To design advanced driver assistance systems with personalized service features, it is essential to delve into the diverse micro-driving styles of drivers. Traditional research often treats driving styles as fixed labels, yet drivers exhibit unique micro-driving behaviors and preferences in different traffic environments. Using data collected from a driving simulator, 68 different road geometries were analyzed to explore variations in driving characteristics under different conditions. Initially, dimensionality reduction was performed on evaluation metrics through feature extraction and selection. Subsequently, the K-means algorithm was employed for driving style clustering, with t-SNE visualization illustrating the differences between the two dimensionality reduction methods. Finally, genetic algorithms were used for adaptive parameter optimization, leading to the development of four identification models: GA-XGBoost, GA-LightGBM, GA-SVM, and GA-BPNN, enabling the discrimination of micro-driving styles without prior knowledge of drivers or driving scenarios. The results indicate that feature selection yields superior dimensionality reduction, retaining more feature information and providing a solid foundation for K-means clustering. Among the various micro-driving style identification models optimized by genetic algorithms, GA-BPNN demonstrated the best performance in predicting unknown data, with high accuracy and strong generalization ability. The research findings provide theoretical foundations and technical support for a deeper understanding of human driving behaviors and the personalized adjustment of autonomous vehicle assistance strategies.
ZHANG Zhi-qing, LI Yi-xin, ZHU Lei-peng, WANG Shi-hao, YU Xiao-zheng, SUN Yu-feng.
Identification of Microscopic Driving Styles Based on Driving Simulator Scenarios[J].
Science Technology and Engineering, 2026, 26(2): 817-831 DOI:10.12404/j.issn.1671-1815.2408320
ZhangXiaohui, ZhaoShishu, GuoKuiyuan, et al. Research on characteristics and current test standards of V2X application scena-rios for commercial vehicles[J]. China Auto, 2022(2): 51-56.
[3]
ChuH, ZhuangH, WangW, et al. A review of driving style recognition methods from short-term and long-term perspectives[J]. IEEE Transactions on Intelligent Vehicles, 2023, 8(11): 4599-4612.
DaXiaofeng, WangJian, XuYinghao, et al. Driving style-based sensitivity analysis of driving risk field in mountain highway through village and town sections[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(6): 316-325.
[6]
MaY, LiW, TangK, et al. Driving style recognition and comparisons among driving tasks based on driver behavior in the online car-hailing industry[J]. Accident Analysis & Prevention, 2021, 154. DOI: 10.1016/j.aap.2021.106096.
[7]
Marina MartinezC, HeuckeM, WangF Y, 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.
[8]
LiangK, ZhaoZ, LiW, et al. Comprehensive identification of driving style based on vehicle’s driving cycle recognition[J]. IEEE Transactions on Vehicular Technology, 2023, 72(1): 312-326.
[9]
ZhaoS, ChenG, HuaM, et al. An identification algorithm of driver steering characteristics based on backpropagation neural network[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2019, 233(9): 2333-2342.
LiuTong, FuRui, MaYong, et al. Car-following warning rules considering driving styles[J]. China Journal of Highway and Transport, 2020, 33(2): 170-180.
[12]
ZhengO, Abdel-AtyM, YueL, et al. CitySim: a drone-based vehicle trajectory dataset for safety-oriented research and digital twins[J]. Transportation Research Record: Journal of the Transportation Research Board, 2024, 2678(4): 606-621.
[13]
SunP, WangX, ZhuM. Modeling car-following behavior on freeways considering driving style[J]. Journal of Transportation Engineering, Part A: Systems, 2021, 147(12). DOI: 10.1061/JTEPBS.0000584.
ZhangLicheng, ZhangTing, CaiXuerui, et al. Review of classification methods and quantitative evaluation of driving behavior[J]. Automobile Technology, 2024(5): 1-14.
[16]
HeX, XuL, ZhangZ. Driving behaviour characterisation by using phase-space reconstruction and pre-trained convolutional neural network[J]. IET Intelligent Transport Systems, 2019, 13(7): 1173-1180.
[17]
ChenZ, ZhuB, ZhaoJ, et al. Variable servo characteristic brake system matching and implementing method based on driving style identification[J]. IEEE Transactions on Transportation Electrification, 2023, 9(1): 45-59.
[18]
GongC, ZongC, DaiC, et al. Adaptive personalized steer-by-wire system design based on driving style identification[C]// IEEE 25th International Conference on Intelligent Transportation Systems (ITSC). Macau: IEEE, 2022: 1367-1374.
[19]
LiuW, DengK, ZhangX, et al. A semi-supervised tri-CatBoost method for driving style recognition[J]. Symmetry, 2020, 12(3): DOI: 10.3390/sym12030336.
LiuDi, ZhengJianming, QinBin, et al. Research on driving style based on big data of natural driving scene[J]. Automobile Technology, 2022(9): 36-42.
[22]
WangW, XiJ, ZhaoD. Driving style analysis using primitive driving patterns with bayesian nonparametric approaches[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(8): 2986-2998.
[23]
ChenC, LiuQ, WangX, et al. Semi-Traj2Graph: identifying fine-grained driving style with GPS trajectory data via multi-task learning[J]. IEEE Transactions on Big Data, 2021, 8(6): 1550-1565.
YangYufeng, QuDayi, LanTianhe, et al. The personalized driving style propensity recognition method based on machine learning[J/OL]. [2025-10-13]. https://link.cnki.net/urlid/44.1401.n.20240102.1717.006.
YangYufeng, QuDayi, LanTianhe, et al. Deep learning-based driver’s driving propensityclassification and identification method[J]. Journal of Guangxi University(Natural Science Edition), 2024, 49(2): 324-335.
[28]
ShzdalevaE, NagyI. An online estimation of driving style using data-dependent pointer model[J]. Transportation Research Part C: Emerging Technologies, 2018, 86: 23-36.
[29]
HuangJ, ChenY, PengX, et al. Study on the driving style adaptive vehicle longitudinal control strategy[J]. IEEE/CAA Journal of Automatica Sinica, 2020, 7(4): 1107-1115.
[30]
ChenX, SunJ, MaZ, et al. Investigating the long-and short-term driving characteristics and incorporating them into car-following models[J]. Transportation Research Part C: Emerging Technologies, 2020, 117. DOI: 10.1016/j.trc.2020.102698.
[31]
GuoQ, ZhaoZ, ShenP, et al. Adaptive optimal control based on driving style recognition for plug-in hybrid electric vehicle[J]. Energy, 2019, 186. DOI: 10.1016/j.energy.2019.07.154.
[32]
WangX, ChenZ, GuoQ, et al. Transferability analysis of the freeway continuous speed model[J]. Accident Analysis & Prevention, 2021, 151. DOI: 10.1016/j.aap.2020.105944.
ZhangLicheng, ZhangTing, CaiXuerui, et al. Review of classification methods and quantitative evaluation of driving behavior[J]. Automobile Technology, 2024(5): 1-14.
LiAodi, QuDayi, DaiShouchen, et al. Safe trajectory planning for lane changing based on reachability analysis[J]. Science Technology and Engineering, 2024, 24(21): 9210-9217.
WeiChuanbao, QuDayi, KangAiping, et al. Modeling of lane change behavior of connected autonomous vehicles based on risk potential field[J]. Science Technology and Engineering, 2024, 24(20): 8754-8760.
FuQiang, ZhaoXiaohua, LiHaijian, et al. Operational characteristics and eco-safe influence of connected mixed platoon in car-following event[J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(8): 65-75.
LiXuewei, ZhaoXiaohua, LiZhenglong, et al. Driver’s visual information processing mode in foggy highway cooperative vehicle-infrastructure system environment based on simulated driving[J]. Journal of South China University of Technology(Natural Science Edition), 2021, 49(3): 131-138, 148.
TianWanqi, BuBing, LüJidong, et al. Research on prediction method of high-speed train tracking trajectory based on driving feature recognition[J]. Journal of the China Railway Society, 2025(1): 71-81.
HouShanshan, ZhangJie, ZhangXueyu, et al. Investigation on the driving risk of high-density over-exchange group vehicles considering driving style[J]. Science Technology and Engineering, 2024, 24(10): 4317-4328.
ZhuZiyong, QinHua, RanLinghua, et al. Effect of driving style of left-turning vehicles on the interaction behavior of straight-traveling vehicles[J]. Science Technology and Engineering, 2024, 24(31): 13612-13619.
[49]
WangX, GuoQ, TarkoA P. Modeling speed profiles on mountainous freeways using high resolution data[J]. Transportation Research Part C: Emerging Technologies, 2020, 117. DOI: 10.1016/j.trc.2020.102679.
ShuHang, YangGuanlong, HuYuanli, et al.Recognition method for driving style based on fuzzy control[C]// The 31st China SAE Annual Conference and Exhibition (SAECCE2024). Chongqing: SAECCE, 2024: 594-602.