Development of a system to diagnose autonomous underwater vehicles

In the underwater environment, installation of a proper scheme to cope with unexpected situations is essential for Autonomous Underwater Vehicles (AUVs) to carry out their mission out of human reach. This paper proposes a model-based approach of selfdiagnosis for AUVs in order to supervise whether the vehicle operates itself in an appropriate way. The proposed self-diagnosis is carried out based on a dynamics model of an AUV and an active mechanism to obtain desirable information. The dynamics model is constructed by an artificial neural network taking advantage of its flexible learning capability. When a sensor is found to be defective, dead reckoning usingits corresponding outputof thedynamics modelcan beintroduced in anattemptto cope with the defect. The performance of the proposed system was examined by implementing it on the 'Twin-Burger', a test-bed AUV. It is shown that the system without the introduction of extra sensors detects failures of onboard sensors and actuators, and then selects a proper action scheme to minimize the damage to the AUV.