Backward construction-a decomposed learning method for robot force/position control

A decomposed learning method, where the motor task is partitioned into several stages by virtue of its task characters, is proposed. The controller can be implemented by neural networks which can be trained partially in different stages. Some of these neural networks, which can be called output networks, directly drive the objects to move along the desired trajectories. The others perform some virtual activations to feed the output networks to make them have a proper output; these are called internal networks. Simple samples that can describe the expected partial characters are engaged in each stage. The well-trained parts can be used to help to train the other parts. The approach uses the notion of backward construction to build backwards the interpretation of the desired motor strategy progressively. This approach is demonstrated in detail with an example of robotic manipulator position/force learning control.<<ETX>>

[1]  P.J. Werbos,et al.  An overview of neural networks for control , 1991, IEEE Control Systems.

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[3]  Toshio Fukuda,et al.  Adaptive force control of manipulators with consideration of object dynamics , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[4]  John J. Craig,et al.  Hybrid position/force control of manipulators , 1981 .

[5]  Michael I. Jordan,et al.  Generic constraints on underspecified target trajectories , 1989, International 1989 Joint Conference on Neural Networks.

[6]  T.P. Leung,et al.  A Robust Neural Network Controller , 1992, 1992 American Control Conference.

[7]  Mitsuo Kawato,et al.  Learning control for a closed loop system using feedback-error-learning , 1990, 29th IEEE Conference on Decision and Control.

[8]  Toshio Fukuda,et al.  Adaptation and learning for robotic manipulator by neural network , 1990, 29th IEEE Conference on Decision and Control.

[9]  Moshe Cohen,et al.  Learning impedance parameters for robot control using an associative search network , 1991, IEEE Trans. Robotics Autom..

[10]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[11]  Neville Hogan,et al.  Impedance Control: An Approach to Manipulation: Part I—Theory , 1985 .

[12]  Hai-Long Pei,et al.  A Neural Network Robot Force Controller , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.