A biologically inspired neural network for navigation with obstacle avoidance in autonomous underwater and surface vehicles

This paper describes a neural network model for the reactive behavioural navigation of an autonomous underwater vehicle (AUV) in which an innovative, neurobiological inspired sensorization control system and a hardware architectures are being implemented. The AUV has been with several types of environmental and oceanographic instruments such as CTD sensors, chlorophyll, turbidity, optical dissolved oxygen (YSI V6600 sonde) and nitrate analyzer (SUNA) together with ADCP, side scan sonar and video camera, in a flexible configuration to provide a water quality monitoring platform with mapping capabilities. This neurobiological inspired control architecture for autonomous intelligent navigation was implemented on an AUV capable of operating during large periods of time for observation and monitoring. In this work, the autonomy of the AUV is evaluated in several scenarios.