Bayesian network-based security decision-making method for the full-ocean-depth “Wukong” AUV

Abstract

Safety is a critical issue to be considered for a full-ocean-depth AUV, which is a platform to submerge into the deepest part of the ocean. This paper investigates the security decision-making problem for a full-ocean-depth AUV. In order to make a reasonable decision when the AUV encounters a hazard case, such as the leakage of the electronic cabin, this paper presents a security decision-making method based on Bayesian network for the full-ocean-depth AUV to improve the safety. Specifically, the structure of the Bayesian network is determined based on the greedy search algorithm, and it also gives the parameters of each node in the Bayesian network. Finally, this method is applied on the full-ocean-depth AUV, named “Wukong” AUV, to demonstrate the effectiveness of the developed method.