG-RRT)。采用覆盖剔除机制强化算法搜索能力,将已搜索区域进行覆盖,覆盖后不再进行搜索和产生新节点,避免重复搜索,提高搜索能力和搜索效率。后续加入目标引导概率,根据地图难度对目标引导概率进行调整,强化算法目标趋向性,对末端节点采用贪婪思想,强化算法收敛性。通过简化路径,去除冗余点,利用三次B样条曲线平滑拐点,提高路径质量。仿真试验表明,IG-RRT算法性能优于传统RRT算法及其相关衍生算法。IG-RRT算法可以增强对复杂约束空间的搜索能力,加快算法的收敛速度,提高路径规划的成功率。

关键词: 路径规划, RRT算法, 机械臂, 趋势强化, 路径平滑

中图分类号:

TP242

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.

WANG Yu, LIU Yanjun, JIA Hua, XUE Gang. Path planning of mechanical arm based on intensified RRT algorithm[J]. Journal of Shandong University(Engineering Science), 2022, 52(6): 123-130.

参考文献

[1] KIM S H, NAM E, HA T I, et al. Robotic machining: a review of recent progress[J]. International Journal of Precision Engineering and Manufacturing, 2019, 20(9): 1629-1642.
[2] RODRIGUEZ G D, SORROSAL G, CABANES I, et al. Human-robot interaction review: challenges and solutions for modern industrial environments[J]. IEEE Access, 2021, 9: 108557-108578.
[3] FANG H C, ONG S K, NEE A Y C. Robot path planning optimization for welding complex joints[J]. The International Journal of Advanced Manufacturing Technology, 2017, 90(9): 3829-3839.
[4] CHEN Y, CHEN W Z, LI B, et al. Paint thickness simulation for painting robot trajectory planning: a review[J]. Industrial Robot:the International Journal of Robotics Research and Application, 2017, 44(5): 629-638.
[5] LIM G H, LAU N, PEDROSA E, et al. Precise and efficient pose estimation of stacked objects for mobile manipulation in industrial robotics challenges[J]. Advanced Robotics, 2019, 33(13): 636-646.
[6] 魏坤. 机械臂混杂场景动态路径规划与多目标识别研究[D].哈尔滨:哈尔滨工业大学, 2019. WEI Kun. Research on dynamic path planning and multi-objective recognition of the manipulator in cluttered scenes [D]. Harbin: Harbin Institute of Technology, 2019.
[7] 郭枭鹏. 基于改进人工势场法的路径规划算法研究[D]. 哈尔滨:哈尔滨工业大学, 2017. GUO Xiaopeng. Research on improved artificial potential field path planning algorithm[D]. Harbin: Harbin Institute of Technology, 2017.
[8] FU Bing, CHEN Lin, ZHOU Yuntao, et al. An improved A* algorithm for the industrial robot path planning with high success rate and short length[J]. Robotics and Autonomous Systems, 2018, 106: 26-37.
[9] LIU Xiaohuan, ZHANG Degan, ZHANG Jie, et al. A path planning method based on the particle swarm optimization trained fuzzy neural network algorithm[J]. Cluster Computing, 2021, 24(3): 1901-1915.
[10] ELHOSENY M, THARWAT A, HASSANIEN A E. Bezier curve based path planning in a dynamic field using modified genetic algorithm[J]. Journal of Computational Science, 2018, 25: 339-350.
[11] WANG Lanfei, KAN Jiangming,GUO Jun, et al. 3D path planning for the ground robot with improved ant colony optimization[J]. Sensors, 2019, 19(4): 815-836.
[12] LAVALLE S M. Rapidly-exploring random trees: a new tool for path planning[R].Iowa,USA: Computer Science Department,Iowa State University, 1998.
[13] LAVALLE S M, KUFFNER J. Rapidly-exploring random trees:progress and prospects[C] //Proceedings of 4th International Workshop on the Algorithmic Foundations of Robotics(WAFR). Hanover, USA: Sandia Natl Labs, 2000:293-308.
[14] KUFFNER J J, LAVALLE S M. RRT-connect: an efficient approach to single-query path planning[C] // Proceedings of 2000 IEEE International Conference on Robotics and Automation. San Francisco, USA: IEEE, 2000: 995-1001.
[15] KARAMAN S, FRAZZOLI E. Incremental sampling-based algorithms for optimal motion planning[J]. International Journal of Robotics Research, 2011, 30(7): 5326-5332.
[16] QURESHI A H, AYAZ Y. Intelligent bidirectional rapidly-exploring random trees for optimal motion planning in complex cluttered environments[J]. Robotics and Autonomous Systems, 2015, 68: 1-11.
[17] NOREEN I, KHAN A, RYU H, et al. Optimal path planning in cluttered environment using RRT*-AB[J]. Intelligent Service Robotics, 2018, 11(1): 41-52.
[18] WANG Wei, ZUO Lei, XU Xin. A learning-based multi-RRT approach for robot path planning in narrow passages[J]. Journal of Intelligent & Robotic Systems, 2018, 90(1): 81-100.
[19] TAHERI E, FERDOWSI M H, DANESH M. Fuzzy greedy RRT path planning algorithm in a complex configuration space[J]. International Journal of Control, Automation and Systems, 2018, 16(6): 3026-3035.
[20] 司徒华杰,雷海波,庄春刚. 动态环境下基于人工势场引导的RRT路径规划算法[J]. 计算机应用研究, 2021, 38(3): 714-717. SITU Huajie, LEI Haibo, ZHUANG Chungang. Artificial potential field based RRT algorithm for path planning in dynamic environment[J]. Computer Application Research, 2021, 38(3): 714-717.
[21] 王兆光. 六自由度机械臂避障路径规划研究[D]. 成都:西南交通大学, 2018. WANG Zhaoguang. Research on obstacle avoidance path planning of 6-DOF manipulator[D]. Chengdu: South-west Jiaotong University, 2018.
[22] XIAO Fan, LI Gongfa, JIANG Du, et al. An effective and unified method to derive the inverse kinematics formulas of general six-DOF manipulator with simple geometry[J]. Mechanism and Machine Theory, 2021, 159: 1-14.
[23] 马慧丽,鲁照权,王寿庭. 基于改进RRT*算法的机械臂路径规划研究[J]. 机械设计与研究, 2020, 36(4): 42-46. MA Huili, LU Zhaoquan, WANG shouting. Research on manipulator path planning based on improved RRT* algorithm[J]. Mechanical Design and Research, 2020, 36(4): 42-46.
[24] ZHANG Tie, HONG Jingdong. Collision detection method for industrial robot based on envelope-like lines[J]. Industrial Robot: the International Journal of Robotics Research and Application, 2019, 46(4): 510-517.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于强化RRT算法的机械臂路径规划

Path planning of mechanical arm based on intensified RRT algorithm

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

多维度评价

本文评价

推荐阅读 0

[1]	石振杰, 刘延俊, 薛钢, 贾华, 王雨. 混合驱动仿人机械臂设计与运动学分析[J]. 山东大学学报 (工学版), 2022, 52(4): 76-82.
[2]	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.
[3]	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.
[4]	吴禹均,吴巍,郭毓,郭健. 一种基于力觉的机器人对孔装配方法[J]. 山东大学学报 (工学版), 2019, 49(5): 119-126.
[5]	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, 74.
[6]	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.
[7]	刘哲,宋锐,邹涛. 基于模型预测控制的磨削机器人末端力跟踪控制算法[J]. 山东大学学报(工学版), 2018, 48(1): 42-49.
[8]	王秀青,曾慧,解飞,吕峰. 基于Spiking神经网络的机械臂故障诊断[J]. 山东大学学报(工学版), 2017, 47(5): 15-21.
[9]	杨元慧,李国栋,吴春富,王小龙,蔡小伟. 移动机械臂手眼关系标定及视觉伺服控制方法[J]. 山东大学学报(工学版), 2016, 46(5): 54-63.
[10]	高焕兵, 田国会. 面向配电系统的带电抢修作业机器人[J]. 山东大学学报(工学版), 2015, 45(1): 45-53.
[11]	严宣辉, 肖国宝*. 基于定长实数路径编码机制的移动机器人路径规划[J]. 山东大学学报(工学版), 2012, 42(1): 59-65.
[12]	刘彬,张仁津. 一种采用两段粒子群优化的路径规划方法[J]. 山东大学学报(工学版), 2012, 42(1): 12-18.
[13]	陈明志1,许春耀2,陈健2,余轮2. 基于语义信息的虚拟环境路径规划[J]. 山东大学学报(工学版), 2011, 41(4): 106-112.