Neural Adaptive Approach-Application to Robot Force Control in an Unknown Environment
Yacine Amirat*, Karim Djouani*, Mohamed Kirad*,
and Nadia Saadia**
*LISSI - Université Paris 12, 120-122, rue Paul Armangot 94400 Vitry sur seine, France
**Electronics and Computer Science Faculty, USTHB University, BP 32, Bab-ezzouar, El Alia, Alger Algeria
This paper presents an effective neural adaptive approach for robot force control with changing/unknown robot-environment interaction dynamic properties. In this approach, a multilayered neural network controller is trained at first off line from data collected during contact motion in order to perform a smooth transition from free to contact motion. Then, an adaptive process is implemented online through a desired impedance reference model such that the closed-loop system maintains a good performance and compensates for uncertain/unknown dynamics of the robot-environment interaction. The effectiveness of the proposed approach has been evaluated for the force control of a 6 DOF (Degree Of Freedom) C5-links parallel robot executing rectangular peg-in-hole insertions with weak tolerances. The experimental results demonstrate that the robot’s skill improves effectively and force control performances are good even if robot-environment interaction dynamic properties change.
and Nadia Saadia, “Neural Adaptive Approach-Application to Robot Force Control in an Unknown Environment,” J. Robot. Mechatron., Vol.18, No.5, pp. 529-538, 2006.
-  O. Khatib, “A unified approach to motion and force control of robot manipulators,” IEEE Trans. On Robotics and Automation, 1(3), pp. 43-53, 1987.
-  M. T. Mason, “Compliance and force control theory for computer controller manipulators,” IEEE Trans. On SMC, Vol.11(6), pp. 418-432, 1981.
-  M. H. Raibert and J. J. Craig, “Hybrid position/force control of manipulators,” Trans. Of ASME, J. Dynamics Systems Measurement and Control, Vol.102, pp. 126-133, 1982.
-  D. E. Whitney and J. L. Nevins, “What is the remote center compliance (RCC) and what can it do,” Proc. 9th Int. Symp. On ind. Rob., pp. 135-147, 1979.
-  V. Perdereau, “Contribution à la commande hybride force-position,” Ph.D. dissertation, University of Paris 6, 1991.
-  C. Reboulet and A. Robert, “Hybrid control of manipulator equipped with an active compliant wrist,” Proc. Of the Int. Symp. of Rob. Res., France, 1985, pp. 237-241.
-  D. E. Whitney, “Historical perspective and state of the art in robot force control,” The International Journal of Robotics Research, 6, pp. 3-14, 1987.
-  G. Zeng and A. Hemami, “An overview of robot force control,” Robotica, 15, pp. 473-482, 1997.
-  D. Katic, “Some recent issues in connectionist robot control,” Proceedings of the Third ECPD International Conference on Advanced Robotics, Intelligent Automation and Active Systems, pp. 79-92, 1997.
-  K. Kiguchi and T. Fukuda, “A survey of force control of robot manipulators using soft computing techniques,” Proceedings of 1999 IEEE International Conference on System, Man, and Cybernetics, pp. II764-II769, 1999.
-  D. Psaltis, A. Sideris, and A. Yamamura, “A multilayered neural network Controller,” IEEE Control System Magazine, pp. 17-21, 1988.
-  H. Asada, “Teaching and learning of compliance using neural nets : representation and generation of nonlinear compliance,” IEEE Int. Conf. on Robotics and Automation, pp. 1237-1244, 1990.
-  D. H. Nguyen and B. Widrow, “Neural networks for self-learning control systems,” IEEE Control System Magazine, Vol.10(3), pp. 18-23, 1990.
-  P. Antsakis, “Neural networks in control systems,” IEEE Control System Magazine, Vol.10, pp. 3-5, 1990.
-  J. H. Sira-Ramirez and S. H. Zak, “The adaptation of perceptrons with application to inverse dynamics identification of unknown dynamic systems,” IEEE Trans. On Syst. Man. Cybern. SMC-21, pp. 634-643, 1991.
-  S. S. Ge and T. H. Lee, “Adaptive neural network control of flexible joint robots based on feedback linearisation,” Int. J. Systems Science, Vol.29(6), pp. 1229-1234, 1998.
-  T. Zhang, S. S. Ge, and C. C. Hang, “Adaptive output feedback control for general non-linear systems using multilayer neural networks,” Proc. American Control Conf., Philadelphia, Vol.1, pp. 520-524, 1998.
-  M. Tokita, T. Mitsuoka, T. Fukuda, and T. Kurihara, “Force control of robot manipulator by neural network model,” Journal of Robotics and Mechatronics, Vol.2, pp. 273-281, 1990.
-  T. Yamada and T. Yabuta, “Neural network controller using autotuning method for nonlinear functions,” IEEE Transactions on Neural Networks, 3, pp. 595-601, 1992.
-  K. Kiguchi and D. S. Necsulescu, “Control of multi-DOF robots using neural networks,” Proceedings of the Knowledge-Based Systems and Robotics Workshop, pp. 747-754, 1993.
-  K. Kiguchi and T. Fukuda, “Neural network controllers for robot manipulators application of damping neurons,” Advanced Robotics, 12, pp. 191-208, 1998.
-  S. Jung and T. C. Hsia, “Neural network impedance force control of robot manipulator,” IEEE Transactions on Industrial Electronics, 45, pp. 451-461, 1998.
-  Y. Amirat, F. Artigue, and J. Pontnau, “A six degrees of freedom parallel robots with C5 links,” Robotica, 10(1), pp. 35-44, 1992.
-  Y. Amirat, “Contribution à la commande de haut niveau de processus robotisés et à l’utilisation des concepts de l’IA dans l’interaction robot-environnement,” HDR Dissertation, University of Paris 12, France, January, 1996.
-  E. Dafaoui, Y. Amirat, J. Pontnau, and C. François, “Analysis and design of six DOF parallel manipulator. Modelling singular configuration and workspace,” IEEE Trans. on Robotics and Automation, 14(1), pp. 78-92, 1998.
-  M. Kirad, M. Guihard, and C. François, “Application of position/force control to scale calibration,” Int. Journal of Mechanics, Electronics and Control, Elsevier Science Ltd., Pergamon Press, England, pp. 207-224, 1999.
-  M. Kirad, “Contribution à la commande force position selon une approche neuronale. Application à un robot parallèle C5 destiné à des tâches d’assemblage,” Ph.D. dissertation, University of Paris 12, 2000.
-  N. Saadia, Y. Amirat, N. K. M’Sirdi, and J. Pontnau, “Neural hybrid control of manipulators, stability analysis,” Robotica, Vol.19, pp. 41-51, 2001.
-  G. Taguchi and S. Konishi, “Orthogonal Arrays and Linear Graphs,” ASI Press, 1987.
-  E. F. Ryckebusch and I. K. Craig, “Pid Tuning For A Multivariable Plant Using Taguchi-based Methods,” In the Proc. Of the 15th IFAC World Congress On Automatic Control, Barcelona, Spain, July 21-26, 2002.
-  R. Williams and D. Zipser, “A learning algorithm for continually running fully recurrent neural networks,” Neural Computation, 1, pp. 270-280, 1989.
-  K. S. Narendra and K. Parthasrathy, “Identification and control of dynamic systems using neural networks,” IEEE, Trans. Neural Networks NN-1(1), pp. 4-27, 1990.
-  R. S. Sutton, “Generalisation in Reinforcement learning: Successful examples using sparse coarse coding,” In D. Touretzky, M. Mozer, and M. Hasselmo (eds.), Neural Information Processing Systems, 8, 1996.
-  H. Asada and Y. Asari, “The direct teaching of tool manipulation skills via the impedance identification of human motion,” Proc. IEEE Int. Conf. on Robotics and Automation (ICRA), Philadelphia, PA, 1988, pp. 1269-1274.
-  P. Sikka and B. J. McCarragher, “Stiffness-based understanding and modelling of contact tasks by human demonstration,” Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), Grenoble, France, 1997, pp. 464-470.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.
Copyright© 2006 by Fuji Technology Press Ltd. and Japan Society of Mechanical Engineers. All right reserved.