Integrating Operators' Preferences into Decisions of Unmanned Aerial Vehicles: Multi-layer Decision Engine and Incremental Preference Elicitation

International audienceDue to the nature of autonomous Unmanned Aerial Vehicles (UAV) missions, it is important that the decisions of a UAV stay consistent with the priorities of an operator, while at the same time allowing them to be easily audited and explained. We therefore propose a multi-layer decision engine that follows the logic of an operator and integrates its preferences through a Multi-Criteria Decision Aiding model. We also propose an incremental approach to elicit the operator's preferences, in view of minimizing his/her cognitive fatigue during this task