Stable adaptive systems
Multilayer feedforward networks are universal approximators
Neural Networks
Neural networks for control systems: a survey
Automatica (Journal of IFAC)
Feedback Systems: Input-Output Properties
Feedback Systems: Input-Output Properties
Robotic Agent Control Based on Adaptive Intelligent Algorithm in Ubiquitous Networks
KES-AMSTA '07 Proceedings of the 1st KES International Symposium on Agent and Multi-Agent Systems: Technologies and Applications
Adaptive fuzzy output feedback control for robot manipulators
SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
| Hi-index | 0.00 |
In this paper a controller based on neural networks is proposed toachieve output trajectory tracking of rigid robot manipulators. Neuralnetworks used here are one hidden layer ones so that their outputs dependlinearly on the parameters. Our method uses a decomposed connectioniststructure. Each neural network approximate a separate element of thedynamical model. These approximations are used to perform an adaptive stablecontrol law. The controller is based on direct adaptive techniques and theLyapunov approach is used to derive the adaptation laws of the nets’parameters. By using an intrinsic physical property of the manipulator, thesystem is proved to be stable. The performance of the controller depends onthe quality of the approximation, i.e. on the inherent reconstruction errorsof the exact functions.