Directed Graph-Based Reinforcement Learning for CAV Cooperative Ramp Merging in Mixed Traffic

Cooperative ramp merging in mixed autonomy traffic presented methodological challenges due to heterogeneous human-driven vehicle behaviors and direction-dependent interactions among agents. Existing reinforcement learning approaches frequently relied on undirected graph representations and uniform t...

Description complète

Détails bibliographiques

Auteurs principaux:	Diwei Zheng, De-Chih Lee
Format:	Artigo
Langue:	Inglês
Publié:	IEEE 2026-01-01
Collection:	IEEE Access
Sujets:	Cooperative ramp merging deep reinforcement learning autonomous vehicles spatio-temporal feature fusion hybrid adjacency matrix
Accès en ligne:	https://ieeexplore.ieee.org/document/11569740/
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!