Autonomous Vehicle’s Impact on Traffic: Empirical Evidence From Waymo Open Dataset and Implications From Modelling

Autonomous Vehicle’s Impact on Traffic: Empirical Evidence From Waymo Open Dataset and Implications From Modelling
复制标题

DOI:
10.1109/tits.2023.3258145
复制
发表时间:
2023-06
影响因子:
8.5
通讯作者:
Xiangwang Hu;Zuduo Zheng;Danjue Chen;Jian Sun
Xiangwang Hu;Zuduo Zheng;Danjue Chen;Jian Sun
中科院分区:
工程技术1区
文献类型:
--
作者:
Xiangwang Hu;Zuduo Zheng;Danjue Chen;Jian Sun

文献摘要

被引文献

相似文献

以往对自动驾驶车辆(AV)的经验行为分析主要集中在安装了自适应巡航控制(ACC)系统的车辆上,原因是缺乏高级别的自动驾驶车辆数据集。最近发布的SAE Level-4 AV数据集,如Waymo Open数据集,为评估它们对交通流量的行为影响提供了很好的机会。在本研究中,我们旨在刻画Waymo自动驾驶车辆的经验跟车(CF)行为,并将其特征与人类驾驶的车辆(HV)进行比较,并使用IDM跟驰模型来捕捉这种行为差异。我们的主要发现包括:(A)基于我们使用替代安全措施进行的分析,AV比HV安全得多,因为AV的时间间隔和堵塞间隔明显大于HV;(B)AV对各种刺激的响应时间也显著大于HV;(C)尽管Waymo Open数据集中的轨迹长度较短,但我们已确认这些轨迹适合于校准IDM的一些参数;并且IDM的校准结果与我们的经验分析一致。此外,建模结果表明,AV的串不稳定行为的比例小于HV;以及(D)对于HV,除了跟随AV时较小的堵塞间距外,跟随AV和跟随HV的串不稳定行为通常没有显著差异。总体而言,我们得出的结论是,目前的AV行为保守,以牺牲交通效率为代价来确保其安全性。
Previous empirical behavior analysis on Autonomous Vehicles (AV) mainly focused on vehicles with Adaptive Cruise Control (ACC) system due to the lack of high-level AV dataset. Recently released SAE Level-4 AV datasets such as the Waymo Open Dataset provide great opportunities to evaluate their behavioral impact on traffic flow. In this study, we aim to characterize the empirical Car Following (CF) behaviors of the Waymo autonomous vehicle and compare its feature with human-driven Vehicles (HV), and capture such behavioral differences using the IDM CF model. Our main findings include: (a) AV is much safer than HV, based on our analysis using surrogate safety measures, as time headways and jam spacings of the AV are significantly larger than HV; (b) the response time of AV is also significantly larger than that of HV in response to various types of stimuli; (c) despite the short length of trajectories in the Waymo Open Dataset, we have confirmed that these trajectories are suitable for calibrating some of the IDM parameters; and the calibration results of IDM are consistent with our empirical analysis. Moreover, the modelling results, reveal that the proportion of string unstable behavior of AV is less than that of HV; and (d) for HV, there is generally no significant difference between following AV and following HV except a smaller jam spacing when following AV. Overall, we conclude that currently AV behaves in a conservative way to ensure its safety at the cost of traffic efficiency.