Simulation-based learning in knowledge-based controllers

Author

Stroud, Phillip D.

Author_Institution

Div. of Technol. & Safety Assessment, Los Alamos Nat. Lab., NM, USA

fYear

1996

fDate

15-18 Sep 1996

Firstpage

168

Lastpage

174

Abstract

A methodology is presented to transform knowledge-based controllers into adaptive structure representations. These adaptive controllers are then evolved using automatic directed search methods, where the performance of the trial controllers is evaluated through simulation in a synthetic environment. This automatically acquired knowledge is incorporated back into a revised knowledge-based controller. This process is developed and demonstrated using the flight and fire controllers of a simulated airborne laser system as a testbed

Keywords

adaptive control; aerospace control; aerospace simulation; control engineering computing; intelligent control; search problems; software packages; adaptive controllers; adaptive structure representations; automatic directed search methods; fire controllers; flight control; knowledge-based controllers; simulated airborne laser system; simulation-based learning; Adaptive control; Aerospace simulation; Automatic control; Fires; Intelligent sensors; Missiles; Object oriented modeling; Optical control; Programmable control; Search methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control, 1996., Proceedings of the 1996 IEEE International Symposium on

Conference_Location

Dearborn, MI

ISSN

2158-9860

Print_ISBN

0-7803-2978-3

Type

conf

DOI

10.1109/ISIC.1996.556196

Filename

556196