Adaptive sampling of cumulus clouds with UAVs

Abstract : This paper presents an approach to guide a fleet of Unmanned Aerial Vehicles to actively gather data in low-altitude cumulus clouds with the aim of mapping atmospheric variables. Building on-line maps based on very sparse local measurements is the first challenge to overcome, for which an approach based on Gaussian Processes is proposed. A particular attention is given to the on-line hyperparameters optimization , since atmospheric phenomena are strongly dynamical processes. The obtained local map is then exploited by a trajectory planner based on a stochastic optimization algorithm. The goal is to generate feasible trajectories which exploit air flows to perform energy-efficient flights, while maximizing the information collected along the mission. The system is then tested in simulations carried out using realistic models of cumu-lus clouds and of the UAVs flight dynamics. Results on mapping achieved by multiple UAVs and an extensive analysis on the evolution of Gaussian Processes hyper-parameters is proposed.
Type de document :
Article dans une revue
Autonomous Robots, Springer Verlag, 2018, 42 (2), pp.491-512. 〈10.1007/s10514-017-9625-1〉
Liste complète des métadonnées

Littérature citée [35 références]  Voir  Masquer  Télécharger
Contributeur : Simon Lacroix <>
Soumis le : samedi 13 mai 2017 - 18:42:18
Dernière modification le : vendredi 2 mars 2018 - 13:10:42
Document(s) archivé(s) le : mardi 15 août 2017 - 00:10:38


Fichiers produits par l'(les) auteur(s)



Christophe Reymann, Alessandro Renzaglia, Fayçal Lamraoui, Murat Bronz, Simon Lacroix. Adaptive sampling of cumulus clouds with UAVs. Autonomous Robots, Springer Verlag, 2018, 42 (2), pp.491-512. 〈10.1007/s10514-017-9625-1〉. 〈hal-01522250〉



Consultations de la notice


Téléchargements de fichiers