[Paper Review] 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 Innovations18 references17 citations

TL;DR

This paper proposes a game theory-based ramp merging strategy for connected and automated vehicles (CAVs) in mixed traffic, optimizing merging sequences and vehicle controls to enhance safety and efficiency. Using a novel Unity-SUMO simulation platform that integrates a game engine with a traffic simulator, the strategy increases average traffic speed by up to 110% and reduces fuel consumption by up to 77% under varying penetration rates and congestion levels.

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.

Motivation & Objective

• To address traffic congestion and safety risks caused by chaotic ramp merging in mixed traffic environments.
• To develop a cooperative merging strategy for connected and automated vehicles (CAVs) that coordinates with human-driven vehicles.
• To optimize dynamic merging sequences and longitudinal/lateral controls using game theory principles.
• To evaluate the strategy’s performance under diverse CAV penetration rates and traffic congestion levels.
• To validate the approach using a novel Unity-SUMO integrated simulation platform enabling realistic human-in-the-loop and sensor modeling.

Proposed method

• A non-cooperative game theory framework is formulated to determine optimal merging sequences among CAVs, considering inter-vehicle distances and speed harmonization.
• The strategy computes dynamic merging order based on vehicle states, including position, speed, and time-to-merge.
• Longitudinal and lateral controls are coordinated to ensure safe inter-vehicle spacing and smooth merging trajectories.
• The Unity-SUMO platform couples a game engine (Unity) for CAV sensing and control with a microscopic traffic simulator (SUMO) for legacy vehicle behavior.
• Human drivers are integrated into the simulation via Unity, enabling realistic interaction with CAVs in mixed traffic scenarios.
• The platform supports realistic CAV perception models, including sensor limitations and environmental dynamics.

Experimental results

Research questions

• RQ1 How can game theory be applied to coordinate optimal merging sequences among CAVs in mixed traffic with human-driven vehicles?
• RQ2 What impact does varying CAV penetration rate have on merging efficiency and traffic flow performance?
• RQ3 How does the proposed strategy affect average traffic speed and fuel consumption under different congestion levels?
• RQ4 To what extent can the Unity-SUMO platform realistically simulate human-in-the-loop interactions in CAV ramp merging?
• RQ5 Can the integration of game engine-based control with traffic simulation improve the fidelity and validity of CAV performance evaluation?

Key findings

• The proposed strategy increased average traffic flow speed by up to 110% compared to baseline scenarios without coordination.
• Fuel consumption was reduced by up to 77% under optimal merging coordination, demonstrating significant environmental and operational benefits.
• The strategy maintained safe inter-vehicle distances and improved merging smoothness, reducing collision risks.
• Performance gains were consistent across different CAV penetration rates and congestion levels, indicating robustness.
• The Unity-SUMO platform successfully enabled realistic simulation of human drivers and CAV sensing, validating the approach’s practical feasibility.