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...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Diwei Zheng, De-Chih Lee
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	IEEE 2026-01-01
Schriftenreihe:	IEEE Access
Schlagworte:	Cooperative ramp merging deep reinforcement learning autonomous vehicles spatio-temporal feature fusion hybrid adjacency matrix
Online-Zugang:	https://ieeexplore.ieee.org/document/11569740/
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!