The advent of automated vehicles (AVs) will provide opportunities for safer, smoother, and smarter road transportation. During the transition from the current human-driven vehicle (HV) to a fully AV traffic environment, there will be a mixed traffic flow including both HVs and AVs. The impact of introducing AVs into existing traffic, however, has not yet been fully understood. In this paper, we advance this understanding by conducting mixed traffic safety evaluation from the perspective of car-following behavior using real-world AV operational data of mixed traffic. To understand how the AVs impact other vehicles on the road, we analyzed the operational behaviors of HV-following-HV, AV-following-HV, and HV-following-AV. A selected car-following model is calibrated, and results show that there are significant differences between the HV-following-HV and the other two groups, indicating safe AV behavior and changes in HV behavior (i.e. less aggressive, safer) after the introduction of AVs into the traffic. Additionally, to understand AV behavioral safety, we investigate behavior predictions (one of the most critical inputs for AVs to make car-following decisions) of AVs and their surrounding vehicles using a mature baseline model and a new Conditional Variational Autoencoder (CVAE) framework. The result shows potential risks of inaccurate predictions of the baseline model and the necessity to consider additional factors, such as vehicle interactions and driver behavior, into the prediction for risk mitigation. Arterial vehicle trajectory data from the Lyft Level 5 Dataset is applied to test the proposed methodological framework to understand the car-following safety risks of HVs and AVs in the mixed traffic stream.

自动驾驶汽车 (AV) 的出现将为更安全、更顺畅和更智能的道路交通提供机会。在从当前的人类驾驶车辆 (HV) 过渡到完全 AV 交通环境的过程中，将出现包括 HV 和 AV 在内的混合交通流。然而，将自动驾驶汽车引入现有交通的影响尚未完全了解。在本文中，我们通过使用混合交通的真实 AV 运营数据从跟车行为的角度进行混合交通安全评估来推进这种理解。为了了解自动驾驶汽车如何影响道路上的其他车辆，我们分析了 HV-following-HV、AV-following-HV 和 HV-following-AV 的操作行为。校准选定的跟驰模型，结果表明，在 HV-following-HV 和其他两组之间存在显着差异，表明在将 AV 引入交通后，安全的 AV 行为和 HV 行为的变化（即不那么激进，更安全）。此外，为了了解自动驾驶汽车的行为安全性，我们使用成熟的基线模型和新的条件变分自动编码器 (CVAE) 框架研究自动驾驶汽车及其周围车辆的行为预测（自动驾驶汽车做出跟车决策的最关键输入之一）。结果显示了基线模型预测不准确的潜在风险，以及在风险缓解预测中考虑其他因素（例如车辆交互和驾驶员行为）的必要性。