Original scientific paper
Multilayer Neural Net Trajectory Tracking Control for Underwater Vehicle
Ognjen Kuljača
; Alcorn State University, Systems Research Institute
Jyotirmay Gadewadikar
; Alcorn State University, Systems Research Institute
Krunoslav Horvat
; Brodarski Institut, Control Systems Department
Abstract
An adaptive multilayer neural network controller for high precision maneuvering of underwater vehicles is presented. Maneuvering of underwater vehicles requires special attention to a number of factors, including thruster and vehicle’s nonlinearities, couplings which exist between various degrees of freedom as well as effects of the sea currents. The neuro control system for underwater
vehicle maneuvering described in this paper is based on a conventional controller supported with the so-called adaptive neural network. The adaptive neural network has two tunable layers, thus
the problem of selection of proper basis is avoided.
Keywords
adaptive neural network; precise maneuvering; trajectory tracking; underwater vehicl
Hrčak ID:
46367
URI
Publication date:
1.12.2009.
Visits: 1.380 *