Neural Network Learning Control for Position and Force Tracking of Multi-Manipulator Systems

ABSTRACTIn this article, an approach to improving the performance of multi-manipulator systems using neural networks is presented. This approach is formulated in the constrained motion framework, within which a nominal feedback control augmented by a neural network is derived. It is shown that the closed-loop system with the neural network learning on-line is stable in the sense that all signals in the systems are bounded. It is further proved that the performance of the multi-manipulator system is improved in the sense that the “size” of a certain error measure decreases as the learning process of the neural network is iterated. Results of computer simulations conducted to verify the analytical conclusions are presented. The results of this work suggest that neural networks could be used as “add-on” control modules to improve the performance of industrial robots in execution of tasks involving two or more cooperative manipulators.

[1]  David E. Orin,et al.  Control of Force Distribution in Robotic Mechanisms Containing Closed Kinematic Chains , 1981 .

[2]  J. Brant Arseneau,et al.  VLSI and neural systems , 1990 .

[3]  Takanori Shibata,et al.  Neuromorphic control for robotic manipulators-position, force and impact control , 1990, Proceedings. 5th IEEE International Symposium on Intelligent Control 1990.

[4]  C. A. Desoer,et al.  Nonlinear Systems Analysis , 1978 .

[5]  Linda R. Petzold,et al.  Numerical solution of initial-value problems in differential-algebraic equations , 1996, Classics in applied mathematics.

[6]  Edward J. Davison,et al.  Experimental Analysis Of A Centralized/decentralized Controller For Robotic Manipulators , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Y. F. Zheng,et al.  Optimal Load Distribution for Two Industrial Robots Handling a Single Object , 1989 .

[8]  Yoshiki Uchikawa,et al.  A neural network compensator for uncertainties of robotic manipulators , 1990, 29th IEEE Conference on Decision and Control.

[9]  Andrew A. Goldenberg,et al.  An adaptive approach to motion and force control of multiple coordinated robot arms , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[10]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[11]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[12]  Suguru Arimoto,et al.  Cooperative motion control of multiple robot arms or fingers , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[13]  J. Y. S. Luh,et al.  Constrained Relations between Two Coordinated Industrial Robots for Motion Control , 1987 .

[14]  M. A. Unseren,et al.  Reduced Order Model and Decoupled Control Architecture for Two Manipulators Holding a Rigid Object , 1991 .

[15]  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.

[16]  Mark W. Spong,et al.  Robust linear compensator design for nonlinear robotic control , 1985, IEEE J. Robotics Autom..

[17]  R. W. Daniel,et al.  Control of machines with friction : Brian Armstrong-Hélouvry , 1992, Autom..

[18]  Edward J. Davison,et al.  Robust motion/force control of cooperative multi-arm systems , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[19]  S. A. Hayati.  Position and force control of coordinated multiple arms , 1988 .

[20]  Ian D. Walker,et al.  Analysis of Motion and Internal Loading of Objects Grasped by Multiple Cooperating Manipulators , 1991, Int. J. Robotics Res..

[21]  N. H. McClamroch,et al.  Feedback stabilization and tracking of constrained robots , 1988 .

[22]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[23]  Jorge Angeles,et al.  Real-time force optimization in parallel kinematic chains under inequality constraints , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[24]  Li-Chun T. Wang,et al.  Dynamic load-carrying capacity and inverse dynamics of multiple cooperating robotic manipulators , 1994, IEEE Trans. Robotics Autom..