Maximizing Information Usefulness in Vehicular CP Networks Using Actor-Critic Reinforcement Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Maximizing Information Usefulness in Vehicular CP Networks Using Actor-Critic Reinforcement Learning

Résumé

Cooperative Perception (CP) allows Connected and Autonomous Vehicles (CAVs) to enhance their Environmental Awareness (EA) by sharing locally perceived objects through CP messages (CPMs). The European Telecommunications Standards Institute has recently defined a set of CPM generation rules to achieve a trade-off between EA and Channel Busy Ratio (CBR) despite massive perception data. Nonetheless, these rules still lack the consideration of information usefulness, resulting in a considerable volume of useless information transmitted in the CP network. This limitation could increase CBR and thus decrease EA due to the loss of CPMs in the network. This paper introduces CloudAC-IU, a cloud-based deep reinforcement learning approach to learn CAVs to maximize perception information usefulness in the network. Simulation results highlight that CloudAC-IU enhances EA by decreasing CBR and increasing CPM reception for CAVs compared to the state-ofthe-art works.
Fichier principal
Vignette du fichier
GHNAYA CNSM 22 camera clean et finale last.pdf (589.2 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04231597 , version 1 (06-10-2023)

Identifiants

Citer

Imed Ghnaya, Toufik Ahmed, Mohamed Mosbah, Hasnaa Aniss. Maximizing Information Usefulness in Vehicular CP Networks Using Actor-Critic Reinforcement Learning. 2022 18th International Conference on Network and Service Management (CNSM), Oct 2022, Thessaloniki, Greece. ⟨10.23919/CNSM55787.2022.9964740⟩. ⟨hal-04231597⟩
6 Consultations
23 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More