Robust control system design by use of neural networks and its application to UAV flight control

Author

Nakanishi, Hiroaki ; Inoue, Koichi

Author_Institution

Graduate Sch. of Eng., Kyoto Univ., Japan

Volume

3

fYear

2004

fDate

25-29 July 2004

Firstpage

1769

Abstract

Stochastic uncertainty are the most typical in flight control system, because wind direction and wind speed, which have significant effect on the flight, vary stochastically. We propose methods to design robust control systems by training a neural network against stochastic uncertainties. Numerical simulations of flight control of an autonomous unmanned helicopter demonstrate the effectiveness of proposed methods.

Keywords

aerospace computing; aerospace control; control system synthesis; helicopters; learning (artificial intelligence); neural nets; nonlinear control systems; remotely operated vehicles; robust control; stochastic processes; uncertain systems; autonomous unmanned helicopter; flight control system; neural networks; nonlinear control systems; robust control system design; stochastic uncertainty; unmanned air vehicles; Aerospace control; Design methodology; Helicopters; Neural networks; Numerical simulation; Robust control; Stochastic systems; Uncertainty; Unmanned aerial vehicles; Wind speed;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-8359-1

Type

conf

DOI

10.1109/IJCNN.2004.1380875

Filename

1380875