基于无监督聚类分析的激进换道行为识别方法

doi:10.16097/j.cnki.1009-6744.2024.02.017

摘要/Abstract

摘要： 为有效指导驾驶人采取更安全的换道行为，本文提出基于改进的自组织映射神经网络(SOM-Kmeans)聚类分析的激进换道行为识别方法。通过模拟驾驶设备和眼动仪获取驾驶数据和眼动状态，运用变点检测算法结合方向盘转角和横向注视位置从多模态数据集中提取换道行为事件数据，进而提取驾驶人换道行为关键特征参数，运用SOM-Kmeans聚类分析识别激进换道行为。将SOM-Kmeans聚类方法分别与基于密度的聚类算法(DBSCAN)及模糊C均值聚类算法(FCM)比较，分析激进换道行为的识别效果。研究结果表明：SOM-Kmeans能够将激进换道行为划分为紧急换道和挤车换道两种类型，并建立相应的行为指标和阈值，当换道过程中加速度波动大于8.22 m·s-3且方向盘转角大于0.83(°)·s-1，识别此次换道为激进换道行为；在激进换道行为的基础上，当换道间隙小于7.5m且换道持续时间大于10.3s时，识别此次换道为挤车换道，否则，为紧急换道行为。挤车换道行为多出现在拥堵较严重的强制换道中，紧急换道行为多出现在交通流环境较好的自由换道中。本文提出的识别方法的准确率为92.5%，与传统聚类分析相比，本文提出的激进换道行为识别方法能够更加细致地识别激进换道行为的种类，研究结果可作为评估驾驶人是否存在危险换道行为和衡量驾驶人换道习惯的参考标准，同时，该两次聚类结果可作为激进型换道行为的参考标准。

关键词: 智能交通, 激进换道行为识别, SOM-Kmeans聚类算法, 城市道路, 模拟驾驶

Abstract: To effectively guide drivers to adopt safer lane-changing behaviours, this paper proposes a method to identify aggressive lane-changing behaviour based on a modified Self-Organising Mapping Neural Network (SOM-Kmeans) cluster analysis. Driving data and eye movement status are obtained by driving simulation equipment and eye movement equipment. Then, a change-point detection algorithm is applied to extract lane-changing behaviour event data from the multimodal dataset by combining the steering wheel angle and lateral gaze position. Afterwards, SOM Kmeans cluster analysis is used to extract key feature parameters of driver lane changing behaviour and identify aggressive lane changing behaviour. The effectiveness of the SOM-Kmeans clustering method is compared with the density-based clustering algorithm (DBSCAN) and the fuzzy C-mean clustering algorithm (FCM), respectively, for the identification of aggressive lane changing behaviour. The results show that SOM-Kmeans is able to classify aggressive lane-changing behaviour into two types: emergency lane-changing and squeezing lane-changing. The proposed method can establish the corresponding behavioural indicators and thresholds, and identify the lane changing behaviour as aggressive when the acceleration fluctuation in the process of lane changing is greater than 8.22 m·s-3 and the steering wheel angle is greater than 0.83 (°)·s-1. Based on aggressive lane changing behaviour, when the lane changing gap is less than 7.5 m and the duration of the lane changing is greater than 10.3 s, the lane changing is identified as crowded lane changing, otherwise it is emergency lane changing behaviour. Crowded lane changing behaviours are mostly found in mandatory lane changing with heavy congestions, and emergency lane changing behaviours are mostly found in free lane changing with low-to-moderate traffic densities. The accuracy of the proposed method identification is 92.5% when compared with the traditional cluster analysis. The proposed method can identify the types of aggressive lane changing behaviour in a more detailed way, and the results of the study can be used as a way to assess whether there is a deviation from the normal lane changing behaviours of a driver and to measure the driver's lane changing habits. The results of the two-layer clustering can also be used as a referential criteria of the radical type of lane changing behaviours.

Key words: intelligent transportation, aggressive lane-changing behaviour identification, SOM-Kmeans clustering algorithm, urban road, driving simulation

中图分类号:

U491

王婉琦, 程国柱, 徐亮. 基于无监督聚类分析的激进换道行为识别方法[J]. 交通运输系统工程与信息, 2024, 24(2): 166-178.

WANGWanqi, CHENG Guozhu, XU Liang. Identification of Aggressive Lane-changing Behaviour Based on Unsupervised Cluster Analysis[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(2): 166-178.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2024.02.017

http://www.tseit.org.cn/CN/Y2024/V24/I2/166

参考文献

[1] MA Y, YIN B, JIANG X, et al. Psychological and environmental factors affecting driver's frequent lane changing driving behaviours: A national sample of drivers in China[J]. IET Intelligent Transport Systems, 2020, 14(8): 825-833.

[2] WANG W, XI J. Arapid pattern-recognition method for driving styles using clustering-based support vector machines[C]. 2016 American Control Conference (ACC), 2016.

[3] LEE J, JANG K. A framework for evaluating aggressive driving behaviors based on in-vehicle driving records[J]. Transportation Research Part F: Traffic Psychology & Behaviour, 2019, 65: 610-619.

[4] AHMED K I, BEN-AKIVA M, KOUTSOPOULOS H N, et al. Models of freeway lane changing and gap acceptance behavior[C]. Internaional Symposium on Transportation and Traffic Theory, 1996.

[5]赵建东,赵志敏,屈云超,等.轨迹数据驱动的车辆换道意图识别研究[J].交通运输系统工程与信息,2022, 22(4): 63-71. [ZHAO J D, ZHAO Z M, QU Y C , et al. Vehicle lane change intention recognition driven by trajectory data[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(4): 63-71.]

[6] MORRIS B, DOSHI A, TRIVEDI M. Lane change intent prediction for driver assistance: On-road design and evaluation[C]. 2011 IEEE Intelligent Vehicles Symposium (IV), 2011.

[7]苏丽娜,李凡,潘秀,等.基于雷达数据的车辆换道行为识别研究[J]. 北京交通大学学报,2022,46(4): 60 67. [SU L N, LI F, PAN X, et al. A study on vehicle lane changing behavior recognition based on radar data [J]. Journal of Beijing Jiaotong University, 2022, 46(4): 60 67.]

[8]GAO J, YI J, MURPHEY Y L. Joint learning of video images and physiological signals for lane-changing behavior prediction[J]. Transportmetrica A: Transport Science, 2022, 18(3): 1234-1253.

[9] PENG X, LIU R, MURPHEY Y L, et al. Driving maneuver detection via sequence learning from vehicle signals and video images[C]. 2018 24th International Conference on Pattern Recognition (ICPR), 2018.

[10] OHN-BAR E, TAWARI A, MARTIN S, et al. Predicting driver maneuvers by learning holistic features[C]. 2014 IEEE Intelligent Vehicles Symposium Proceedings, 2014.

[11] ALI Y, BLIEMER M, HAQUE S M M, et al. Examining braking behaviour during failed lane-changing attempts in a simulated connected environment with driving AIDS [J]. Transportation Research Part C: Emerging Technologies, 2022, 136: 103531.

[12] XUE Q, LI X, WANG Y. Uncertainty analysis of rear-end collision risk based on car-following driving simulation experiments[J]. Discrete Dynamics in Nature and Society, 2018, 2018: 1-13.

[13] 石京, 柳美玉.基于驾驶模拟实验的驾驶风格对高速公路换道行为的影响[J].东南大学学报(自然科学版), 2017, 47(5): 1037-1041. [SHI J, LIU M Y. Influence of driving style on highway lane-changing behavior based on driving simulation experiments[J]. Journal of Southeast University (Natural Science Edition), 2017, 47 (5): 1037-1041.]

[14] LUNG-YUT-FONG A, LéVY-LEDUC C, CAPPé O. Distributed detection/localization of change-points in high-dimensional network traffic data[J]. Statistics and Computing, 2009, 22: 485-496.

[15] IWATA T, NAKAMURA K, TOKUSASHI Y, et al. An FPGA-based change-point detection for 10 GBPS packet stream[J]. IEICE Transactions on Information and Systems, 2019, E102.D(12): 2366-2376.

[16] HIDAS P. Modelling vehicle interactions in microscopic simulation of merging and weaving[J]. Transportation Research Part C: Emerging Technologies, 2005, 13(1): 37-62.

[17] SU L, LI F, PAN X, et al. Detection of vehicle lane changing behavior based on radar data[J]. Journal of Beijing Jiaotong University, 2022, 46(4): 60-67.

[18] 徐进, 孙子秋,王思棋,等.高密度互通立交出口匝道驾驶人视觉搜索行为特征[J].东南大学学报(自然科学版), 2022, 52(6): 1189-1198. [XU J, SUN Z Q, WANG S Q, et al. Characteristics of driver's visual search behavior in exit ramp of high-density interchanges[J]. Journal of Southeast University (Natural Science Edition), 2022, 52(6): 1189-1198.]

[19] 朱秋晨, 吴付威,白骅,等.城市快速路中央分隔带线性空间布局形式的视觉刺激对驾驶行为的影响[J].中国公路学报,2022, 35(11): 239-251. [ZHU Q C, WU F W, BAI H, et al. Influence of visual stimuli on driving behavior in the form of linear spatial layout of urban expressway median strip[J]. China Journal of Highway and Transport, 2022, 35(11): 239-251.]

[20] TRUONG C, OUDRE L, VAYATIS N. Selective review of offline change point detection methods[J]. Signal Processing, 2020, 167: 107299.

[21] KILLICK R, FEARNHEAD P, ECKLEY I A. Optimal detection of changepoints with a linear computational cost[J]. Journal of the American Statistical Association, 2012, 107(500): 1590-1598.

[22] AOKI T, AOYAGI T. Self-organizing maps with asymmetric neighborhood function[J]. Neural Computation, 2007, 19(9): 2515-2135.

[23] WANG W, CHENG G. The characteristics of driver lane changing behavior in congested road environments[J/ OL]. Transportation Safety and Environment, (2023-11 21)[2024-01-11]. https://doi.org/10.1093/tse/tdad039.