Published September 25, 2012 | Version 14940
Journal article Open

An Enhanced Situational Awareness of AUV's Mission by Multirate Neural Control

Description

This paper focuses on a critical component of the situational awareness (SA), the neural control of depth flight of an autonomous underwater vehicle (AUV). Constant depth flight is a challenging but important task for AUVs to achieve high level of autonomy under adverse conditions. With the SA strategy, we proposed a multirate neural control of an AUV trajectory using neural network model reference controller for a nontrivial mid-small size AUV "r2D4" stochastic model. This control system has been demonstrated and evaluated by simulation of diving maneuvers using software package Simulink. From the simulation results it can be seen that the chosen AUV model is stable in the presence of high noise, and also can be concluded that the fast SA of similar AUV systems with economy in energy of batteries can be asserted during the underwater missions in search-and-rescue operations.

Files

14940.pdf

Files (947.5 kB)

Name Size Download all
md5:04c5f4b1f09419cae42ba1a640d15133
947.5 kB Preview Download