Optimization of Trajectories in Bounded-Acceleration Traffic Models Using Mean Field Game Framework

The evolution of Connected Autonomous Vehicles (CAVs) has highlighted the need for advanced traffic models capable of addressing the unique dynamics of such systems. Traditional traffic models often fail to account for the complexities introduced by bounded acceleration, a crucial factor for maintaining safety and efficiency in high-density traffic scenarios. This study investigates the integration of Mean-Field Game (MFG) theory with boundedacceleration traffic models to optimize vehicle trajectories and enhance traffic flow management. By bridging the gap between macroscopic traffic flow principles and microscopic vehicle dynamics, this research introduces a scalable and adaptive approach tailored to the specific demands of CAV systems. The proposed framework improves traffic modeling by incorporating realistic physical constraints, enabling safer and more efficient traffic operations and supporting the seamless integration of CAVs into modern transportation networks.