复杂交通场景智能驾驶典型工况风险特征分析

汽车电器 ›› 2026, Vol. 1 ›› Issue (2) : 35-37.

智能网联

钟陈志鹏

作者信息 +

Analysis of Risk Characteristics of Typical Operating Conditions for Intelligent Driving in Complex Traffic Scenarios

Zhong Chenzhipeng

Author information +

文章历史 +

摘要

本文基于 NHTSA 2021—2025 自动驾驶车辆事故报告公开数据 [1]，对复杂交通场景中智能驾驶的典型工况进行风险特征分析。研究选取十字路口、高密度场景、混驾场景三类典型工况，提取各场景下的风险特征并深入剖析事故成因。结果表明，不同工况具有独特的风险模式：十字路口工况的关键风险因素为闯红灯、违规转弯等不规范行为；高密度场景变道工况主要风险因素为车距过近、频繁变道；混驾场景变道工况的核心风险因素为有人驾驶车辆与无人驾驶车辆的行为差异。本研究为提升智能驾驶在复杂交通场景下的安全性提供数据支持与决策依据，有助于针对性优化智能驾驶算法及完善交通管理策略。

Abstract

This study is grounded in the publicly accessible data from the NHTSA Autonomous Vehicle Accident Reports spanning from 2021—2025[1]. It undertakes a risk characteristic analysis of typical operating conditions of intelligent driving within complex traffic scenarios. Specifically, three typical operating conditions are investigated: intersections, high density scenarios, and mixed-driving scenarios. Risk characteristics are extracted, and the causes of accidents are analyzed in depth. The research reveals that distinct operating conditions exhibit unique risk patterns. For the intersection operating condition, the critical risk factors include non-compliant behaviors such as running red lights and making illegal turns. In the high-density traffic lane changing operating condition, the primary risk factors are insufficient vehicle spacing and frequent lane changing maneuvers. In the lane changing operating condition of the mixed driving scenario, the risk factors are attributed to the behavioral disparities between human driven and autonomous vehicles.This research offers data support and a decision-making foundation for enhancing the safety of intelligent driving in complex traffic scenarios. It is conducive to making targeted improvements to intelligent driving algorithms and traffic management strategies.

导出引用

钟陈志鹏. 复杂交通场景智能驾驶典型工况风险特征分析[J]. 汽车电器. 2026, 1(2): 35-37

Zhong Chenzhipeng.

Analysis of Risk Characteristics of Typical Operating Conditions for Intelligent Driving in Complex Traffic Scenarios

[J]. AUTO ELECTRIC PARTS. 2026, 1(2): 35-37

中图分类号： U463.6

参考文献

[1] Guo R, Chen Y, Zhang Y, et al. Analysis of factors contributing to severity of AV crashes at intersections: Insights from the Autonomous Vehicle Operation Incident Dataset Across The Globe (AVOID) [J]. Traffic Injury Prevention, 2025：1-8.

[2] Zheng O, Abdel-Aty M, Wang Z, et al. AVOID: Autonomous Vehicle Operation Incident Dataset Across the Globe [Z]. arXiv, 2023.

[3] Ding S, Abdel-Aty M, Wang D, et al. Exploratory analysis of the crash severity between vehicular automation (SAE L2-5) with multi-source data [Z]. 2023.

[4] 赵光明，周文辉，王艺帆。中美自动驾驶汽车死亡事故对车辆安全管理的启示研究 [J]. 道路交通管理，2016（11）：30-32.

[5] 刘倩，王雪松。交叉口自动驾驶车辆事故前场景生成与致因分析 [J]. 中国公路学报，2024，37（4）：297-309.

[6] 阎莹，王玉莹，周旋，等。基于混合模型的自动驾驶车辆事故严重程度影响因素分析 [J]. 交通运输工程学报，2025，25（1）：184-196.

[7] 谭正平，车瑶栎，肖凌云，等。面向自动驾驶的典型汽车与行人事故冲突场景研究 [J]. 安全与环境学报，2021，21（4）：1573-1582.

[8] 袁泉，高岩，裘晨璐。基于人 - 机 - 环境因素的未来交通事故风险研究 [J]. 系统仿真学报，2019，31（3）：566-574.

[9] 陈吉清，舒孝雄，兰凤崇，等。典型危险事故特征的自动驾驶测试场景构建 [J]. 华南理工大学学报（自然科学版），2021，49（5）：1-8.