Stabilizing position/force control of robots interacting with environment by learning connectionist structures

Abstract This paper is mostly concerned with the application of connectionist architectures for fast on-line learning of robot dynamic uncertainties used at the executive hierarchical control level in robot contact tasks. The connectionist structures are integrated in non-learning control laws for contact tasks which enable stabilization and good tracking performance of position and force. It has been shown that the problem of tracking a specified reference trajectory and specified force profile with a present quality of their transient response can be efficiently solved by means of the application of a four-layer perceptron. A four-layer perceptron is part of a hybrid learning control algorithm through the process of synchronous training which uses fast learning rules and available sensor information in order to improve robotic performance progressively in the minimum possible number of learning epochs. Some simulation results of the deburring process with robot MANUTEC r3 are shown to verify effectiveness of the proposed control learning algorithms.

[1]  J. Y. S. Luh,et al.  Application of neural network with real-time training to robust position/force control of multiple robots , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.

[2]  Roderic A. Grupen,et al.  Learning admittance mappings for force-guided assembly , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[3]  Miomir Vukobratovic,et al.  Decomposed connectionist architecture for fast and robust learning of robot dynamics , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[4]  Masayoshi Tomizuka,et al.  Learning hybrid force and position control of robot manipulators , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[5]  Miomir Vukobratovic,et al.  Highly efficient robot dynamics learning by decomposed connectionist feedforward control structure , 1995, IEEE Trans. Syst. Man Cybern..

[6]  Yoshiki Uchikawa,et al.  Trajectory control of robotic manipulators using neural networks , 1991 .

[7]  Sheng Liu,et al.  Transfer of human skills to neural net robot controllers , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[8]  Miomir Vukobratovic,et al.  Contact control concepts in manipulation robotics-an overview , 1994, IEEE Trans. Ind. Electron..

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

[10]  Roderic A. Grupen,et al.  Learning reactive admittance control , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[11]  Yuri Ekalo,et al.  New approach to control of robotic manipulators interacting with dynamic environment , 1996, Robotica.

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

[13]  Suguru Arimoto,et al.  Learning control for robot tasks under geometric endpoint constraints , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[14]  Neville Hogan,et al.  Impedance Control: An Approach to Manipulation , 1984, 1984 American Control Conference.

[15]  H. Harry Asada,et al.  Representation and learning of nonlinear compliance using neural nets , 1993, IEEE Trans. Robotics Autom..

[16]  Daniel E. Whitney,et al.  Historical Perspective and State of the Art in Robot Force Control , 1985, Proceedings. 1985 IEEE International Conference on Robotics and Automation.

[17]  Seul Jung,et al.  On neural network application to robust impedance control of robot manipulators , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[18]  Miomir Vukobratović,et al.  Robot control structures for high-quality learning in flexible manufacturing , 1994 .

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