Deep Reinforcement Learning for Trajectory Control of Connected and Automated Vehicles at a Mixed-Traffic Intersection

Abstract

AbstractVehicle trajectory control has garnered significant interest due to the potential of connected and automated vehicles (CAVs) to enhance traffic efficiency and reduce accidents. Effective vehicle control is crucial for autonomous driving and has ...Practical ApplicationsThe proposed DRL-based trajectory control framework offers significant potential for real-world deployment of CAVs in complex urban environments. By leveraging the DDPG algorithm, the control policy achieves a balance among safety, ...