Coordinated multi lane-changing on highways for connected and automated vehicles in mixed traffic

Abstract

This paper presents a decentralized coordination algorithm for multi-vehicle lane changing in mixed traffic composed of Connected and Automated Vehicles (CAVs) and Human-Driven Vehicles (HDVs). Unlike approaches based on traditional single-vehicle decision-making, centralized control, or learning-based methods that depend on iterative exploration, the proposed framework employs a decentralized Markov Decision Process (MDP)-based model to compute a ready-to-use policy for each CAV. Assuming known reward structures, this model enables policy computation in advance. The framework is further extended with a priority-based mechanism for resolving trajectory conflicts, vehicle-to-vehicle communication for synchronized decision-making, smooth trajectory generation, and a Proportional–Integral–Derivative (PID) controller to ensure smooth longitudinal control during lane changes.

Simulation results demonstrate significant gains in traffic efficiency, with cooperative vehicles achieving up to 40% reductions in travel time compared to those constrained to fixed-lane behavior and affected by the presence of slower, non-cooperative HDVs. Acceleration remained below 2 m/s${}^2$, indicating smooth transitions and enhanced passenger comfort. The approach also minimized sudden braking and hesitation during lane merges, resulting in safer and more stable interactions. These findings highlight the framework’s potential to improve throughput, safety, and comfort in mixed-autonomy traffic, offering a scalable solution for real-time cooperative decision-making. Future work will explore online learning and model adaptation to better address highly dynamic environments, including unpredictable human driving behavior and varying conditions such as weather disturbances.