Abstract
A neural approach is proposed to estimate parameters in dynamics of a direct drive robot. Before the estimation, the input-output data for identification are generated in a sequential and term-by-term manner first. Then a two-layer neural network for parameter identification is proposed, in which the back-propagation training method is used to adjust the weights between neurons. The goal is to find the weights that minimize the root-mean-square error between the identification data and output of the network. With the estimated dynamics, existing trajectory-tracking algorithms, such as the well-known computed-torque method, can then be applied to make the robot move along a desired trajectory.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
AsadaH., KanadeT. and TakeyamaI.: 1983, Control of a direct-drive arm, ASME J. Dynam. Syst., Meas., Contr. 105, 36–142.
AsadaH. and Youcef-ToumiK.: 1984, Analysis and design of a direct-drive arm with fivebar-link parallel drive mechanism, ASME J. Dynam. Syst., Meas., Contr. 106, 225–230.
AsadaH. and Youcef-ToumiK.: 1987, Direct-Drive Robots: Theory and Practice, MIT Press, Cambridge, MA.
ChuS. R., ShoureshiR. and TenorioM.: 1990, Neural networks for system identification, IEEE Control Systems Magazine 10, 31–35.
CraigJ. J.: 1989, Introduction to Robotic Manipulators: Mechanics and Control, 2nd edn, Addison-Wesley, Reading, MA.
FunanashiK.I.: 1989, On the approximate realization of continuous mappings by neural networks, Neural Networks 2, 183–192.
HornikK., StinchcombeM. and WhiteH.: 1989, Multilayer feedforward networks are universal approximators, Neural Networks 2, 359–366.
KoskoB.: 1992, Neural Networks and Fuzzy Systems, Prentice-Hall, Englewood Cliffs, NJ.
LewisF. L., AbdallahT. and DawsonD. M.: 1993, Control of Robot Manipulators, MacMillan, New York.
LjungL. and SöderstromT.: 1985, Theory and Practice of Recursive Identification, MIT Press, Cambridge, MA.
NarendraK. S. and ParthasarathyK.: 1990, Identification and control of dynamical systems using neural networks, IEEE Trans. on Neural Networks 1, 4–27.
PoggioT. and GirosiF.: 1990, Networks for approximation and learning, Proc. IEEE 78(9), 1481–1497.
WassermannP. D.: 1989, Neural Computing: Theory and Practice, Van Nostrand Reinhold, New York.
Youcef-ToumiK. and KuoA. T. Y.: 1993, High-speed trajectory control of a direct-drive manipulator, IEEE Trans. on Robotics and Automation, 9, 102–108.
ZuradaJ. M.: 1992, Introduction to Artificial Neural Systems, West Publishing Company, St. Paul, MN.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wu, CJ., Huang, CH. Back-propagation neural networks for identification and control of a direct drive robot. J Intell Robot Syst 16, 45–64 (1996). https://doi.org/10.1007/BF00309655
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00309655