Connected and Automated Vehicles (CAVs) offer a promising solution to the challenges of mixed traffic with both CAVs and Human-Driven Vehicles (HDVs). A significant hurdle in such scenarios is traffic oscillation, or the "stop-and-go" pattern, during car-following situations. While HDVs rely on limited information, CAVs can leverage data from other CAVs for better decision-making. This allows CAVs to anticipate and mitigate the spread of deceleration waves that worsen traffic flow. We propose a novel "CAV-AHDV-CAV" car-following framework that treats the sequence of HDVs between two CAVs as a single entity, eliminating noise from individual driver behaviors. This deep reinforcement learning approach analyzes vehicle equilibrium states and employs a state fusion strategy. Trained and tested on diverse datasets (HighD, NGSIM, SPMD, Waymo, Lyft) encompassing over 70,000 car-following instances, our model outperforms baselines in collision avoidance, maintaining equilibrium with both preceding and leading vehicles and achieving the lowest standard deviation of time headway. These results demonstrate the effectiveness of our approach in developing robust CAV control strategies for mixed traffic. Our model has the potential to mitigate traffic oscillation, improve traffic flow efficiency, and enhance overall safety.

翻译：网联自动驾驶车辆（CAVs）为应对CAV与人工驾驶车辆（HDVs）混行的交通挑战提供了一种前景广阔的解决方案。在此类场景中，一个重大障碍是跟车过程中出现的交通振荡，即“走走停停”模式。HDV仅能依赖有限的信息，而CAV可以利用来自其他CAV的数据进行更优决策。这使得CAV能够预测并缓解加剧交通流恶化的减速波传播。我们提出了一种新颖的“CAV-AHDV-CAV”跟车框架，该框架将两辆CAV之间的HDV序列视为一个整体，从而消除了来自个体驾驶员行为的噪声干扰。这种深度强化学习方法分析了车辆的平衡状态，并采用了状态融合策略。在涵盖超过70,000个跟车实例的多样化数据集（HighD、NGSIM、SPMD、Waymo、Lyft）上进行训练和测试后，我们的模型在避免碰撞、与前车及前导车保持平衡以及实现最低车头时距标准差方面均优于基线方法。这些结果证明了我们的方法在开发面向混合交通的鲁棒CAV控制策略方面的有效性。我们的模型具有缓解交通振荡、提升交通流效率以及增强整体安全性的潜力。