The trajectory planning and tracking of redundant manipulators by a hierarchical neurocontroller

A hierarchical neurocontroller architecture, which comprises two artificial neural network (ANN) systems for inversion kinematics solution and motion control of robotic redundant manipulators is presented. The solution of inverse kinematics is realized by a Hopfield network, in which the global planning of a collision-free trajectory is based on the potential functions using the necessary conditions of minimum for an integral type criterion. A direct servo-level controller is utilized by a multilayer feedforward network based on backpropagation algorithm, in which the computed torque technique is employed to control manipulator's joints to track the trajectory. The stability of the both sub-controllers is analyzed. Another major contribution of this paper is to provide an approach for the most difficult problem in using neurocontroller-how to efficiently train the designed ANNs.

[1]  John T. Wen,et al.  A two-time-scale neural controller for the tracking control of rigid manipulators , 1994 .

[2]  Bin Jin.  Robotic manipulator trajectory control using neural networks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[3]  Pradeep K. Khosla,et al.  Real-time obstacle avoidance using harmonic potential functions , 1991, IEEE Trans. Robotics Autom..

[4]  R.T. Newton,et al.  Neural network control of a space manipulator , 1993, IEEE Control Systems.

[5]  A S Rana,et al.  Collision-free motion planning of multiarm robots using evolutionary algorithms , 1997 .

[6]  Rahmat A. Shoureshi,et al.  Neural networks for system identification , 1990 .

[7]  C. Fonseca,et al.  GENETIC ALGORITHMS FOR MULTI-OBJECTIVE OPTIMIZATION: FORMULATION, DISCUSSION, AND GENERALIZATION , 1993 .

[8]  A.M.S. Zalzala,et al.  Dynamic Modelling and Genetic- Based Motion Planning of Mobile Manipulator Systems with Nonholonomic Constraints , 1995 .

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

[10]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[11]  John R. Rice,et al.  Numerical methods, software, and analysis , 1983 .

[12]  Richard S. Sutton,et al.  Neural networks for control , 1990 .

[13]  Dan Boneh,et al.  On genetic algorithms , 1995, COLT '95.

[14]  M. Galicki,et al.  Optimal Planning of a Collision-free Trajectory of Redundant Manipulators , 1992 .

[15]  Kalyanmoy Deb,et al.  Muiltiobjective Optimization Using Nondominated Sorting in Genetic Algorithms , 1994, Evolutionary Computation.

[16]  Kang G. Shin,et al.  Direct control and coordination using neural networks , 1993, IEEE Trans. Syst. Man Cybern..

[17]  Peter J. Fleming,et al.  Multiobjective genetic algorithms made easy: selection sharing and mating restriction , 1995 .

[18]  Bin Jin,et al.  A multitask neuromorphic controller for redundant robots , 1994, Proceedings of 1994 33rd IEEE Conference on Decision and Control.