A New Solution for Inverse Kinematics of 7-DOF Manipulator Based on Neural Network
For dealing with the complexity in gaining inverse kinematics solution of 7-DOF manipulator, a new approach based on RBF neural network is proposed. To solve the problem of multi-solution caused by redundancy, a rule for a joint of “best compliance based on weighted Least Square Method is supposed at the beginning of this paper, which makes the multisolution a mono-one. And with application of genetic algorithm (GA) to search for all global optimum solution, the sample-data of artificial neural network training is gained successfully. In artificial neural network training and simulating, satisfactory result has been achieved. Simulation shows that the method proposed in the paper is feasible, provides a new approach for inverse kinematics solution of manipulator of any redundancy.
GA neural network redundant manipulator joint compliance inverse kinematics
Yugui Yang Guangzheng Peng Yifeng Wang Hongli Zhang
Department of Automatic Control, School of Information Science and Technology, Beijing Institute of Technology, Beijing, 100081, China
国际会议
2007 IEEE International Conference on Automation and Lofistics
山东济南
英文
2007-08-18（万方平台首次上网日期，不代表论文的发表时间）