DocumentCode
2440453
Title
Recurrent neural network based tracking control
Author
Xu, Zhao ; Song, Qing ; Wang, Danwei
Author_Institution
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore, Singapore
fYear
2010
fDate
7-10 Dec. 2010
Firstpage
2454
Lastpage
2459
Abstract
In this paper, a recurrent neural network (RNN) based robust tracking controller is designed for a class of multiple-input-multiple-output (MIMO) discrete time nonlinear systems. The RNN is used in the closed-loop system to estimate online unknown nonlinear system function. A multivariable robust adaptive gradient-descent training algorithm is developed to train RNN. The proposed neural control system guarantees the stability of the closed-loop system and good tracking performance is achieved.
Keywords
MIMO systems; closed loop systems; discrete time systems; gradient methods; nonlinear control systems; recurrent neural nets; robust control; closed loop system; discrete time nonlinear systems; multiple input multiple output systems; multivariable robust adaptive gradient descent training algorithm; recurrent neural network; robust tracking controller; Artificial neural networks; Fuzzy control; Heuristic algorithms; Joints; MIMO; Recurrent neural networks; Training;
fLanguage
English
Publisher
ieee
Conference_Titel
Control Automation Robotics & Vision (ICARCV), 2010 11th International Conference on
Conference_Location
Singapore
Print_ISBN
978-1-4244-7814-9
Type
conf
DOI
10.1109/ICARCV.2010.5707971
Filename
5707971
Link To Document