融合K-means与高斯混合模型的驾驶风格聚类研究

doi:10.16265/j.cnki.issn1003-3033.2019.12.007

中国安全科学学报 ›› 2019, Vol. 29 ›› Issue (12): 40-45.doi: 10.16265/j.cnki.issn1003-3033.2019.12.007

融合K-means与高斯混合模型的驾驶风格聚类研究

刘通¹, 付锐^1,2 教授, 张名芳³, 田顺¹

1 长安大学汽车学院,陕西西安 710064;
2 长安大学汽车运输安全保障技术交通行业重点实验室,陕西西安 710064;
3 北方工业大学电气与控制工程学院,北京 100144

收稿日期:2019-09-20 修回日期:2019-11-11 出版日期:2019-12-28 发布日期:2020-11-24
作者简介:刘通 (1989—),男,山西怀仁人,博士研究生,研究方向为人-车-路系统安全、驾驶行为分析、驾驶员类型划分。E-mail: liutong@chd.edu.cn。
基金资助:
国家自然科学基金资助(51775053);国家重点研发计划(2018YFB1600500);教育部长江学者与创新团队发展计划项目(IRT_17R95);汽车运输安全保障技术交通行业重点试验室开放课题 (300102229505)。

Study on driving style clustering based on K-means and Gaussian mixture model

LIU Tong¹, FU Rui^1,2, ZHANG Mingfang³, TIAN Shun¹

1 School of Automobile, Chang'an University, Xi'an Shaanxi 710064, China;
2 Key Laboratory of Automobile Transportation Safety Technology, Ministry of Transport, Chang'an University, Xi'an Shaanxi 710064, China;
3 School of Electrical and Control Engineering, North China University of Technology, Beijing 100144, China

Received:2019-09-20 Revised:2019-11-11 Online:2019-12-28 Published:2020-11-24

摘要/Abstract

摘要： 为研究驾驶员的跟车特性,探究驾驶员风格划分方法,采集50名驾驶员的实车试验数据,选取平均跟车时距和平均制动时距为二维向量,建立基于K-means聚类结果的高斯混合模型(GMM)并分析不同风格驾驶员的聚类结果。研究表明:样本数据聚为3类时的平均轮廓系数为0.45,将驾驶员划分为冒进型、平稳型、保守型3类时聚类效果较好;冒进型驾驶员倾向于选择较小的跟车时距和制动时距,保守型驾驶员的跟车及制动时距则普遍较大,模型聚类结果更加柔性,样本区分度更高。

关键词: 驾驶风格, K-means聚类, 高斯混合模型(GMM), 跟车特性, 制动特点

Abstract: In order to study drivers' car-following characteristics and explore an effective method to classify driving styles, 50 participants were recruited to carry out a real road driving test. A GMM with results of K-means clustering was established based on two-dimensional variables: average car-following time gap and average braking time gap. And then results of different types of drivers were analyzed. The research shows that clustering result is better with three categories (aggressive drivers, steady drivers, and conservative drivers) with an average contour value of 0.45. It is found that aggressive drivers tend to choose a smaller car-following time gap or braking time gap while conservative drivers usually take a larger value, and a much softer clustering result with a high separability between samples would be achieved.

Key words: driving style, K-means clustering, Gaussian mixture model (GMM), car-following characteristics, braking characteristics

中图分类号:

刘通, 付锐, 张名芳, 田顺. 融合K-means与高斯混合模型的驾驶风格聚类研究[J]. 中国安全科学学报, 2019, 29(12): 40-45.

LIU Tong, FU Rui, ZHANG Mingfang, TIAN Shun. Study on driving style clustering based on K-means and Gaussian mixture model[J]. China Safety Science Journal, 2019, 29(12): 40-45.

参考文献

[1] 吕能超,任泽远,段至诚,等. Near-crash事件中驾驶人行为特征分析[J]. 中国安全科学学报, 2017, 27(6): 19-24.
LYU Nengchao, REN Zeyuan, DUAN Zhicheng, et al. Analysis of driving behavior characteristics of drivers in Near-crash events [J]. China Safety Science Journal, 2017, 27(6):19-24.
[2] 楚文慧,吴超仲,张晖,等. 基于个性化行为模型的驾驶疲劳识别方法[J]. 中国安全科学学报, 2018, 28(6): 43-48.
CHU Wenhui, WU Chaozhong, ZHANG Hui, et al. Driver behavior model and its application in driver fatigue identification [J]. China Safety Science Journal, 2018, 28(6):43-48.
[3] MARTINEZ C M, HEUCKE M, WANG F Y, et al. Driving style recognition for intelligent vehicle control and advanced driver assistance: a survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 19(3): 666-676.
[4] ELANDER J, WEST R, FRENCH D. Behavioral correlates of individual differences in road-traffic crash risk: an examination of methods and findings[J]. Psychological Bulletin, 1993, 113(2): 279-294.
[5] GONZALEZ A B R, WILBY M R, DIAZ J J V, et al. Modeling and detecting aggressiveness from driving signals[J]. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(4): 1 419-1 428.
[6] JEONG E. Detection of lateral hazardous driving events using in-vehicle gyro sensor data[J]. KSCE Journal of Civil Engineering, 2013, 17(6): 1 471-1 479.
[7] LAJUNEN T, SUMMALA H. Driving experience, personality, and skill and safety-motive dimensions in drivers' self-assessments[J]. Personality and Individual Differences, 1995, 19(3): 307-318.
[8] 庄明科, 白海峰, 谢晓非. 驾驶人员风险驾驶行为分析及相关因素研究[J]. 北京大学学报:自然科学版, 2008, 44(3): 475-482.
ZHUANG Mingke, BAI Haifeng, XIE Xiaofei. A study on risky driving behavior and related factors [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2008, 44(3): 475-482.
[9] LI Pengfei, SHI Jianjun, LIU Xiaoming. Driving style recognition based on driver behavior questionnaire[J]. Open Journal of Applied Sciences, 2017, 7(4): 115-128.
[10] 孙龙,常若松. 营运驾驶员驾驶风格研究[J]. 人类工效学, 2014, 20(3): 10-12.
SUN Long, CHANG Ruosong. A study on driving styles of commercial driver [J]. Chinese Journal of Ergonomics,2014, 20(3): 10-12.
[11] 侯海晶,金立生,关志伟,等. 驾驶风格对驾驶行为的影响[J]. 中国公路学报, 2018, 31(4): 22-31.
HOU Haijing, JIN Lisheng, GUAN Zhiwei, et al. Effects of driving style on driver behavior [J]. China Journal of Highway and Transport, 2018, 31(4): 22-31.
[12] WOO H, JI Yonghoon, TAMURA Y, et al. Driver classification in vehicle following behavior by using dynamic potential field method[C]. 2017 IEEE 20^th International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2017: 1-6.
[13] 王畅,付锐,彭金栓,等. 应用于换道预警的驾驶风格分类方法[J]. 交通运输系统工程与信息, 2014, 14(3): 187-193.
WANG Chang, FU Rui, PENG Jinshuan, et al. Driving style classification method for lane change warning system [J]. Journal of Transportation Systems Engineering and Information Technology, 2014, 14(3): 187-193.
[14] PENG Guanghan, HE Hongdi, LU Weizhen. A new car-following model with the consideration of incorporating timid and aggressive driving behaviors[J]. Physica A: Statistical Mechanics and its Applications, 2016, 442: 197-202.
[15] LYU Chen, HU Xiaosong, ALBERTO S V, et al. Driving-style-based co-design optimization of an automated electric vehicle: a cyber-physical system approach[J]. IEEE Transactions on Industrial Electronics, 2019, 66(4): 2 965-2 975.
[16] MARTINEZ C M, HEUCKE M, WANG F, et al. Driving style recognition for intelligent vehicle control and advanced driver assistance: a survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(3), 666-676.
[17] LIU Tong, SELP I, FU Rui. The relationship between different safety indicators in car-following situations[C]. 2018 IEEE Intelligent Vehicles Symposium (IV), IEEE, 2018: 1 515-1 520.
[18] 王雪松,朱美新,邢祎伦. 基于自然驾驶数据的避撞预警对跟车行为影响[J]. 同济大学学报:自然科学版, 2016, 44(7): 1 045-1 051.
WANG Xuesong, ZHU Meixin, XING Yilun. Impacts of collision warning system on car-following behavior based on naturalistic driving data [J]. Journal of Tongji University:Natural Science, 2016, 44(7): 1 045-1 051.
[19] HIGGS B, ABBAS M. A two-step segmentation algorithm for behavioral clustering of naturalistic driving styles[C]. 2013 IEEE 16^th International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2013: 857-862.
[20] LU Guangquan, CHENG Bo, LIN Qingfeng, et al. Quantitative indicator of homeostatic risk perception in car following[J]. Safety Science, 2012, 50(9): 1 898-1 905.

融合K-means与高斯混合模型的驾驶风格聚类研究

Study on driving style clustering based on K-means and Gaussian mixture model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王铁旦, 穆毅强, 彭定洪. HAZOP风险评级的变权犹豫模糊方法[J]. 中国安全科学学报, 2022, 32(5): 61-67.
[2]	彭亚雄, 刘广进, 黄智刚, 吕虎波, 吴立. 穿越富水断层带隧道爆破围岩突变失稳判据研究[J]. 中国安全科学学报, 2022, 32(5): 104-111.
[3]	刘嘉豪, 余杨, 张振兴, 余建星, 王巍巍, 傅一钦. 二维云模型和贝叶斯网络的立管风险评估方法[J]. 中国安全科学学报, 2022, 32(5): 147-154.
[4]	吕贞, 戚春华, 朱守林. 草原公路超车工况下驾驶人动态视觉特性及负荷[J]. 中国安全科学学报, 2022, 32(4): 15-22.
[5]	胡小兵, 李佳茹, 刘骋越, 李航, 周航. 一种评估网络结点和链接重要性的改进介数[J]. 中国安全科学学报, 2022, 32(3): 33-40.
[6]	罗福周, 袁慧卿, 张扬. 旧工业建筑再生项目消防安全韧性评估[J]. 中国安全科学学报, 2022, 32(3): 167-173.
[7]	骆正山, 段远哲, 王小完, 张新生. 高温环境下气藏型储气库泥岩盖层密封性评价^*[J]. 中国安全科学学报, 2022, 32(2): 74-82.
[8]	张鸽. 基于累积接尘量的尘肺病风险评估方法^*[J]. 中国安全科学学报, 2022, 32(2): 200-206.
[9]	石娟, 常丁懿, 郑鹏. 基于BP神经网络的建筑工人不安全行为预警模型^*[J]. 中国安全科学学报, 2022, 32(1): 27-33.
[10]	刘卓凡, 周星池, 刘通, 吴付威. 视觉分心程度对跟车运动状态的影响^*[J]. 中国安全科学学报, 2022, 32(1): 58-64.
[11]	宋英华, 白明轩, 马亚萍, 吕伟, 霍非舟. 考虑区域灾情分级的应急物资公平调度优化模型^*[J]. 中国安全科学学报, 2022, 32(1): 172-179.
[12]	杨天姿, 王铁骊, 彭恒明, 段海林. 小微企业生产安全事故应急脆弱性评价^*[J]. 中国安全科学学报, 2021, 31(12): 176-183.
[13]	余建星, 范海昭, 陈海成, 吴世博, 韩放, 刘少卿. 海洋立管失效风险因素分析方法及应用^*[J]. 中国安全科学学报, 2021, 31(11): 47-53.
[14]	宋英华, 汪雅馨, 马亚萍, 吕伟. 考虑灾民类型多模式协同应急疏散调度研究^*[J]. 中国安全科学学报, 2021, 31(11): 135-140.
[15]	阎红巧, 陈怡玥, 田琨, 胡瑾秋, 冒亚明, 周靖桐. 企业安全生产关键指标体系与风险评价模型^*[J]. 中国安全科学学报, 2021, 31(9): 21-28.