A Bayesian approach to predicting risk of loss during Autonomous Underwater Vehicle missions

摘要

Autonomous Underwater Vehicles (AUVs) are effective platforms for science research and monitoring, and for military and commercial data-gathering purposes. However, there is an inevitable risk of loss during any mission. Quantifying the risk of loss is complex, due to the combination of vehicle reliability and environmental factors, and cannot be determined through analytical means alone. A critical step in assessing risk uses expert judgment of the fault history of the vehicle, and, consequently, what affect faults or incidents have on the probability of loss in a defined environment. However, formal expert judgment is a time-consuming process, and a method is needed to broaden the applicability of judgments beyond the narrow confines of an elicitation for a defined environment. We propose and explore a solution founded on a Bayesian Belief Network, where the results of the expert judgment elicitation are taken as the initial prior probability of loss. The design of the network topology captures the causal effects of the environment separately on the vehicle and on the support platform, and combines these to produce an updated probability of loss. Complementary expert knowledge is included within the conditional probability tables of the Bayesian Belief Network. To illustrate the process, the case of an AUV operating under sea ice cover is considered, and the affects of ice concentration, thickness and vessel capability explored.