A Method of Intelligent Driving-Style Recognition Using Natural Driving Data
Source abstract
Abstract
At present, achieving efficient, sustainable, and safe transportation has led to increasing attention on driving behavior recognition and advancements in autonomous driving. Identifying diverse driving styles and corresponding types is crucial for providing targeted training and assistance to drivers, enhancing safety awareness, optimizing driving costs, and improving autonomous driving systems responses. However, current studies mainly focus on specific driving scenarios, such as free driving, car-following, and lane-changing, lacking a comprehensive and systematic framework to identify the diverse driving styles. This study proposes a novel, data-driven approach to driving-style recognition utilizing naturalistic driving data NGSIM. Specifically, the NGSIM dataset is employed to categorize car-following and lane-changing groups according to driving-state extraction conditions. Then, characteristic parameters that fully represent driving styles are optimized through correlation analysis and principal component analysis for dimensionality reduction. The K-means clustering algorithm is applied to categorize the car-following and lane-changing groups into three driving styles: conservative, moderate, and radical. Based on the clustering results, a comprehensive evaluation of the driving styles is conducted. Finally, a comparative evaluation of SVM, Random Forest, and KNN recognition indicates the superiority of the SVM algorithm and highlights the effectiveness of dimensionality reduction in optimizing characteristic parameters. The proposed method achieves over 97% accuracy in identifying car-following and lane-changing behaviors, confirming that the approach based on naturalistic driving data can effectively and intelligently recognize driving styles.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Autonomous Vehicle Technology and Safety · Video Surveillance and Tracking Methods · Traffic Prediction and Management Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai 201804, China
Funding
Fundamental Research Funds for the Central Universities
References (65)
Show source-provided references
1. Behavioral Correlates of Individual Differences in Road-Traffic Crash Risk: An Examination of Methods and Findings10.1037/0033-2909.113.2.279 ↗
2. Wang, X. (2020). Research on Driving Behavior Identification and Modeling Method Based on Natural Driving Data. [Master’s Thesis, Henan University].
3. Selpi Characterisation of Motorway Driving Style Using Naturalistic Driving Data10.1016/j.trf.2020.01.003 ↗
4. A Methodology for Generating Driving Styles for Autonomous Cars10.1080/15472450.2022.2109417 ↗
5. Safety Evaluation of Vehicle Following Behavior Based on NGSIM Microscopic Trajectory Data
6. Driving Style Classification Method for Lane Change Warning System
7. Intelligent Driving Path Tracking Algorithm Considering Driver Characteristics
8. Mao, J. (2012). Methods of Lane Change Warning Considering the Driving Style. [Master’s Thesis, Chang’an University].
9. Classifying Travelers’ Driving Style Using Basic Safety Messages Generated by Connected Vehicles: Application of Unsupervised Machine Learning10.1016/j.trc.2020.102917 ↗
10. Driving Style Recognition Considering Vehicle Following Vehicle and Lane Changing Interaction Parameters
11. Al-refai, G., Elmoaqet, H., and Ryalat, M. (2022). In-Vehicle Data for Predicting Road Conditions and Driving Style Using Machine Learning. Appl. Sci., 12.10.3390/app12188928 ↗
12. Driver Classification for Optimization of Energy Usage in a Vehicle10.1016/j.procs.2012.01.077 ↗
13. Application of Self-Organizing Maps on Time Series Data for Identifying Interpretable Driving Manoeuvres10.1186/s12544-020-00421-x ↗
14. Vaitkus, V., Lengvenis, P., and Zylius, G. (2014, January 2–5). Driving Style Classification Using Long-Term Accelerometer Information. Proceedings of the 2014 19th International Conference on Methods and Models in Automation and Robotics (MMAR), Miedzyzdroje, Poland.10.1109/MMAR.2014.6957429 ↗
15. Sysoev, M., Kos, A., Guna, J., and Pogacnik, M. (2017). Estimation of the Driving Style Based on the Users’ Activity and Environment Influence. Sensors, 17.10.3390/s17102404 ↗
16. Duan, X., Schockenhoff, F., and Koch, A. (2022). Implementation of Driving Cycles Based on Driving Style Characteristics of Autonomous Vehicles. World Electr. Veh. J., 13.10.3390/wevj13060108 ↗
17. Ishibashi, M., Okuwa, M., Doi, S.I., and Akamatsu, M. (2007, January 17–20). Indices for Characterizing Driving Style and Their Relevance to Car Following Behavior. Proceedings of the SICE Annual Conference 2007, Takamatsu, Japan.
18. Current Status and Prospects of Driving Style Research
19. Relationship between Driving Styles and Biological Behavior of Drivers in Negative Emotional State10.1016/j.trf.2022.01.010 ↗
20. Classification of Driving Style Using Simplified Features of Headway Under the Connected Vehicles Environment
21. Driving Style Recognition System Using Smartphone Sensors Based on Fuzzy Logic
22. Tian, F. (2016). Research on Lane Change Behavioral Spectral Analysis. [Master’s Thesis, Wuhan University of Technology].
23. Cordero, J., Aguilar, J., Aguilar, K., Chavez, D., and Puerto, E. (2020). Recognition of the Driving Style in Vehicle Drivers. Sensors, 20.10.3390/s20092597 ↗
24. Driving Style Recognition Using Interval Type-2 Fuzzy Inference System and Multiple Experts Decision-Making10.1007/s40815-023-01616-9 ↗
25. A Method of Automatic Driving Decision for Smart Car Considering Driving Style
26. Research of Clustering and Recognition for Driving Style
27. Wang, Q. (2020). A Driving Risk Evaluation Method Considering Driver Characteristics. [Master’s Thesis, Jilin University].
28. Research on Driving Style Clustering Based on NGSIM Database
29. Study on driving style clustering based on K-means and Gaussian mixture model
30. Does a Cautious Driving Style Reduce the Crash Risk of Older Drivers? An Analysis Using a Novel Driving Style Recognition Method10.1016/j.trf.2024.05.019 ↗
31. Research on Classification and Recognition of Driving Style of Domestic Crowds
32. Analysis of Safe Driving Behavior Based on Combination Weighting and Fuzzy Comprehensive Evaluation
33. Research on a driving style recognition method based on improved DBSCAN algorithm
34. Wang, L., Lin, Q.-F., Wu, Z.-Y., and Yu, B. (2020). A Data-Driven Estimation of Driving Style Using Deep Clustering. CICTP 2020, American Society of Civil Engineers.10.1061/9780784482933.359 ↗
35. Zheng, Q. (2022). Research on Driver Style Recognition and Vehicle Behavior Prediction for Intelligent Driving. [Master’s Thesis, Zhejiang University].
36. Identification of driver types in automated driving Results of an online survey and a driving simulator study
37. A Study on the Driving Style Recognition of Hybrid Electric Vehicle
38. Research on Classification and Recognition of Driving Styles Based on Feature Engineering10.1109/ACCESS.2019.2926593 ↗
39. Driving Style Recognition and Quantification for Heavy-duty Truck Drivers
40. Jin, L. (2019). Construction of Driving Style Recognition Model Based on Multi-Feature Parameter. [Master’s Thesis, Hunan University].
41. Xia, L., and Kang, Z. (2021). Driving Style Recognition Model Based on NEV High-Frequency Big Data and Joint Distribution Feature Parameters. World Electr. Veh. J., 12.10.3390/wevj12030142 ↗
42. Driving Style Classification and Recognition Method Based on Data Features
43. Silva, I., and Eugenio Naranjo, J. (2020). A Systematic Methodology to Evaluate Prediction Models for Driving Style Classification. Sensors, 20.10.3390/s20061692 ↗
44. Research on driving style recognition based on multivariate feature parameters and an improved SVM algorithm
45. Driving Style-Based Conditional Variational Autoencoder for Prediction of Ego Vehicle Trajectory10.1109/ACCESS.2021.3138502 ↗
46. Adaptive Driving Style Classification through Transfer Learning with Synthetic Oversampling10.3390/vehicles4040069 ↗
47. Doerr, D., Grabengiesser, D., and Gauterin, F. (2014, January 8–11). Online Driving Style Recognition Using Fuzzy Logic. Proceedings of the 2014 IEEE 17th International Conference on Intelligent Transportation Systems (ITSC), Qingdao, China.10.1109/ITSC.2014.6957822 ↗
48. Johnson, D.A., and Trivedi, M.M. (2011, January 5–7). Driving Style Recognition Using a Smartphone as a Sensor Platform. Proceedings of the 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC), Washington, DC, USA.10.1109/ITSC.2011.6083078 ↗
49. A Fuzzy Logic Approach on the Evaluation of Driving Styles and Investigation of Drivability Calibration Effects10.35378/gujs.862867 ↗
50. Panagiotopoulos, I., and Dimitrakopoulos, G. (2023). Intelligent, In-Vehicle Autonomous Decision-Making Functionality for Driving Style Reconfigurations. Electronics, 12.10.3390/electronics12061370 ↗
51. DrivingStyles: A Mobile Platform for Driving Styles and Fuel Consumption Characterization10.1109/JCN.2017.000025 ↗
52. Croce, A.I., Musolino, G., Rindone, C., and Vitetta, A. (2021). Traffic and Energy Consumption Modelling of Electric Vehicles: Parameter Updating from Floating and Probe Vehicle Data. Energies, 15.10.3390/en15010082 ↗
53. Assessing Driving Behavior Influence on Fuel Efficiency Using Machine-Learning and Drive-Cycle Simulations10.1016/j.trd.2023.104025 ↗
54. Two-Layer Pointer Model of Driving Style Depending on the Driving Environment10.1016/j.trb.2019.08.009 ↗
55. Rygula, A. (2009, January 25–28). Driving Style Identification Method Based on Speed Graph Analysis. Proceedings of the ICBAKE: 2009 International Conference on Biometrics and Kansei Engineering, Cieszyn, Poland.10.1109/ICBAKE.2009.51 ↗
56. The Prevention of Road Accidents in Non-Expert Drivers: Exploring the Influence of Theory of Mind and Driving Style10.1016/j.ssci.2024.106516 ↗
57. Rizzo, N., Sprissler, E., Hong, Y., and Goel, S. (2015, January 19–23). Privacy Preserving Driving Style Recognition. Proceedings of the 2015 International Conference on Connected Vehicles and Expo (Iccve), Shenzhen, China.10.1109/ICCVE.2015.42 ↗
58. Russo, F., and Rindone, C. (2024). Methods for Risk Reduction: Training and Exercises to Pursue the Planned Evacuation. Sustainability, 16.10.3390/su16041474 ↗
59. Driving Simulator Validation Studies: A Systematic Review10.1016/j.simpat.2024.103020 ↗
60. Smoothing and Differentiation of Data by Simplified Least Squares Procedures10.1021/ac60214a047 ↗
61. What is a Savitzky-Golay Filter?10.1109/MSP.2011.941097 ↗
62. Least-Squares Fitting of Data by Polynomials10.1109/5289.975465 ↗
63. On class of perceptrons
64. The Research and Implementation of Cloud Platform Based Random Forest Algorithm on High Dimensional Data
65. A Random Forest Algorithm for Imbalanced Classification