Abstract
This chapter discusses a method for the identification of dynamics and control of a multilink industrial robot manipulator using Runge-Kutta-Gill neural networks (RKGNNs). RKGNNs are used to identify an ordinary differential equation of the dynamics of the robot manipulator. A structured function neural network (NN) with subnetworks to represent the components of the dynamics is used in the RKGNNs. The subnetworks consist of shape adaptive radial basis function (RBF) NNs. An evolutionary algorithm is used to optimize the shape parameters and the weights of the RBFNNs. Due to the fact that the RKGNNs can accurately grasp the changing rates of the states, this method can effectively be used for long-term prediction of the states of the robot manipulator dynamics. Unlike in conventional methods, the proposed method can even be used without input torque information because a torque network is part of the function network. This method can be proposed as an effective option for the dynamics identification of manipulators with high degrees-of-freedom, as opposed to the derivation of dynamic equations and making additional hardware changes as in the case of statistical parameter identification such as linear leastsquares method. Experiments were carried out using a sevenlink industrial manipulator.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
An, C. H., Atkeson, C. G., and Hollerbach, J. M. (1986): Estimation of Internal Parameters of Rigid Body Links of Manipulators. Artificial Intelligence Memo 887, MIT Artificial Intelligence Laboratory
Kawasaki, H. and Nishimura, K. (1998): Terminal Link Parameter Estimation of Robotic Manipulators. IEEE Trans. on Robotics and Automation. 4(5), 485–490.
Wu, C.-J. and Huang, C.-H. (1996): Back-Propagation Neural Networks for Identification and Control of a Direct Drive Robot. J. of Intelligent and Robotic Systems. 16 (1), 45–64.
Kwan, C., Lewis, F. L., and Dawson, D. M. (1998): Robust Neural-Network Control of Rigid-Link Electrically Driven Robots. IEEE Trans. on Neural Networks. 9 (4), 481–488.
Behera, L., Gopal, M., and Chaudhury, S. (1996): On Adaptive Trajectory Trackingg of a Robot Manipulator Using Inversion of Its Neural Emulator. IEEE Trans. on Neural Networks. 7 (6), 1401–1414.
Wang, Y.-J., and Lin, C.-T. (1998): Runge-Kutta Neural Network for Identification of Dynamical Systems in High Accuracy. IEEE Trans. on Neural Networks. 9 (2), 294–307.
Noriega, J. R. and Wang, H. (1998): A Direct Adaptive Neural-Network Control for Unknown Nonlinear Systems and Its Application. IEEE Trans. on Neural Networks. 9 (1), 27–34.
Yao, X. and Liu, Y. (1997): A New Evolutionary System for Evolving Artificial Neural Networks. IEEE Trans. on Neural Networks. 8 (3), 694–713.
Craig, J. J. (1989): Introduction to Robotics: Mechanics and Control. 2nd edn, Reading, MA: Addison-Wesley.
Web, A. R. and Shannon, S. (1998): Shape Adaptive Radial Basis Functions. IEEE Trans. on Neural Networks. 9 (6), 1155–1166.
Nanayakkara, T., Watanabe, K., and Izumi, K. (1999): Evolving in Dynamic Environments Through Adaptive Chaotic Mutation. in Procs. of Fourth International Symposium on Artificial Life and Robotics. Oita, Japan, Jan 19–22, 2, 520–523.
Nanayakkara, T., Watanabe, K., Kiguchi, K., and Izumi, K. (1999): Evolutionary Optimization with Strategic Moves Based on Historical Knowledge. in Procs. of the First SOFT Kyushu Branch Annual Conference, 21–28
Back, T. and Schwefel, H. P. (1993): An Overview of Evolutionary Algorithms for Parameter Optimization. Evolutionary Computation. 1 (1), 1–23.
Leung, Y. (1997): Degree of Population Diversity—A Perspective on Premature Convergence in Genetic Algorithms and its Markov Chain Analysis. IEEE Trans. on Neural Networks. 8 (5), 1165–1175.
Nanayakkara, T., Watanabe, K. and Izumi, K. (1999): Evolving Runge-KuttaGill RBF Networks to Estimate the Dynamics of a Multi-Link Manipulator. in Proc. of IEEE International Conference on Systems, Man, and Cybernetics. 2, 770–775.
Nanayakkara, T., Watanabe, K., Kiguchi, K., and Izumi, K. (2000): Dynamic Identification of an Industrial Seven-Link Manipulator by Evolving RungeKutta-Gill RBF Networks. in Proc. of Fifth International Symposium on Artificial Life and Robotics. 2, 669–672.
Kim, J.-H. and Myung, H. (1997): Evolutionary Programing Techniques for Constrained Optimization Problems. IEEE Trans. on Evolutionary Computation. 1 (2), 129–140.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Nanayakkara, T., Watanabe, K., Kiguchi, K., Izumi, K. (2003). Evolutionary Dynamics Identification of Multi-Link Manipulators Using Runge-Kutta-Gill RBF Networks. In: Reznik, L., Kreinovich, V. (eds) Soft Computing in Measurement and Information Acquisition. Studies in Fuzziness and Soft Computing, vol 127. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-36216-6_14
Download citation
DOI: https://doi.org/10.1007/978-3-540-36216-6_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-53509-3
Online ISBN: 978-3-540-36216-6
eBook Packages: Springer Book Archive