[1]陈 桂,陈耀忠,林 健,等.机器人逆运动学的微分进化与粒子群优化 BP神经网络求解[J].南京理工大学学报(自然科学版),2014,38(06):763.
 Chen Gui,Chen Yaozhong,Lin Jian,et al.Solving robot inverse kinematics based on differential evolution and particle swarm optimization BP neural network[J].Journal of Nanjing University of Science and Technology,2014,38(06):763.
点击复制

机器人逆运动学的微分进化与粒子群优化 BP神经网络求解
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
38卷
期数:
2014年06期
页码:
763
栏目:
出版日期:
2014-12-31

文章信息/Info

Title:
Solving robot inverse kinematics based on differential evolution and particle swarm optimization BP neural network
作者:
陈 桂1陈耀忠2林 健1温秀兰1
1.南京工程学院 自动化学院,江苏 南京 211167; 2.北方信息控制集团有限公司,江苏 南京 211153
Author(s):
Chen Gui1Chen Yaozhong2Lin Jian1Wen Xiulan1
1.School of Automation,Nanjing Institute of Technology,Nanjing 211167,China; 2.China North Industries Group Corporation,Nanjing 211153,China
关键词:
微分进化 粒子群优化 反向传播神经网络 机器人 逆运动学 收敛速度 权值 阈值 关节角度误差 位置误差
Keywords:
differential evolution particle swarm optimization back propagation neural network robots inverse kinematics convergence speed weights thresholds joint angle error position error
分类号:
TP242
摘要:
针对采用传统反向传播(BP)神经网络算法进行逆运动学求解收敛速度慢的问题,提出将微分进化(DE)与粒子群优化(PSO)算法相结合,对用于机器人逆运动学求解的BP神经网络进行优化。基于机器人正解映射建立优化算法的目标函数,在PSO过程中,引入DE操作优化粒子进化方向,并将此混合算法用于BP神经网络权值与阈值的优化。对KUKA机器人进行仿真实验,结果表明:采用该文方法对机器人逆运动学问题的求解精度高,求得的关节角度误差小于0.1°; 逆运动学求解结果所对应位姿矩阵的位置误差在0.1 mm数量级,具有较好的泛化能力。该文方法满足机器人位置和姿态方面的精度要求
Abstract:
Aiming at the problem of slow convergence speed of traditional back propagation(BP)neural network algorithms,differential evolution(DE)and particle swarm optimization(PSO)are combined to optimize BP neural network for robot inverse kinematics.An objective function of the optimization algorithm is formulated based on the mapping of robot forward kinematics.DE operation is employed to optimize particle evolution direction in PSO,and the weights and thresholds of the BP neural network are optimized.A simulation experiment is proposed for a KUKA robot,and the result shows that:the solution accuracy of robot inverse kinematics of the algorithm proposed here is high,and the joint angle error is below 0.1°; the position error between the initial pose matrix of the robot and that solved by the algorithm proposed here is of the order of magnitude of 0.1 mm,and has good generalization ability.The algorithm proposed here satisfies the accuracy requirements of robot locations and postures.

参考文献/References:

[1] 蔡自兴.机器人学[M].2版.北京:清华大学出版社,2009.
[2]Niku S B.机器人学导论——分析、系统及应用[M].孙富春,朱纪洪,刘国栋,等译.北京:电子工业出版社,2004.
[3]Olaru A,Olaru S.Optimization of the robots inverse kinematics results by using the neural network and LabVIEW simulation[A].2011 International Conference on Future Information Technology[C].Singapore:IACSIT Press,2011:40-45.
[4]吴振宇,姚明江,冯林,等.基于遗传粒子群的PUMA机器人逆运动求解[J].计算机仿真,2011,28(10):173-176. Wu Zhenyu,Yao Mingjiang,Feng Lin,et al.Solving PUMA robot inverse kinematics based on genetic particle swarm optimization[J].Computer Simulation,2011,28(10):173-176.
[5]芮挺,朱经纬,蒋新胜,等.PUMA机器人逆运动模拟退火粒子群求解方法[J].计算机工程与应用,2010,46(3):27-29. Rui Ting,Zhu Jingwei,Jiang Xinsheng,et al.Solving PUMA robot inverse kinematics based on simulated annealing particle swarm optimization[J].Computer Engineering and Applications,2010,46(3):27-29.
[6]钱学毅,迟建华,吴双.微分进化多目标优化算法研究[J].机械传动,2013,37(6):22-25. Qian Xueyi,Chi Jianhua,Wu Shuang.Research on differential evolution multi-objective optimization algorithm[J].Journal of Mechanical Transmission,2013,37(6):22-25.
[7]门志国,彭秀艳,王兴梅,等.基于GA优化BP神经网络辨识的Volterra级数核估计算法[J].南京理工大学学报,2012,36(6):962-967. Men Zhiguo,Peng Xiuyan,Wang Xingmei,et al.Volterra series kernels estimation algorithm based on GA optimized BP neural network identification[J].Journal of Nanjing University of Science and Technology,2012,36(6):962-967.
[8]周炜,廖文和,田威,等.基于粒子群优化神经网络的机器人精度补偿方法研究[J].中国机械工程,2013,24(2):174-179. Zhou Wui,Liao Wenhe,Tian Wei,et al.Method of industrial robot accuracy compensation based on particle swarm optimization neural network[J].China Mechanical Engineering,2013,24(2):174-179.
[9]陈志敏,薄煜明,吴盘龙,等.收敛粒子群全区域自适应粒子滤波算法及其应用[J].南京理工大学学报,2012,36(5):861-868. Chen Zhimin,Bo Yuming,Wu Panlong,et al.Novel landscape adaptive particle filter algorithm based on convergent particle swarm and its application[J].Journal of Nanjing University of Science and Technology,2012,36(5):861-868.
[10]张玲,王玲,吴桐.基于改进的粒子群算法优化反向传播神经网络的热舒适度预测模型[J].计算机应用,2014,34(3):775-779. Zhang Ling,Wang Ling,Wu Tong.Thermal comfort prediction model based on improved particle swarm optimization-back propagation neural network[J].Journal of Computer Applications,2014,34(3):775-779.
[11]岳海波,张树栋,史志茹,等.基于自适应差分进化和BP网络的罗盘误差补偿[J].宇航学报,2013,34(12):1628-1633. Yue Haibo,Zhang Shudong,Shi Zhiru,et al.Compass error compensation based on adaptive differential evolution and BP network[J].Journal of Astronautics,2013,34(12):1628-1633.
[12]Xin Bin,Chen Jie,Peng Zhihong,et al.An adaptive hybrid optimizer based on particle swarm and differential evolution for global optimization[J].Science China Information Sciences,2010,53(5):980-989.
[13]Kim P,Lee J.An integrated method of particle swarm optimization and differential evolution[J].Journal of Mechanical Science and Technology,2009,23(2):426-434.
[14]Hao Zhifeng,Guo Guanghan,Huang Han.A particle swarm optimization algorithm with differential evolution[A].2007 International Conference on Machine Learning and Cybernetics[C].Hong Kong,China:IEEE,2007:1031-1035.
[15]栾丽君,谭立静,牛奔.一种基于粒子群优化算法和差分进化算法的新型混合全局优化算法[J].信息与控制,2007,36(6):708-714. Luan Lijun,Tan Lijing,Niu Ben.A novel hybrid global optimization algorithm based on particle swarm optimization and differential evolution[J].Information and Control,2007,36(6):708-714.

相似文献/References:

[1]熊伟丽,徐保国.基于PSO-SVR的发酵过程状态预估模型[J].南京理工大学学报(自然科学版),2008,(04):517.
 XIONG Wei-li,XU Bao-guo.State Estimation Model of Fermentation Process Based on PSO-SVR[J].Journal of Nanjing University of Science and Technology,2008,(06):517.
[2]汤可宗,肖 绚,贾建华,等.基于离散式多样性评价策略的 自适应粒子群优化算法[J].南京理工大学学报(自然科学版),2013,37(03):12.
 Tang Kezong,Xiao Xuan,Jia Jianhua,et al.Adaptive particle swarm optimization algorithm based on discrete estimate strategy of diversity[J].Journal of Nanjing University of Science and Technology,2013,37(06):12.
[3]徐巍华,陈特欢,许 超,等.基于虚拟仪器的非稳态流管道参数辨识[J].南京理工大学学报(自然科学版),2014,38(01):22.
 Xu Weihua,Chen Tehuan,Xu Chao,et al.Pipeline parameter identification of non-stationary flows based on LabVIEW[J].Journal of Nanjing University of Science and Technology,2014,38(06):22.
[4]徐彬泰,孟祥鹿,田安琪,等.基于粒子群优化及高斯过程回归的铅酸电池荷电状态预测[J].南京理工大学学报(自然科学版),2018,42(02):162.[doi:10.14177/j.cnki.32-1397n.2018.42.02.005]
 Xu Bintai,Meng Xianglu,Tian Anqi,et al.Prediction for state of charge of lead-acid battery by particleswarm optimization with Gaussian process regression[J].Journal of Nanjing University of Science and Technology,2018,42(06):162.[doi:10.14177/j.cnki.32-1397n.2018.42.02.005]
[5]孙新程,孔建寿,刘 钊.基于核主成分分析与改进神经网络的电力负荷中期预测模型[J].南京理工大学学报(自然科学版),2018,42(03):259.[doi:10.14177/j.cnki.32-1397n.2018.42.03.001]
 Sun Xincheng,Kong Jianshou,Liu Zhao.Middle-term power load forecasting model based on kernel principalcomponent analysis and improved neural network[J].Journal of Nanjing University of Science and Technology,2018,42(06):259.[doi:10.14177/j.cnki.32-1397n.2018.42.03.001]
[6]汤可宗,李佐勇,詹棠森,等.一种基于Pareto关联度支配的多目标粒子群优化算法[J].南京理工大学学报(自然科学版),2019,43(04):439.[doi:10.14177/j.cnki.32-1397n.2019.43.04.009]
 Tang Kezong,Li Zuoyong,Zhan Tangsen,et al.A multi-objective particle swarm optimization algorithmbased on Pareto correlation degree domination[J].Journal of Nanjing University of Science and Technology,2019,43(06):439.[doi:10.14177/j.cnki.32-1397n.2019.43.04.009]

备注/Memo

备注/Memo:
收稿日期:2014-05-16 修回日期:2014-07-14
基金项目:江苏省自然科学基金(BK2010479); 南京工程学院校级科研基金(YKJ201319)
作者简介:陈桂(1973-),女,副教授,主要研究方向:机电控制系统及机器人技术,E-mail:zdhxcg@njit.edu.cn。
引文格式:陈桂,陈耀忠,林健,等.机器人逆运动学的微分进化与粒子群优化BP神经网络求解[J].南京理工大学学报,2014,38(6):763-768.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2014-12-31