基于冰雪路面危险驾驶行为谱的行车风险识别方法

doi:10.16097/j.cnki.1009-6744.2024.04.013

摘要/Abstract

摘要： 为描述驾驶人在冰雪路面行车时危险驾驶行为的具体表现形式，并量化其整体行车风险，通过模拟驾驶试验获取驾驶人操作类数据和车辆运动类数据，构建包含猛打方向、急变速、超速行驶、横向摇摆和跨道行驶这5种行为的危险驾驶行为谱。根据具体试验条件和四分位差法，分别确定不同路面附着系数下危险驾驶行为的阈值，并通过加权平均的方式计算危险驾驶行为谱特征值。以特征值作为行车风险评价指标，利用K-means聚类算法，将行车风险状态划分为4类，将随机森林模型、元启发式优化算法与支持向量机(SupportVectorMachine,SVM)结合，建立冰雪路面行车风险识别模型。结果表明：超速行驶对冰雪路面行车安全影响最大，其权重为0.285；危险驾驶行为谱特征值主要分布于区间[0.00,0.20]内，最大值出现在路面附着系数为0.2条件下；在路面附着系数为0.2和0.4条件下，严重行车风险明显增加，其占比分别为正常路面的4.85倍和2.49倍；鱼鹰优化算法(OspreyOptimizationAlgorithm, OOA)与SVM结合得到的行车风险识别模型的识别准确率为93.96%，优于浣熊优化算法(CoatiOptimizationAlgorithm, COA)和灰狼优化算法(Gray Wolf Optimization Algorithm, GWOA)。研究结果有助于了解驾驶人在冰雪路面和正常路面行车时的差异，为提升驾驶人的行车安全水平提供依据。

关键词: 交通工程, 风险识别, 危险驾驶行为谱, 冰雪路面, OOA-SVM, 模拟驾驶

Abstract: To describe the specific forms of dangerous driving behavior and quantify the overall driving risk of drivers on ice and snow pavement, driving operation data and vehicle motion data were collected through simulated driving experiments. A dangerous driving behavior spectrum was constructed, which included five behaviors: sharp changes in direction, sharp changes in speed, speeding, lateral swaying, and occupying adjoining lanes. The threshold values of dangerous driving behavior under different pavement adhesion coefficients were determined based on specific experimental conditions and the quartile difference method. Then, the characteristic value of the dangerous driving behavior spectrum was calculated by weighted averaging. The characteristic value of the dangerous driving behavior spectrum was used as the driving risk evaluation index. The K-means clustering algorithm was used to divide the driving risk state into four categories, and the Random Forest model, metaheuristic optimization algorithm, and Support Vector Machine (SVM) were combined to establish a model for identifying driving risks on ice and snow pavement. The results show that speeding has the greatest impact on driving safety on ice and snow pavement with a weight of 0.285; the characteristic values of the dangerous driving behavior spectrum are mainly distributed in the interval [0.00, 0.20], and the maximum value appears under the pavement adhesion coefficient of 0.2; under the conditions of pavement adhesion coefficients of 0.2 and 0.4, the severe driving risk increases significantly, accounting for 4.85 times and 2.49 times of normal pavement, respectively. The recognition accuracy of the driving risk recognition model obtained by combining the Osprey Optimization Algorithm (OOA) with SVM is 93.96%, outperforming the Coati Optimization Algorithm (COA) and the Grey Wolf Optimizer Algorithm (GWOA). The research results provide insight into the understand the differences between driving on ice and snow pavement and normal pavement, and provide a basis for enhancing driving safety.

Key words: traffic engineering, risk identification, dangerous driving behavior spectrum, ice and snow pavement, OOA SVM, driving simulation experiment

中图分类号:

U491

程国柱, 李天仪, 汪国鹏. 基于冰雪路面危险驾驶行为谱的行车风险识别方法[J]. 交通运输系统工程与信息, 2024, 24(4): 127-138.

CHENGGuozhu, LI Tianyi, WANG Guopeng. Driving Risk Identification Method Based on Dangerous Driving Behavior Spectrum on Ice and Snow Pavement[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(4): 127-138.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2024.04.013

http://www.tseit.org.cn/CN/Y2024/V24/I4/127

参考文献

[1]王可,陆键,蒋愚明.基于车辆行驶轨迹的道路不良驾驶行为谱构建与特征值计算方法[J].交通运输工程学报, 2020, 20(6): 236-249. [WANG K, LU J, JIANG Y M. Abnormal road driving behavior spectrum establishment and characteristic value calculation method based on vehicle driving trajectory[J]. Journal of Traffic and Transportation Engineering, 2020, 20(6): 236-249.]

[2] 刘唐志,毕辉云,杨卓思,等.基于操纵量指标的合流区危险驾驶行为谱研究[J].交通运输系统工程与信息, 2023, 23(2): 242-251. [LIU T Z, BI H Y, YANG Z S, et al. Dangerous driving behavior spectrum in merging are abased on maneuver indicators[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(2): 242-251.]

[3]陆键,王可,蒋愚明.基于车辆行驶轨迹的道路不良驾驶行为实时辨识方法[J].交通运输工程学报,2020,20 (6): 227-235. [LU J, WANG K, JIANG Y M. Real-time identification method of abnormal road driving behavior based on vehicle driving trajectory[J]. Journal of Traffic and Transportation Engineering, 2020, 20(6): 227-235.]

[4]汪敏,涂辉招,李浩.基于跟驰行为谱的跟驰风险状态预测[J].同济大学学报(自然科学版),2021,49(6): 843 852. [WANG M, TU H Z, LI H. Prediction of car following risk status based on car-following behavior spectrum[J]. Journal of Tongji University(Natural Science), 2021, 49(6): 843-852.]

[5]陈镜任,吴业福,吴冰.基于车辆行驶数据的驾驶人行为谱分析方法[J]. 计算机应用, 2018, 38(7): 1916 1922, 1928. [CHEN J R, WU Y F, WU B. Driver behavior spectrum analysis method based on vehicle driving data[J]. Journal of Computer Application, 2018, 38(7): 1916-1922, 1928.]

[6] JIANG K, WANG Y L, FENGZ X, et al. Research on intervention methods for children's street-crossing behavior: Application and expansion of the theory of behavior spectrums[J]. Accident Analysis and Prevention, 2021, 152: 105979.

[7]CHEN S W, FANG C Y. Driving behavior modeling system based on graph construction[J]. Transportation Research Part C: Emerging Technologies, 2013, 26: 314 330.

[8]WANG J, XU W, FU T, et al. Modeling aggressive driving behavior based on graph construction[J]. Transportation Research Part C: Emerging Technologies, 2022, 138: 103654.

[9] 程国柱,莫宣艳,毛程远.冰雪条件下城市道路交通安全评价方法研究[J].交通运输系统工程与信,2011,11 (1): 130-134. [CHENG G Z, MO X Y, MAO C Y. Urban road traffic safety evaluation method under the condition of ice and snow pavement[J]. Journal of Transportation Systems Engineering and Information Technology, 2011, 11(1): 130-134.]

[10] 柳本民, 廖岩枫,涂辉招,等.基于模拟实验的低等级公路车辆过弯风险预测模型[J].同济大学学报(自然科学版), 2021, 49(4): 499-506. [LIU B M, LIAO Y F, TU H Z, et al. Risk prediction model of vehicle driving in small radius curves based on simulation experiment[J]. Journal of Tongji University(Natural Science), 2021, 49 (4): 499-506.]

[11] CHEN Y, LI Y, KING M, et al. Identification methods of key contributing factors in crashes with high numbers of fatalities and injuries in China[J]. Traffic Injury Prevention, 2016, 17(8): 878-883.

[12] 刘佳雨, 冷军强,尚平,等.冰雪路面下高速公路事故及严重程度影响因素分析[J].哈尔滨工业大学学报, 2022, 54(3): 57-64. [LIU J Y, LENG J Q, SHANG P, et al. Analysis of traffic crashes and injury severity influence factors for ice-snow covered freeway roads[J]. Journal of Harbin Institute of Technology, 2022, 54(3): 57-64.]

[13] EBOIL L, MAZZULLA G, PUNGILLO G. Combining speed and acceleration to define car users' safe or unsafe driving behavior[J]. Transportation Research Part C: Emerging Technologies, 2016, 68:113-125.

[14] CHEN S, CHENG K, YANG J, et al. Driving behavior risk measurement and cluster analysis driven by vehicle trajectory data[J]. Applied Sciences, 2023, 13(9): 5675.

[15] 胡立伟, 张瑞杰,赵雪亭,等.道路环形交叉口机动冲突风险区识别模型研究[J].交通运输系统工程与信息,2024, 24(1): 168-178. [HU L W, ZHANG R J, ZHAO X T, et al. Roundabout motor vehicle conflict risk identification model[J]. Journal of Transportation Systems Engineeringand Information Technology, 2024, 24(1): 168-178.]

[16] 鲍琼, 屈琦凯,唐涵润,等.网联环境下基于多驾驶人风险评价的不良行为主动干预研究[J].交通运输系统工程与信息,2022, 22(4): 283-292. [BAO Q, QU Q K, TANG H R, et al. Multi-drivers risk evaluation based proactive intervention of drivers' risky behavior under connected transportation contexts[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(4): 283-292.]

[17] 王雪松, 徐晓妍.基于自然驾驶数据的危险事件识别方法[J]. 同济大学学报(自然科学版),2020,48(1): 51 59. [WANG X S, XU X Y. Detection of safety-critical events based on naturalistic driving data[J]. Journal of Tongji University(Natural Science), 2019, 48(1): 51-59.]

[18] 袁振洲,胡嫣然,杨洋.考虑多维动态特征交互的高速公路实时事故风险建模[J].交通运输系统工程与信息, 2022, 22(3): 215-223. [YUAN Z Z, HU Y R, YANG Y. Modeling towards freeway real-time traffic crash prediction considering multi-dimensional dynamic feature interactions[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(3): 215-223.]

[19] XIANG H, ZHU J, LIANG G, et al. Prediction of dangerous driving behavior based on vehicle motion state and passenger feeling using cloud model and Elman neural network[J]. Frontiers in Neurorobotics, 2021, 15: 1662-1678.