Integrating operators’ preferences into decisions of unmanned aerial vehicles: Multi-layer decision engine and incremental preference elicitation

Khannoussi, Arwa; Olteanu, Alexandru-Liviu; Labreuche, Christophe; Narayan, Pritesh; Dezan, Catherine; Diguet, Jean-Philippe; Petit-Frère, Jacques; Meyer, Patrick

Abstract

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.

Citation

Khannoussi, A., Olteanu, A., Labreuche, C., Narayan, P., Dezan, C., Diguet, J., …Meyer, P. (2019). Integrating operators’ preferences into decisions of unmanned aerial vehicles: Multi-layer decision engine and incremental preference elicitation. In S. Pekeč, & K. B. Venable (Eds.), International Conference on Algorithmic Decision Theory (49-64). https://doi.org/10.1007/978-3-030-31489-7_4

• Conference Name: 6th International Conference, ADT 2019
• Conference Location: Durham, NC, USA
• Start Date: Oct 25, 2019
• End Date: Oct 27, 2019
• Acceptance Date: Oct 1, 2019
• Online Publication Date: Oct 10, 2019
• Publication Date: Dec 31, 2019
• Deposit Date: Oct 27, 2019
• Publicly Available Date: Oct 11, 2020
• Publisher: Springer Verlag
• Volume: 11834
• Pages: 49-64
• Series Title: Lecture Notes in Computer Science
• Series ISSN: 0302-9743
• Edition: 2019
• Book Title: International Conference on Algorithmic Decision Theory
• ISBN: 9783030314880
• DOI: https://doi.org/10.1007/978-3-030-31489-7_4
• Public URL: https://uwe-repository.worktribe.com/output/4154528
• Publisher URL: https://link.springer.com/book/10.1007/978-3-030-31489-7#about
• Additional Information: First Online: 10 October 2019; Conference Acronym: ADT; Conference Name: International Conference on Algorithmic DecisionTheory; Conference City: Durham, NC; Conference Country: USA; Conference Year: 2019; Conference Start Date: 25 October 2019; Conference End Date: 27 October 2019; Conference ID: aldt2019; Conference URL: https://conferences.fuqua.duke.edu/adt/; Type: Double-blind; Conference Management System: Confy; Number of Submissions Sent for Review: 31; Number of Full Papers Accepted: 10; Number of Short Papers Accepted: 7; Acceptance Rate of Full Papers: 32% - The value is computed by the equation "Number of Full Papers Accepted / Number of Submissions Sent for Review * 100" and then rounded to a whole number.; Average Number of Reviews per Paper: 3; Average Number of Papers per Reviewer: 3; External Reviewers Involved: No