Advanced Control Concepts for Industrial Robots
Many tasks in robot control are very nonlinear and complex. These tasks can be performed in an advantageous way by using fuzzy methods or artificial neuronal networks. In the first part of this paper the optimal design of fuzzy controllers acting as common nonlinear time discrete controllers is investigated. In the second part artificial neuronal networks in connection with several controller structures are presented. Best results are obtained by using the structure of the adaptive model based robot control system. It is shown that the fuzzy controller and the artificial neuronal networks lead to better results than conventional control concepts.
KeywordsFuzzy Controller Control Circuit Industrial Robot Robot Control Linear Controller
Unable to display preview. Download preview PDF.
- Fu, K.S., Gonzales, R.C. and Lee, C.S.G.: Robotics: control, vision and intelligence. McGraw Hill, New York, 1987Google Scholar
- Kuhn, Th., Wernstedt, J.: ILMFUZZY Version 1. 0 Ein Programmpaket zur Simulation und Optimierung einschleifiger Fuzzy Regelkreise. TU Ilmenau 1992Google Scholar
- Miller, W.T., III, Hewes, R.P., Glanz, F. H., and Kraft, L.G. III: Real-time dynamic control of an industrial manipulator using a neural-network-based learning controller. IEEE Trans., 1990, RA-6 (1), pp. 1–9Google Scholar
- Poo, A.N., Ang Jr. M.H., Teo, C.L. and Qing Li: Performance of a neuro-model-based robot controller: adaptability and noise rejection. Intelligent Systems Engineering, Autumn 1992, pp. 50–62Google Scholar
- Tourassis, V.D.: Computer-control of robotic manipulators using predictors. Proc. 1987 IEEE Symp. on Intelligent control, Philadelphia, Pennsylvania 18–20 January 1987, pp. 204–209Google Scholar
- Tourassis, V.D. and Neumann, C.P.: Robust nonlinear feedback control for robot manipulatrs. IEEE Proc. D, 1985, 132, pp. 134143Google Scholar