A neural network based controller for underwater robotic vehicles

TL;DR

This paper presents a neural network-enhanced control system for underwater robotic vehicles, improving their dynamic positioning capabilities by compensating for uncertainties and disturbances, validated through numerical simulations.

Contribution

It introduces a novel neural network-based control approach combined with Lyapunov Stability Theory for underwater vehicle positioning.

Findings

Effective disturbance compensation demonstrated in simulations

Improved stability and robustness of underwater vehicle control

Potential for enhanced underwater exploration capabilities

Abstract

Due to the enormous technological improvements obtained in the last decades it is possible to use robotic vehicles for underwater exploration. This work describes the development of a dynamic positioning system for remotely operated underwater vehicles based. The adopted approach is developed using Lyapunov Stability Theory and enhanced by a neural network based algorithm for uncertainty and disturbance compensation. The performance of the proposed control scheme is evaluated by means of numerical simulations.