Abstract
A neural network based identification approach of manipulator dynamics is presented. For a structured modelling, RBF-like static neural networks are used in order to represent and adapt all model parameters with their non-linear dependences on the joint positions. The neural architecture is hierarchically organised to reach optimal adjustment to structural apriori-knowledge about the identification problem. The model structure is substantially simplified by general system analysis independent of robot type. But also a lot of specific features of the utilised experimental robot are taken into account.
A fixed, grid based neuron placement together with application of B-spline polynomial basis functions is utilised favourably for a very effective recursive implementation of the neural architecture. Thus, an online identification of a dynamic model is submitted for a complete 6 joint industrial robot.
Similar content being viewed by others
References
E. Freund and H. Hoyer, “Das Prinzip nichtlinearer Systementkopplung mit Anwendung auf Industrieroboter.” Regelungstechnik, vol. 28, no. 3/4, pp. 80–87, 116–126, 1980.
M.W. Spong and M. Vidyasagar, Robot Dynamics and Control, 1st. edn., John Wiley & Sons: New York, 1989.
L. Sciavicco and B. Siciliano, Modeling and Control of Robot Manipulators, 1st. edn., The McGraw-Hill, New York, 1996.
S. T¨urk, “Zur Modellierung der Dynamik von Robotern mit rotatorischen Gelenken,” Ph.D. Thesis, Technische Universität München, 1990.
V. Held, “Parameterschätzung und Reglersynthese für Indusatrieroboter,” Ph.D. Thesis, Technische Hochschule Darmstadt, 1992.
M. Daemi-Avval, “Modellierung und Identifikation des Dynamik von Industrierobotern für den Eisnsatz in Regelungen,” Ph.D. Thesis, Universität Hannover, 1998.
K.Y. Goldberg and B.A. Pearlmutter, “Using backpropagation with temporal windows to learn the dynamics of the CMU direct-drive arm II,” Advances in Neural Information Procesing Systems I, pp. 356–363, 1989.
F. Peinemann, “Neuronale Regelungskonzepte zur sensomotorischen Koordination von Industrierobotern,” Ph.D. Thesis, Universität Bremen, 1996.
M. Jansen, “Learning an accurate neural model of the dynamics of a typical industrial robot,” in Int. Conf. on Artificial Neural Networks, Sorrento., 1994, pp. 1257–1260.
S. Miesbach, “Bahnführung von Robotern mit Neuronalen Netzen,” Ph.D. Thesis, Technische Universität München, 1995.
Y.H. Kim and F.L. Lewis, High-Level Feedback Control with Neural Networks, 1st. edn., World Scintific Series in Robotics and Intelligent Systems, World Scintific: Singapore, 1998.
J. Beerhold, “Stabile adaptive Regelung nichtlinearer Mehrgrösen-Systeme mit neuronalen RBF-Netzen am Beispiel von Mehrgelenkrobotern,” Automatisierungstechnik, vol. 44, no. 12, pp. 577–583, 1996.
S.S. Ge, T.H. Lee, and C.J. Harris, Adaptive Neural Network Control of Robotic Manipulators, 1st. edn., World Scintific Series in Robotics and Intelligent Systems, World Scintific: Singapore, 1998.
M. Krabbes and C. Döschner, “Modelling of robot dynamics based on multi-dimensional RBF-like neural network,” in: 1999 IEEE International Conference on Information, Intelligence, and System (ICIIS' 99), Bethesda, USA, November 1999, pp. 180–187.
J.J. Craig, Introduction to Robotics Mechanics and Control, 2nd. edn., Addison-Wesley: Reading, MA, 1989.
T. Poggio and F. Girosi, “A theory of networks for approximation and learning,” AI Memo No. 1140, MIT, Cambridge, MA, 1989.
M. Brown and C. Harris, Neurofuzzy Adaptive Modelling and Control, 1st. edn., Series in Systems and Control Engeneering, Prentice Hall: Englewood Cliffs, NJ: 1994.
J. Zhang and A. Knoll, “Constructing fuzzy controllers with B-spline models-principles and applications,” in Int. Journ. Intelligent Systems, vol. 13, no. 2/3, pp. 257–286, 1998.
B. Widrow and M.E. Hoff, “Adaptive switching circuits,” in: IRE WESCON Convention Record, New York, 1960, pp. 96–104.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Krabbes, M., Döschner, C. Modelling of Complete Robot Dynamics Based on a Multi-Dimensional, RBF-like Neural Architecture. Applied Intelligence 17, 61–73 (2002). https://doi.org/10.1023/A:1015779731969
Issue Date:
DOI: https://doi.org/10.1023/A:1015779731969