Drone-assisted lane change maneuver using reinforcement learning with dynamic reward function - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Drone-assisted lane change maneuver using reinforcement learning with dynamic reward function

Résumé

This paper provides a Lane Change Assistance (LCA) platform that communicates with Unmanned Aerial Vehi-cles (UAV). The proposed platform is based on a reinforcement learning technique, where a Deep Q-Network (DQN) is trained to make lane change decisions. The reward function of the DQN agent considers safety, comfort and efficiency perspectives. Specifically, the safety reward, based on the road vehicular density, is adapted dynamically by the drone during the training phase. Performance analysis proves that the proposed platform improves the total travel time while reducing the collision rate and responding to urgent lane changes in a timely manner.
Fichier non déposé

Dates et versions

hal-03887747 , version 1 (07-12-2022)

Identifiants

Citer

Jialin Hao, Rola Naja, Djamal Zeghlache. Drone-assisted lane change maneuver using reinforcement learning with dynamic reward function. IEEE 2022 18th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), Oct 2022, Thessaloniki, Greece. pp.314-320, ⟨10.1109/WiMob55322.2022.9941534⟩. ⟨hal-03887747⟩
25 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More