欢迎访问《汽车安全与节能学报》，
汽车安全与节能学报

汽车安全与节能学报 ›› 2025, Vol. 16 ›› Issue (1): 170-180.DOI: 10.3969/j.issn.1674-8484.2025.01.017

• 智能驾驶与智慧交通 • 上一篇    

基于CatBoost和SHAP的高级别自动驾驶车辆非预期停车冲突风险预测

刘擎超1(), 王瑞海1(), 蔡英凤1, 王海2, 陈龙1   

  1. 1.江苏大学 汽车工程研究院，镇江 212013，中国
    2.江苏大学 汽车与交通工程学院，镇江 212013，中国
  • 收稿日期:2024-09-10 修回日期:2024-12-31 出版日期:2025-02-28 发布日期:2025-03-04
  • 作者简介:刘擎超（1987—），男（汉），江苏，副教授。E-mail：lqc@ujs.edu.cn。
    王瑞海（2001—），男（汉），山西，硕士研究生。E-mail：962802988@qq.com。
  • 基金资助:
    国家重点研发计划资助项目(2023YFB2504403);国家自然科学基金资助项目(52372413);国家自然科学基金资助项目(52225212)

Unintended stopping conflict risk prediction for high-level autonomous vehicles based on CatBoost and SHAP

LIU Qingchao1(), WANG Ruihai1(), CAI Yingfeng1, WANG Hai2, CHEN Long1   

  1. 1. Automotive Engineering Research Institute, Jiangsu University, Zhenjiang 212013, China
    2. School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China
  • Received:2024-09-10 Revised:2024-12-31 Online:2025-02-28 Published:2025-03-04

RichHTML

5

PDF

55

摘要：

针对高级别自动驾驶车辆非预期停车引发的交通冲突及其环境影响问题，现有研究缺乏对风险特征交互的捕获和可解释性评估。本研究提出了一种基于CatBoost和SHAP的风险预测及解释模型，通过分析城市中心、住宅区和郊区交通网络的接管次数，构建了冲突风险预测模型。结果表明，接管次数在城市中心、住宅区和郊区分别为161次、227次和164次，最高单路段接管次数分别为11次、11次和16次；模型预测精度达93%以上。SHAP分析显示，前后车辆间相对速度和相对位置对冲突风险的影响显著。研究结果对提升自动驾驶车辆的可靠性和安全性具有重要意义。

关键词: 冲突风险, 交通排放, 高级别自动驾驶, CatBoost算法, SHAP解释模型

Abstract:

For the traffic conflicts and environmental impacts arising from unanticipated parking of high-level autonomous vehicles, existing research lacks the capture and interpretability assessment of risk characteristic interactions. This study proposed a risk prediction and interpretation model utilizing Categorical Boosting (CatBoost) and SHapley Additive exPlanations (SHAP), constructing a conflict risk prediction framework by analyzing takeover events in urban centers, residential areas, and suburban transportation networks. The results show that the number of takeovers reaches 161, 227, and 164 instances in urban centers, residential areas, and suburbs, respectively, with the maximum single-road-section takeover frequencies being 11, 11, and 16 times. The prediction accuracy of the model exceeds 93%. SHAP analysis reveales that the relative speed and position between preceding and following vehicles significantly influence collision risk. These findings hold important implications for enhancing the reliability and safety of autonomous vehicles.

Key words: conflict risk, traffic emission, high-level autonomous vehicles, Categorical Boosting (CatBoost), Shapley Additive exPlanations (SHAP)

中图分类号: