UAV Path Planning for Wireless Data Harvesting: A Deep Reinforcement Learning Approach - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

UAV Path Planning for Wireless Data Harvesting: A Deep Reinforcement Learning Approach

Résumé

Autonomous deployment of unmanned aerial vehicles (UAVs) supporting next-generation communication networks requires efficient trajectory planning methods. We propose a new end-to-end reinforcement learning (RL) approach to UAVenabled data collection from Internet of Things (IoT) devices in an urban environment. An autonomous drone is tasked with gathering data from distributed sensor nodes subject to limited flying time and obstacle avoidance. While previous approaches, learning and non-learning based, must perform expensive recomputations or relearn a behavior when important scenario parameters such as the number of sensors, sensor positions, or maximum flying time, change, we train a double deep Qnetwork (DDQN) with combined experience replay to learn a UAV control policy that generalizes over changing scenario parameters. By exploiting a multi-layer map of the environment fed through convolutional network layers to the agent, we show that our proposed network architecture enables the agent to make movement decisions for a variety of scenario parameters that balance the data collection goal with flight time efficiency and safety constraints. Considerable advantages in learning efficiency from using a map centered on the UAV's position over a noncentered map are also illustrated.
Fichier principal
Vignette du fichier
publi-6302_1.pdf (1.89 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04138904 , version 1 (23-06-2023)

Identifiants

Citer

Harald Bayerlein, Mirco Theile, Marco Caccamo, David Gesbert. UAV Path Planning for Wireless Data Harvesting: A Deep Reinforcement Learning Approach. GLOBECOM 2020, IEEE Global Communications Conference, IEEE, Dec 2020, Taipei, Taiwan. pp.1-6, ⟨10.1109/GLOBECOM42002.2020.9322234⟩. ⟨hal-04138904⟩

Collections

EURECOM
23 Consultations
40 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More