This paper investigates the use of a multilayered perceptron (MLP) network in controlling an unmanned underwater vehicle over a sea-bed profile and compares the use of applying chemotaxis learning to that of the more commonly employed back propagation algorithm. The reults show that, for differing sized MLPs, the chemotaxis algorithm produces a succesful controller over the sea-bed profile in an improved training time. Also it will be shown that, in the presence of noise and change in vehicle mass, the neural controller out-performed a classical proportional-integral-derivative controller
A neural auto-depth controller for an unmanned underwater vehicle
Eine neurale Regeleinrichtung fuer die Tiefensteuerung eines unbemanntenUnterwasserfahrzeuges
The Journal of Navigation ; 50 , 2 ; 292-302
1997
11 Seiten, 7 Bilder, 5 Tabellen, 10 Quellen
Article (Journal)
English
A Neural Auto-depth Controller for an Unmanned Underwater Vehicle
Online Contents | 1997
|BASE | 2017
|