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

Arwa Khannoussi (1, 2) , Alexandru Liviu Olteanu (3) , Christophe Labreuche (4) , Pritesh Narayan (5) , Catherine Dezan (2) , Jean-Philippe Diguet (6) , Jacques Petit-Frère (7) , Patrick Meyer (8, 1)

1 Lab-STICC_IMTA_CID_DECIDE
2 Lab-STICC_UBO_CACS_MOCS
3 Lab-STICC_UBS_CID_DECIDE
4 Thales Research and Technology [Palaiseau]
5 UWE Bristol - University of the West of England [Bristol]
6 Lab-STICC_UBS_CACS_MOCS
7 THALES [France]
8 LUSSI - Département Logique des Usages, Sciences sociales et Sciences de l'Information

Due 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.

Domaines: Mathématique discrète [cs.DM]; Intelligence artificielle [cs.AI]; Recherche opérationnelle [math.OC]

Arwa Khannoussi, Alexandru Liviu Olteanu, Christophe Labreuche, Pritesh Narayan, Catherine Dezan, et al.. Integrating Operators' Preferences into Decisions of Unmanned Aerial Vehicles: Multi-layer Decision Engine and Incremental Preference Elicitation. 6th International Conference, ADT 2019, Oct 2019, Durham, NC, United States. pp.49-63, ⟨10.1007/978-3-030-31489-7_4⟩. ⟨hal-02334090⟩