Edge Computing for Visual Navigation and Mapping in a UAV Network - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Edge Computing for Visual Navigation and Mapping in a UAV Network

Résumé

This research work presents conceptual considerations and quantitative evaluations into how integrating computation offloading to edge computing servers would offer a paradigm shift for an effective deployment of autonomous drones. The specific mission that has been considered is collaborative autonomous navigation and mapping in a 3D environment of a small drone network. Specifically, in order to achieve this mission, each drone is required to compute a low latency, highly compute intensive task in a timely manner. The proposed model decides for each task, while considering the impact on performance and mission requirements, whether to (i) compute locally, (ii) offload to the edge server, or (iii) to the ground station. Extensive simulation work was performed to assess the effectiveness of the proposed scheme compared to other models.
Fichier principal
Vignette du fichier
MAM2020.pdf (274.3 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02965660 , version 1 (18-01-2022)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Mohamed Ayoub Messous, Hermann Hellwagner, Sidi-Mohammed Senouci, Driton Emini, Dominik Schnieders. Edge Computing for Visual Navigation and Mapping in a UAV Network. ICC 2020 - 2020 IEEE International Conference on Communications (ICC), Jun 2020, Dublin, Ireland. pp.1-6, ⟨10.1109/ICC40277.2020.9149087⟩. ⟨hal-02965660⟩
95 Consultations
187 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More