This paper proposes a high-fidelity simulation framework that can estimate the potential safety benefits of vehicle-to-infrastructure (V2I) pedestrian safety strategies. This simulator can support cooperative perception algorithms in the loop by simulating the environmental conditions, traffic conditions, and pedestrian characteristics at the same time. Besides, the benefit estimation model applied in our framework can systematically quantify both the risk conflict (non-crash condition) and the severity of the pedestrian's injuries (crash condition). An experiment was conducted in this paper that built a digital twin of a crowded urban intersection in China. The result shows that our framework is efficient for safety benefit estimation of V2I pedestrian safety strategies.

翻译：本文建议了一个高度忠诚的模拟框架,可以估计车辆到基础设施(V2I)行人安全战略的潜在安全效益。这个模拟器可以通过同时模拟环境条件、交通条件和行人特点,支持循环中的合作感知算法。此外,我们框架中采用的效益估计模型可以系统地量化风险冲突(非崩溃状况)和行人伤害的严重程度(崩溃状况)。本文中进行了一项实验,在中国建造了拥挤的城市交叉点的数码双胞胎。结果显示,我们的框架对于V2I行人安全战略的安全效益估计是有效的。