Applying Utility Theory to Improve Autonomous Underwater Vehicle Mission Playload Planning and Replanning

This work presents a method by which utility theory can be applied to the payload decision making processes of autonomous underwater vehicles (AUV) for mission planning and replanning purposes. Such an application allows AUVs to determine the ‘best’ payload to use for a specific mission without operator intervention, thus improving AUV reliability while the vehicle is out of communication range from the operator. Because ‘best’ is subjective, focusing on relevant payload attributes and tailoring these functions to individual operator preferences ensures a unique vehicle makes decisions that align with a unique operator’s preferences. The creation of these functions is an iterative process that involves interviewing an individual operator to determine the form and weight of that operator’s preferences based upon theoretical payload attributes, followed by the testing of the resulting equation using actual payload attributes. Contained in this paper are example utility functions that take into consideration three attributes each for describing the decision making preferences for three AUV operators when determining the appropriate side scan sonar to use to perform a specific seabed imagining mission. These three functions were tested and determined to produce results that align with the individual operators’ preferences, thus validating the appropriateness of these equations for these operators on this mission.