AUV robot's real-time control navigation system using multi-layer neural networks management

Abstract

This paper describes the detection and tracking of static and dynamic underwater object(s). It addresses the case study application of a multi-layer artificial neural network prototype model on the bases of an analytical approach. It supports an Autonomous Underwater Vehicle (AUV) robot's controller system with automated detection of processed-obstacle-signals. The significance of this work is to investigate the neural network learning perception process of signal detection within operational environments. In this case, the acoustic-sound density is the source of detection and classification processes. The outcomes of this work are presented as simulated results that illustrate the error-detection control system. It activates due to a range of training forces originating from encountered acoustic-sensors' signals. In addition, the benefit of further simulation of the proposed technique can provide sufficient knowledge on the set-up of the controller's cyclic triggering towards actuators. The other benefits are included with control overshoot and rotational alignment of thrusters for precise navigational trajectory in real-time.