TY - JOUR A2 - Wang, Kun AU - Chen, Hengrui AU - Chen, Hong AU - Liu, Zhizhen AU - Sun, Xiaoke AU - Zhou，自动驾驶汽车(AV)技术的研究和开发在全球范围内不断取得进展。然而，一些研究对涉及自动驾驶汽车的撞车事故的成因进行了深入的探索。本研究旨在预测涉及自动驾驶汽车的碰撞严重程度，并分析不同因素对碰撞严重程度的影响。碰撞数据来自2019年提交给加州机动车管理局(California Department of Motor Vehicles)的与自动驾驶汽车有关的碰撞报告，其中包括75起未受伤事故和18起受伤事故。兴趣点(point -of-interest, POI)数据来自谷歌地图应用编程接口(Map Application Programming Interface, API)。采用描述性统计分析方法，从碰撞类型、碰撞严重程度、碰撞前车辆运动和车辆损伤程度等方面分析了涉及自动驾驶汽车的碰撞特征。为了比较不同分类器的分类性能，我们使用了两种不同的分类模型:极端梯度助推(eXtreme Gradient Boosting, XGBoost)和分类回归树(classification and Regression Tree, CART)。结果表明，XGBoost模型在识别涉及自动驾驶汽车的受伤事故方面具有较好的性能。与原XGBoost模型相比，结合POI数据的XGBoost模型的查全率和G-mean分别提高了100%和11.1%。 The main features that contribute to the severity of crashes include weather, degree of vehicle damage, accident location, and collision type. The results indicate that crash severity significantly increases if the AVs collided at an intersection under extreme weather conditions (e.g., fog and snow). Moreover, an accident resulting in injuries also had a higher probability of occurring in areas where land-use patterns are highly diverse. The knowledge gained from this research could ultimately contribute to assessing and improving the safety performance of the current AVs. SN - 0197-6729 UR - https://doi.org/10.1155/2020/8881545 DO - 10.1155/2020/8881545 JF - Journal of Advanced Transportation PB - Hindawi KW - ER -