An intelligent control system for remotely operated vehicles

Author

Yuh, J. ; Lakshmi, Ranganath

Author_Institution

Dept. of Mech. Eng., Hawaii Univ., Honolulu, HI, USA

Volume

18

Issue

1

fYear

1993

fDate

1/1/1993 12:00:00 AM

Firstpage

55

Lastpage

62

Abstract

The application of a neural network controller to remotely operated vehicles (ROVs) is described. Three learning algorithms for online implementation of a neural net controller are discussed with a critic equation. These control schemes do not require any information about the system dynamics except an estimate of the inertia terms. Selection of the number of layers in the neural network, the number of neurons in the hidden layer, initial weights for the network and the critic coefficient were done based on the results of preliminary tests. The performances of the three learning algorithms were compared by computer simulation. The effectiveness of the neural net controller in handling time-varying parameters and random noise is shown by a case study of the ROV system

Keywords

digital simulation; feedforward neural nets; intelligent control; learning (artificial intelligence); marine systems; mobile robots; telecontrol; computer simulation; critic coefficient; inertia terms; intelligent control; learning algorithms; neural network controller; neurons; online implementation; random noise; remotely operated vehicles; time-varying parameters; underwater vehicles; Computer simulation; Control systems; Equations; Intelligent control; Neural networks; Neurons; Remotely operated vehicles; Testing; Time varying systems; Vehicle dynamics;

fLanguage

English

Journal_Title

Oceanic Engineering, IEEE Journal of

Publisher

ieee

ISSN

0364-9059

Type

jour

DOI

10.1109/48.211496

Filename

211496