Designing neural networks for adaptive control
Authors:
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (01912216) , 1833-1839
Abstract
This paper discusses the design of neural networks to solve specific problems of adaptive control. In particular, it investigates the influence of typical problems arising in real-world control tasks as well as techniques for their solution that exist in the framework of neurocontrol. Based on this investigation, a systematic design method is developed. The method is exemplified for the development of an adaptive force controller for a robot manipulator.Keywords
This publication has 10 references indexed in Scilit:
- Learning controllers for industrial robotsMachine Learning, 1996
- Acquiring robot skills via reinforcement learningIEEE Control Systems, 1994
- Adaptive control of nonlinear multivariable systems using neural networksNeural Networks, 1994
- Centralized and decentralized neuro-adaptive robot controllersNeural Networks, 1993
- Adaptive control of dynamic systems by back propagation networksNeural Networks, 1993
- A reinforcement learning—based architecture for fuzzy logic controlInternational Journal of Approximate Reasoning, 1992
- Neural Networks1990
- Phoneme recognition using time-delay neural networksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Neuronlike adaptive elements that can solve difficult learning control problemsIEEE Transactions on Systems, Man, and Cybernetics, 1983
- A New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)Journal of Dynamic Systems, Measurement, and Control, 1975