[en] Autonomous Unmanned Aerial Vehicles (UAVs) are in increasing demand thanks to their applicability in a wide range of domains. However, to fully exploit such potential, UAVs should be capable of intelligently planning their collision-free paths as that impacts greatly the execution quality of their applications. While being a problem well addressed in literature, most presented solutions are either computationally complex centralised approaches or ones not suitable for the multiobjective requirements of most UAV use-cases. This extended abstract introduces ongoing research on a novel distributed Pareto path planning algorithm incorporating a dynamic multi-criteria decision matrix allowing each UAV to plan its collision-free path relying on local knowledge gained via digital stigmergy. The article presents some initial simulations results of a distributed UAV Traffic Management system (UTM) on a weighted multilayer network.
Disciplines :
Computer science
Author, co-author :
SAMIR LABIB, Nader ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > PCOG
DANOY, Grégoire ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
BRUST, Matthias R. ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > PCOG
BOUVRY, Pascal ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
External co-authors :
no
Language :
English
Title :
A Distributed Pareto-based Path Planning Algorithm for Autonomous Unmanned Aerial Vehicles (Extended Abstract)
Publication date :
07 January 2021
Event name :
29th International Joint Conference on Artificial Intelligence IJCAI 2020 Multi-Agent Path Finding Workshop (MAPF)