智能网联汽车中联合驾驶风格的交通流数据有效性分析

doi:10.19678/j.issn.1000-3428.0067946

摘要/Abstract

摘要： 在智能网联汽车(ICV)中,提高驾驶数据的有效性是提升车辆安全性的基石。只有准确的、可靠的驾驶数据才能为车辆的安全性提供可靠的依据和支持。与传统的异常分析相比,ICV数据有效性分析面临数据异常的多样性(传感器异常、驾驶行为、恶意篡改等)。如何将车辆自身数据特征、驾驶风格和交通流特征相结合,提供有效的数据异常检测方法,已成为智能网联汽车中新的问题。针对ICV系统,采用结合驾驶风格和交通流理论的方法,设计基于粒子群优化的TE-PSO-SVM数据有效性检测算法,实现驾驶数据的有效检测。首先定义驾驶风格识别系数R_ad,设计驾驶风格量化模型;其次建立交通流模型,将车辆状态数据与驾驶风格和交通流理论相结合,通过长短期记忆(LSTM)网络对车辆速度预测;最后通过TE-PSO-SVM算法进行数据有效性检测。由于ICV数据的多样性,单一模型在多类型异常混合并存的场景中检测精度仍有局限,利用多个模型的优势构建模型池,并提出基于强化学习的模型选择(RLBMS)算法。在真实数据集highD上的实验结果表明,在不同噪声环境下,TE-PSO-SVM算法模型的F1值相比于传统SVM模型平均提升约8.1个百分点;RLBMS算法模型在不同噪声环境下的F1值相比于模型池中检测率最高的算法平均提高约1.7个百分点,明显提高了数据有效性检测的准确率。

关键词: 智能网联汽车, 驾驶风格, 交通流理论, 粒子群优化算法, 强化学习, 有效性分析

Abstract: In an Intelligent Connected Vehicle (ICV), improving the effectiveness of driving data is crucial for improving vehicle safety. Only accurate and reliable driving data can provide a reliable basis and support for vehicle safety. Compared with the conventional anomaly analysis, the analysis of ICV data validity is accompanied by various data anomalies (e.g., sensor anomalies, driving behavior, and malicious tampering). Researchers of intelligent networked vehicles are attempting to identify a method to combine the vehicle's data characteristics, driving style, and traffic-flow characteristics to provide an effective data-anomaly detection method. For an ICV system, a TE-PSO-SVM data-validity detection algorithm based on particle swarm optimization is designed by combining driving style and traffic-flow theory to effectively detect driving data. First, the driving-style recognition coefficient Rad is defined and the driving-style quantitative model is designed. Second, a traffic-flow model is established, which combines the driving style and traffic-flow theory with vehicle-state data to predict vehicle speed via the Long Short-Term Memory (LSTM) network. Finally, the TE-PSO-SVM algorithm is used to detect the validity of the data. Owing to the diversity of ICV data, the detection accuracy of a single model is limited in scenarios where multiple types of anomalies coexist. To fully utilize the advantages of multiple models, a model pool is constructed, and a Reinforcement Learning-Based Model Selection(RLBMS) algorithm is proposed. Experiments on real dataset highD show that the F1 value of the TE-PSO-SVM algorithm model is 8.1 percentage points higher than that of the conventional SVM model under different noise environments. Compared with the result of the algorithm with the highest detection rate in the model pool, the F1 value of the RLBMS algorithm model in different noise environments is approximately 1.7 percentage points higher on average, which further improves the accuracy of data-validity detection.

Key words: Intelligent Connected Vehicle(ICV), driving style, traffic flow theory, Particle Swarm Optimization(PSO) algorithm, reinforcement learning, validity analysis

中图分类号:

TP391

高家豪, 胡创业, 丁男, 刘战东. 智能网联汽车中联合驾驶风格的交通流数据有效性分析[J]. 计算机工程, 2024, 50(6): 367-376.

GAO Jiahao, HU Chuangye, DING Nan, LIU Zhandong. Validity Analysis of Traffic-Flow Data for Combined Driving Style in Intelligent Connected Vehicle[J]. Computer Engineering, 2024, 50(6): 367-376.

https://www.ecice06.com/CN/Y2024/V50/I6/367

参考文献

[1] CHEN Y, CHEN T, JIN L. Development strategy research on intelligent and connected vehicle of America[C]//Proceedings of IET International Conference on Intelligent&Connected Vehicles. Washington D. C., USA:IEEE Press, 2016:457-468.
[2] 腾讯科恩实验室.Autopilot的几个软件漏洞被发现了[EB/OL].[2023-05-11].https://www.guancha.cn/qiche/2019_04_02_496109.shtml. Tencent Cohen Laboratory. Several software vulnerabilities in Autopilot have been discovered[EB/OL].[2023-05-11].https://www.guancha.cn/qiche/2019_04_02_496109.shtml.(in Chinese)
[3] 汽车前沿.SiriusXM车联网服务曝高危漏洞[EB/OL].[2023-05-11]. https://www.hfyili.cn/a/349443. Automotive Frontiers. SiriusXM connected car service exposed a high risk vulnerability[EB/OL].[2023-56-11]. https://www.hfyili.cn/a/349443.(in Chinese)
[4] 新浪科技.19岁黑客连续破解25辆特斯拉[EB/OL].[2023-05-11]. https://36kr.com/p/1572012375527304. Sina Technology. 19-year-old hacker cracked 25 Tesla vehicles in a row[EB/OL].[2023-05-11]. https://36kr.com/p/1572012375527304. (in Chinese)
[5] 彭锦峰,申德荣,寇月,等.基于多视角的多类型错误全面检测方法[J].软件学报, 2023, 34(3):1049-1064. PENG J F, SHEN D R, KOU Y, et al. Comprehensive error detection method for multiple types errors based on multiple views[J]. Journal of Software, 2023, 34(3):1049-1064.(in Chinese)
[6] WANG Y Y, MASOUD N, KHOJANDI A. Real-time sensor anomaly detection and recovery in connected automated vehicle sensors[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(3):1411-1421.
[7] DING N, MA H X, ZHAO C G, et al. Driver's emotional state-based data anomaly detection for vehicular ad hoc networks[C]//Proceedings of IEEE International Conference on Smart Internet of Things. Washington D. C.,USA:IEEE Press, 2019:121-126.
[8] RANAWEERA M, SENEVIRATNE A, REY D, et al. Anomalous data detection in vehicular networks using traffic flow theory[C]//Proceedings of the 90th IEEE Vehicular Technology Conference. Honolulu, USA:IEEE Press, 2019:1-5.
[9] 张海春,姜荣帅,王颉,等.基于熵的车载CAN总线异常检测研究[J].汽车工程, 2021, 43(10):1543-1548. ZHANG H C, JIANG R S, WANG J, et al. Research on anomaly detection of in-vehicle CAN bus based on entropy[J]. Automotive Engineering, 2021, 43(10):1543-1548.(in Chinese)
[10] ARSHAD M, ULLAH Z, KHALID M, et al. Beacon trust management system and fake data detection in vehicular ad-hoc networks[J]. IET Intelligent Transport Systems, 2019, 13(5):780-788.
[11] KHATTAK Z H, FONTAINE M D, LI W, et al. Investigating the relation between instantaneous driving decisions and safety critical events in naturalistic driving environment[J]. Accident Analysis⪻evention, 2021, 156:106086.
[12] MAERIVOSE S, DE MOOR B. Traffic flow theory[EB/OL].[2023-05-11]. https://arxiv.org/abs/0507126.
[13] XING Z C, LIU X L, FANG R, et al. Research on qualitative classification method of drivers'driving style[C]//Proceedings of IEEE International Conference on Advances in Electrical Engineering and Computer Applications. Washington D. C., USA:IEEE Press, 2021:709-716.
[14] ZYLIUS G. Investigation of route-independent aggressive and safe driving features obtained from accelerometer signals[J]. IEEE Intelligent Transportation Systems Magazine, 2017, 9(2):103-113.
[15] XIA N Y, YAN Y B, TANG X Q, et al. Research on driving style recognition model considering different traffic density and driving behavior[C]//Proceedings of the 6th CAA International Conference on Vehicular Control and Intelligence. Washington D. C.,USA:IEEE Press, 2022:1-8.
[16] MURPHEY Y L, MILTON R, KILIARIS L. Driver's style classification using jerk analysis[C]//Proceedings of IEEE Workshop on Computational Intelligence in Vehicles and Vehicular Systems. Nashville, USA:IEEE Press, 2009:23-28.
[17] GREENSHIELDS B D, BIBBINS J R, CHANNING W S, et al. A study of traffic capacity[J]. Highway Research Board Proceedings, 1935, 14(1):448-477.
[18] 曹栋发,李勇,胡创业,等.基于用户画像以及Stackelberg博弈的交通环岛通行策略[J].计算机工程, 2023, 49(9):208-216. CAO D F, LI Y, HU C Y, et al. Traffic strategy of roundabout based on user portrait and Stackelberg game[J]. Computer engineering, 2023, 49(9):208-216.(in Chinese)
[19] BEN-HUR A, HORN D, SIEGELMANN H T, et al. A support vector clustering method[C]//Proceedings of the 15th International Conference on Pattern Recognition. Barcelona, Spain:IEEE Press, 2000:724-727.
[20] KENNEDY J, EBERHART R. Particle swarm optimization[C]//Proceedings of International Conference on Neural Networks. Perth, Australia:IEEE Press, 1995:1942-1948.
[21] OSBAND I, BLUNDELL C, PRITZEL A, et al. Deep exploration via bootstrapped DQN[C]//Proceedings of Advances in Neural Information Processing Systems. Cambridge, USA:MIT Press, 2016:4033-4041.
[22] 崔景洋,陈振国,田立勤,等.基于机器学习的用户与实体行为分析技术综述[J].计算机工程, 2022, 48(2):10-24. CUI J Y, CHEN Z G, TIAN L Q, et al. Overview of user and entity behavior analytics technology based on machine learning[J]. Computer Engineering, 2022, 48(2):10-24.(in Chinese)
[23] CHANDOLA V, BANERJEE A, KUMAR V. Anomaly detection:a survey[J]. ACM Computing Surveys, 2009, 41(3):15.
[24] KRAJEWSKI R, BOCK J, KLOEKER L, et al. The highD dataset:a drone dataset of naturalistic vehicle trajectories on German highways for validation of highly automated driving systems[C]//Proceedings of the 21st International Conference on Intelligent Transportation Systems. New York, USA:ACM Press, 2018:2118-2125.
[25] 国家工业信息安全发展研究中心.自动驾驶数据安全白皮书(2020)[EB/OL].[2023-05-11].https://m.sohu.com/a/453643278_653604. National Industrial Information Security Development research Center. Autonomous driving data security white paper (2020)[EB/OL].[2023-05-11].https://m.sohu.com/a/453643278_653604. (in Chinese)
[26] ABBAS M, SAFAR M, SALEM A. Anomaly detection system for altered signal values within the intra-vehicle network[C]//Proceedings of the 15th Design&Technology of Integrated Systems in Nanoscale Era. Marrakech, Morocco:IEEE Press, 2020:1-6.
[27] REN G, ZHU S. Parameter calibration of traffic flow speed-density model based on k-means clustering algorithm and least square method[C]//Proceedings of CICTP'21. Reston, USA:American Society of Civil Engineers, 2021:66-76.

选择文件类型/文献管理软件名称

选择包含的内容