[论文解读] A Game Theory Based Ramp Merging Strategy for Connected and Automated Vehicles in the Mixed Traffic: A Unity-SUMO Integrated Platform

Xishun Liao, Xuanpeng Zhao+5 more|arXiv (Cornell University)|Jan 27, 2021

Transportation and Mobility Innovations参考文献 18被引用 17

一句话总结

本文提出一种基于博弈论的混合交通环境中联网自动驾驶车辆（CAVs）坡道汇入策略，通过优化汇入序列与车辆控制，提升安全性和效率。利用新型Unity-SUMO仿真平台，该平台将游戏引擎与交通仿真器结合，使平均车速最高提升110%，燃油消耗最高降低77%，适用于不同渗透率和拥堵水平的场景。

ABSTRACT

Ramp merging is considered as one of the major causes of traffic congestion and accidents because of its chaotic nature. With the development of connected and automated vehicle (CAV) technology, cooperative ramp merging has become one of the popular solutions to this problem. In a mixed traffic situation, CAVs will not only interact with each other, but also handle complicated situations with human-driven vehicles involved. In this paper, a game theory-based ramp merging strategy has been developed for the optimal merging coordination of CAVs in the mixed traffic, which determines dynamic merging sequence and corresponding longitudinal/lateral control. This strategy improves the safety and efficiency of the merging process by ensuring a safe inter-vehicle distance among the involved vehicles and harmonizing the speed of CAVs in the traffic stream. To verify the proposed strategy, mixed traffic simulations under different penetration rates and different congestion levels have been carried out on an innovative Unity-SUMO integrated platform, which connects a game engine-based driving simulator with a traffic simulator. This platform allows the human driver to participate in the simulation, and also equip CAVs with more realistic sensing systems. In the traffic flow level simulation test, Unity takes over the sensing and control of all CAVs in the simulation, while SUMO handles the behavior of all legacy vehicles. The results show that the average speed of traffic flow can be increased up to 110%, and the fuel consumption can be reduced up to 77%, respectively.

研究动机与目标

• 解决混合交通环境中因汇入混乱导致的交通拥堵与安全风险。
• 为联网自动驾驶车辆（CAVs）开发一种与人类驾驶车辆协同的协作式汇入策略。
• 基于博弈论原理，优化动态汇入序列及纵向/横向控制。
• 在不同CAV渗透率和交通拥堵水平下评估该策略的性能表现。
• 通过新型Unity-SUMO集成仿真平台验证该方法，实现实时人机交互与传感器建模。

提出的方法

• 构建非合作博弈论框架，基于车辆间距与速度协调性，确定CAVs之间的最优汇入序列。
• 根据车辆状态（包括位置、速度和汇入时间）动态计算汇入顺序。
• 协调纵向与横向控制，确保安全的车距与平滑的汇入轨迹。
• Unity-SUMO平台将游戏引擎（Unity）用于CAV感知与控制，与微观交通仿真器（SUMO）结合，用于模拟传统车辆行为。
• 通过Unity将人类驾驶员集成到仿真中，实现在混合交通场景下与CAV的真实交互。
• 平台支持真实的CAV感知模型，包括传感器限制与环境动态特性。

实验结果

研究问题

• RQ1 博弈论如何应用于混合交通中人类驾驶车辆与CAVs之间的最优汇入序列协调？
• RQ2 CAV渗透率的变化对汇入效率与交通流性能有何影响？
• RQ3 在不同拥堵水平下，该策略对平均车速与燃油消耗的影响如何？
• RQ4 Unity-SUMO平台在多大程度上能真实模拟CAV坡道汇入中的人机交互？
• RQ5 将基于游戏引擎的控制与交通仿真相结合，能否提升CAV性能评估的保真度与有效性？

主要发现

• 与无协调的基线场景相比，所提策略使平均交通流速度最高提升110%。
• 在最优汇入协调下，燃油消耗最高降低77%，展现出显著的环境与运营效益。
• 该策略维持了安全的车距并提升了汇入平顺性，降低了碰撞风险。
• 性能增益在不同CAV渗透率与拥堵水平下均保持稳定，表明其鲁棒性。
• Unity-SUMO平台成功实现了对人类驾驶员与CAV感知的逼真仿真，验证了该方法的实际可行性。