Intersections are critical areas for road safety and traffic efficiency, accounting for a significant portion of vehicle crashes and fatalities. While connected and autonomous vehicle (CAV) technologies offer a promising solution for autonomous intersection management, many existing proposals either rely on computationally heavy centralized controllers or overlook the practical impairments of real-world communication networks. This paper introduces seamless mobility of vehicles over intersections (Moveover), a novel algorithm comprising a vehicle-to-network (V2N) communication protocol designed to let vehicles cross autonomous intersections without stopping. Moveover delegates trajectory and speed profile selection to individual vehicles, allowing each CAV to optimize them according to its unique kinematic characteristics. Simultaneously, a local intersection controller prevents collisions through deterministic conflict zone reservations. The algorithm is rigorously evaluated under both ideal and non-ideal networking conditions, specifically modeling 4G and 5G communication delays, across multiple layouts including single-lane, multi-lane, and roundabouts. Furthermore, we test Moveover on a real urban map with multiple intersections. Simulation results demonstrate that Moveover significantly outperforms baseline strategies, offering substantial improvements in travel times and reduced pollutant emissions.

翻译：交叉口是道路安全与交通效率的关键区域，车辆碰撞事故与死亡事件中相当大比例发生于此类区域。虽然网联自动驾驶车辆（CAV）技术为自主交叉口管理提供了前景广阔的解决方案，但现有研究方案多依赖于计算密集的集中式控制器，或忽视了实际通信网络的现实损伤。本文提出一种面向交叉口的车辆无缝通行算法（Moveover），该创新算法包含一套车联网（V2N）通信协议，旨在实现车辆无需停车通过自主交叉口。Moveover将轨迹与速度曲线选择任务分配至各独立车辆，使每辆CAV能依据其独特运动学特性进行自主优化。同时，本地交叉口控制器通过确定性的冲突区域预留机制防止碰撞发生。该算法在理想与非理想网络条件下（特别针对4G与5G通信延迟建模）进行了严格评估，测试场景涵盖单车道、多车道及环岛等多种布局。此外，我们在真实城市路网的多交叉口环境中对Moveover进行了验证。仿真结果表明，Moveover显著优于基线策略，在行程时间优化与污染物减排方面实现实质性提升。