On the convergence of neural tracking controller for robotics

Author

Song, Q. ; Xiao, J. ; Soh, Y.C.

Author_Institution

Sch. of Electr. & Electron. Eng., Nanyang Technol. Inst., Singapore

Volume

2

fYear

1998

fDate

16-18 Dec 1998

Firstpage

1593

Abstract

A robust backpropagation algorithm with a dead zone scheme is used for the online tuning of the neural network (NN) tracking control system. This assures the convergence of the multi-layered NN in the presence of disturbance. It is proved that the selection of a smaller range of the dead zone leads to a smaller estimate error of the NN, and hence a smaller tracking error of the NN tracking controller. The proposed algorithm is applied to a three-layered network with adjustable weights and a complete convergence proof is provided. The results can also be extended to the network with more hidden layers

Keywords

backpropagation; closed loop systems; convergence; discrete time systems; multilayer perceptrons; neurocontrollers; nonlinear control systems; position control; robots; dead zone scheme; estimate error; neural tracking controller; online tuning; robust backpropagation algorithm; three-layered network; tracking error; Control systems; Convergence; Error correction; Linear approximation; Neural networks; Neurons; Noise robustness; Robot control; Robust control; Robust stability;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 1998. Proceedings of the 37th IEEE Conference on

Conference_Location

Tampa, FL

ISSN

0191-2216

Print_ISBN

0-7803-4394-8

Type

conf

DOI

10.1109/CDC.1998.758520

Filename

758520