江翠宁,刘桥缘,李 慧

基于车载GPS数据再现公交车运行轨迹，构建基于规则判断和机器学习的双向融合算法，旨在准确地识别不同道路场景下的危险驾驶行为。首先以运动学参数百分位值为基准，采用贝叶斯优化算法对危险驾驶行为判别阈值进行重新标定，实现对公交危险驾驶行为的准确识别。同时，特别强调区分道路场景、公交运行线路类型要素，以确保识别结果更加具有可行性。实例验证显示，该方法具有机器学习进行危险驾驶行为识别精度高的特点，同时又具有基于规则识别算法运行成本低的优势，且避免了过于依赖主观经验阈值识别带来的不足。

公交车；车辆轨迹；道路场景；危险驾驶行为

[1] World Health organization.Global status report on road safety 2023[R].Geneva:World Health organization,2023. [2] 王涛,黎文皓,谢思红,等.电动自行车风险驾驶行为因子分析及相关因素研究[J].重庆交通大学学报(自然科学版),2019,38(11):118-126. [3] 朱彤,秦丹,董傲然,等.公交驾驶员违规类型同交通事故间的关联分析[J].交通运输系统工程与信息,2022,22(02):322-329. [4] 任慧君,许涛,李响.利用车载 GPS 轨迹数据实现公交车驾驶安全性分析[J].武汉大学学报(信息科学版),2014,39(06):739-744. [5] 纪少波,张珂,李伦,等.基于纯电动汽车高频数据的驾驶风格分类方法[J].同济大学学报(自然科学版),2022,50(02):273-282. [6] Jia S,Hui F,Li S,et al.Long short-term memory and convolutional neural network for abnormal driving behaviour recognition[J].IET Intelligent Transport Systems,2020,14(5):306-312. [7] Yu Z,Yingying H,Likai Z.Recognition method of abnormal driving behavior using the bidirectional gated recurrent unit and convolutional neural network[J].Physica A:Statistical Mechanics and its Applications,2023,609. [8] Damerow F,Li Y,Puphal T,et al.Intersection Warning System for Occlusion Risks Using Relational Local Dynamic Maps[J].IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE,2018,10(4):47-59. [9] Samerei S A,Aghabayk K,Mohammadi A,et al.Data mining approach to model bus crash severity in Australia[J].JOURNAL OF SAFETY RESEARCH,2021,76:73-82. [10] Liu R,Yu H,Ren Y,et al.The Analysis of Classification and Spatiotemporal Distribution Characteristics of Ride-Hailing Driver’s Driving Style:A Case Study in China[J].International journal of environmental research and public health,2022,19(15):9734. [11] Dias C,Iryo-Asano M,Abdullah M,et al.Modeling Trajectories and Trajectory Variation of Turning Vehicles at Signalized Intersections[J].IEEE ACCESS,2020,8:109821-109834. [12] 程建梅,陈强,章超,等.城市道路不同驾驶环境下汽车驾驶员注意力分配定量研究[J].科学技术与工程,2018,18(25):286-295.

点击下载PDF