A Hybrid Particle Swarm Optimization for Manipulator Inverse Kinematics Control

A very important problem usually encountered in the study of robot manipulators is the inverse kinematics problem. The inverse kinematics control of a robotic manipulator requires solving non-linear equations having transcendental functions and involving time-consuming calculations. In this paper, a hybrid particle swarm optimization based on the behaviour of insect swarms and natural selection mechanism is firstly presented to optimize neural network (HPSONN) for manipulator inverse kinematics. Compared with the results of the fast back propagation learning algorithm (FBP), conventional genetic algorithm (GA) based elitist reservation (EGA), improved GA (IGA) and immune evolutionary computation (IEC), the simulation results verify the hybrid particle swarm optimization is more effective for manipulator inverse kinematics control than above most methods.

[1]  P.D. Lawrence,et al.  Manipulator inverse kinematics based on joint functions , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[2]  William W. Melek,et al.  A Genetic Algorithm Approach to solve for Multiple Solutions of Inverse Kinematics using Adaptive Niching and Clustering , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[3]  Jong-Hwan Kim,et al.  Evolutionary ordered neural network and its application to robot manipulator control , 1996, Proceedings of the 1996 IEEE IECON. 22nd International Conference on Industrial Electronics, Control, and Instrumentation.

[4]  P. J. Angeline,et al.  Using selection to improve particle swarm optimization , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[5]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[6]  Martin Brown,et al.  Neurofuzzy adaptive modelling and control , 1994 .

[7]  Jing Tan,et al.  The combination of immune evolution and neural network for nonlinear time series forecasting , 2006, International Symposium on Instrumentation and Control Technology.

[8]  J. Teng,et al.  A Novel ACS-Based Optimum Switch Relocation Method , 2002, IEEE Power Engineering Review.

[9]  John Baillieul,et al.  Kinematic programming alternatives for redundant manipulators , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[10]  Ming Li,et al.  Hybrid Evolutionary Search Method Based on Clusters , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Yoshikazu Fukuyama,et al.  A Hybrid Particle Swarm Optimization for Distribution State Estimation , 2002, IEEE Power Engineering Review.

[12]  R. Eberhart,et al.  Comparing inertia weights and constriction factors in particle swarm optimization , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[13]  Ali M. S. Zalzala,et al.  A hybrid intelligent active force controller for robot arms using evolutionary neural networks , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[14]  Aiguo Song,et al.  An improved genetic algorithm for planar and spatial straightness error evaluation , 2003 .

[15]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[16]  Chang-Hwan Im,et al.  Multimodal function optimization based on particle swarm optimization , 2006, IEEE Transactions on Magnetics.

[17]  Liqun Gao,et al.  Transmission network optimal planning using the particle swarm optimization method , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[18]  E. Watanabe,et al.  A study of generalization ability of neural network for manipulator inverse kinematics , 1991, Proceedings IECON '91: 1991 International Conference on Industrial Electronics, Control and Instrumentation.