A survey and experimental study of neural network AUV control

Author

Lorentz, Jørgen ; Yuh, J.

Author_Institution

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

fYear

1996

fDate

2-6 Jun 1996

Firstpage

109

Lastpage

116

Abstract

This paper presents a survey of neural network controllers for AUVs. A direct adaptive neural net controller incorporating integral action was designed for the heave motion of the ODIN underwater vehicle. The neural net controller is trained online by parallel recursive error prediction method and the critic equation. The influence of the various design parameters of the neural net controller was investigated by computer simulation and the controller was also experimentally tested using the ODIN. Results of the computer simulation and experiment are discussed in this paper

Keywords

adaptive control; intelligent control; learning systems; marine systems; motion control; neurocontrollers; real-time systems; simulation; ODIN underwater vehicle; adaptive control; computer simulation; heave motion control; neural network control; online control; parallel recursive error prediction; Adaptive control; Computer errors; Computer simulation; Error correction; Integral equations; Motion control; Neural networks; Prediction methods; Programmable control; Underwater vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Autonomous Underwater Vehicle Technology, 1996. AUV '96., Proceedings of the 1996 Symposium on

Conference_Location

Monterey, CA

Print_ISBN

0-7803-3185-0

Type

conf

DOI

10.1109/AUV.1996.532406

Filename

532406