空间3R机械手逆向运动学的多模块神经网络求解

摘要/Abstract

摘要： 提出用多模块神经网络的方法求解空间3R机械手的逆运动学多解。通过几何分析，将关节空间划分为多个只有唯一逆运动学解的关节子空间，每个子空间均用3个单输出的BP神经网络训练和求解。通过仿真试验并与其他方法对比，表明该方法不仅可以准确地划分逆运动学解的取值范围，还可以快速求得高精度的逆运动学多解。

关键词: 机器人逆运动学多解, BP神经网络, 关节子空间, 3R机械手

Abstract: A multiple module neural network method was proposed to solve the inverse kinematics multiple solutions of space 3R manipulators.The joint spaces were divided into several joint subspaces with unique inverse kinematics solution through geometric analysis. Each subspace was trained and solved by 3 single output BP neural networks. After the simulation and comparison with other methods, results show that the method herein may accurately divide the value ranges of inverse kinematics solutions, and quickly obtain high precision inverse kinematics multiple solutions.

Key words: inverse kinematics multiple solution of robot, BP neural network, joint subspace, 3R manipulator

中图分类号:

TP242.2

肖帆;李光;游雨龙. 空间3R机械手逆向运动学的多模块神经网络求解[J]. 中国机械工程.

XIAO Fan;LI Guang;YOU Yulong. Multiple Module Neural Network Solving for Inverse Kinematics of Space 3R Manipulators[J]. China Mechanical Engineering.

参考文献

[1]熊超,张鹏超,冯博琳,等.基于并行RBF神经网络的机器人逆运动求解[J].组合机床与自动化加工术,2017(10):34-36.
XIONG Chao, ZHANG Pengchao, FENG Bolin, et al. Solution to Inverse Kinematics of Robot Based on Parallel RBF Neural Networks[J]. Combined Machine Tool and Automatic Machining,2017(10):34-36.
[2]姜宏超,刘士荣,张波涛.六自由度模块化机械臂的逆运动学分析[J].浙江大学学报(工学版),2010,44(7):1348-1354.
JIANG Hongchao, LIU Shirong, ZHANG Botao. Inverse Kinematics Analysis for 6 Degree-of-freedom Modular Manipulator[J]. Journal of Zhejiang University (Engineering Edition) ,2010,44(7):1348-1354.
[3]王英石. 冗余机器人的运动学及轨迹规划的研究[D].天津：南开大学,2014.
WANG Yingshi .Research on the Kinematics and Trajectory Planning of Redundant Roborts[D].Tianjin: Nankai University,2014.
[4]房立金,高瑞.一般6R机器人逆运动学算法的改进[J].机械科学与技术, 2018(9):1325-1330.
FANG Lijin, GAO Rui. Modified Inverse Kinematics Algorithm for General 6-DOF Robots[J].Mechanical Science and Technology, 2018(9):1325-1330.
[5]PEIPER D L.The Kinematics of Manipulators under Computer Control[D]. California：Stanford University，1968.
[6]DUFFY J. Analysis of Mechanisms and Robot Manipulators[M]. London：Edward Arnold，1980：369-409.
[7]王俊龙,张国良,敬斌,等.一种新的六自由度机械臂运动学反解方法研究[J].计算机工程与应用,2013,49(22):266-270.
WANG Junlong, ZHANG Guoliang, JING Bin, et al. Research on Way of Inverse Kinematic Solution of Six DOF Manipulator[J]. Computer Engineering and Applications, 2013, 49（22）：266-270.
[8]林阳,赵欢,丁汉.基于多种群遗传算法的一般机器人逆运动学求解[J].机械工程学报,2017,53(3):1-8.
LIN Yang, ZHAO Huan, DING Han. Solution of Inverse Kinematics for General Robot Manipulators Based on Multiple Population Genetic Algorithm[J]. Journal of Mechanical Engineering, 2017,53(3):1-8.
[9]DAYA B, KHAWANDI S, AKOUM M. Applying Neural Network Architecture for Inverse Kinematics Problem in Robotics[J]. Journal of Software Engineering and Applications, 2010, 3(3): 230-239.
[10]DUKA A V. Neural Network Based Inverse Kinematics Solution for Trajectory Tracking of a Robotic Arm[J]. Procedia Technology, 2014, 12: 20-27.
[11]RAHEEM F A, KAREEM A R, HUMAIDI A J. Inverse Kinematics Solution of Robot Manipulator End-effector Position Using Multi-neural Networks[J]. Engineering and Technology Journal, 2016, 34: 1360-1368.
[12]宋孟军,张明路,张建华.一种新型移动机器人运动学坐标系快速构建方法研究[J].中国机械工程,2011,22(17):2017-2021.
SONG Mengjun, ZHANG Minglu，ZHANG Jianhua. Research on Rapid Construction Method of Kinematics Coordinate System from a New Kind of Mobile Robot[J]. China Mechanical Engineering, 2011,22(17): 2017-2021.
[13]张尧. 激活函数导向的RNN算法优化[D].杭州：浙江大学,2017.
ZHANG Yao. Activation Function Awareness of RNN Algorithm Optimization[D]. Hanghzou：Zhejiang University,2017.
[14]陈明. MATLAB神经网络原理与实例精解[M]. 北京：清华大学出版社, 2013:10-173.
CHEN Ming.Theory and Example of Neural Network on MATLAB[M]. Beijing：Tsinghua University Press, 2013:10-173.
[15]张峤,邓贵仕.Levenberg-Marquardt神经网络在煤矿作业人员人因可靠性评价中应用研究[J].大连理工大学学报,2015,55(4):424-430.
ZHANG Qiao, DENG Guishi. Investigation on Application of Levenberg-Marquadt Neural Networks to Human Reliability Evaluation of Coalmine Workers[J]. Journal of Dalian University of Technology, 2015,55(4):424-430.