Focusing on Driving Modes Rather than Drivers: Toward More Precise and Efficient Car-Following Behavior Modeling
Source abstract
Abstract
Car-following (CF) behavior is one of the most important driving behaviors. Accurately understanding and modeling CF behavior is essential for traffic flow simulation and user-acceptable advanced driving assistance systems (ADASs). In previous decades, CF models were calibrated based on drivers or trajectories, with short-term changes ignored. Recent studies have indicated that these changes could be caused by occasional irritations or regular switches of driving modes, but there is still a lack of specific understanding of driving modes and how these modes affect simulation accuracy in the reproduction of CF behavior. This paper explored the existence of driving modes and the quantified modeling influence of driving modes. Specifically, we first extracted 4000 high-resolution CF events of 40 drivers from large-scale naturalistic driving data for the discovery of underlying driving modes. Then, we introduced a novel multivariate time series method, Toeplitz Inverse Covariance-based Clustering (TICC), to achieve the segmentation and classification extraction of different driving modes. Finally, calibrated by the CF dataset, the proper cluster number of the driving mode was determined, and a comparison of driving-mode-based modeling (DMBM) and driver-based modeling (DBM) was conducted. The results showed that the driving process could be viewed as five core driving modes, and the DMBM has the potential to bring upwards of a 13% accuracy improvement with fewer parameters.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Traffic control and management · Traffic Prediction and Management Techniques · Autonomous Vehicle Technology and Safety
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai 200092, China
Hangzhou Hikvision Digital Technology Co., Ltd., Hangzhou 310051, China
Funding
National Natural Science Foundation of China · Zhejiang Lab Open Research Project
References (58)
Show source-provided references
1. A comprehensive comparison study of four classical car-following models based on the large-scale naturalistic driving experiment10.1016/j.simpat.2021.102383 ↗
2. Stability analysis methods and their applicability to car-following models in conventional and connected environments10.1016/j.trb.2018.01.013 ↗
3. Higatani, A., and Saleh, W. (2021). An investigation into the appropriateness of car-following models in assessing autonomous vehicles. Sensors, 21.10.3390/s21217131 ↗
4. Artificial intelligence techniques for driving safety and vehicle crash prediction10.1007/s10462-016-9467-9 ↗
5. On identification of driving-induced stress using electroencephalogram signals: A framework based on wearable safety-critical scheme and machine learning10.1016/j.inffus.2019.06.006 ↗
6. Investigating the long-and short-term driving characteristics and incorporating them into car-following models10.1016/j.trc.2020.102698 ↗
7. Segmentation and clustering of car-following behavior: Recognition of driving patterns10.1109/TITS.2014.2326082 ↗
8. A general framework for calibrating and comparing car-following models
9. Chen, C., Li, L., Hu, J., and Geng, C. (2010, January 15–17). Calibration of MITSIM and IDM car-following model based on NGSIM trajectory datasets. Proceedings of the 2010 IEEE International Conference on Vehicular Electronics and Safety, Qingdao, China.10.1109/ICVES.2010.5550943 ↗
10. Lu, X.-Y., and Skabardonis, A. (2007, January 21–25). Freeway traffic shockwave analysis: Exploring the NGSIM trajectory data. Proceedings of the 86th Annual Meeting of the Transportation Research Board, Washington, DC, USA.
11. A critical evaluation of the Next Generation Simulation (NGSIM) vehicle trajectory dataset10.1016/j.trb.2017.09.018 ↗
12. Studying car-following dynamics on the basis of the HighD dataset10.1177/0361198120925063 ↗
13. Incorporating human-factors in car-following models: A review of recent developments and research needs10.1016/j.trc.2014.09.008 ↗
14. Traffic dynamics: Studies in car following10.1287/opre.6.2.165 ↗
15. A generalization of linear car-following theory10.1287/opre.14.4.595 ↗
16. Ahmed, K.I. (1999). Modeling Drivers’ Acceleration and Lane Changing Behavior, Massachusetts Institute of Technology.
17. Kometani, E. (1959). Theory of Traffic Flow, Proceedings of the Symposium on the Theory of Traffic Flow (GM), Detroit, MI, USA, 7–8 December 1959, Transportation Research Board.
18. Nonlinear effects in the dynamics of car following10.1287/opre.9.2.209 ↗
19. A behavioural car-following model for computer simulation10.1016/0191-2615(81)90037-0 ↗
20. Helly, W. (1959). Simulation of Bottlenecks in Single-Lane Traffic Flow, Scientific Research Publishing.
21. Higgs, B.J. (2011). Application of Naturalistic Truck Driving Data to Analyze and Improve Car Following Models, Virginia Tech.
22. Higgs, B., Abbas, M., and Medina, A. (2011, January 14–15). Analysis of the Wiedemann car following model over different speeds using naturalistic data. Proceedings of the 3rd International Conference on Road Safety and Simulation, Indianapolis, IN, USA.
23. A car-following model considering asymmetric driving behavior based on long short-term memory neural networks10.1016/j.trc.2018.07.022 ↗
24. Using trajectory data to analyze intradriver heterogeneity in car-following10.3141/2188-10 ↗
25. MOHA: A multi-mode hybrid automaton model for learning car-following behaviors10.1109/TITS.2018.2823418 ↗
26. Müller, M. (2007). Information Retrieval for Music and Motion, Springer.10.1007/978-3-540-74048-3 ↗
27. Multianticipative piecewise-linear car-following model10.3141/2315-11 ↗
28. Movement similarity assessment using symbolic representation of trajectories10.1080/13658816.2011.630003 ↗
29. Gionis, A., and Mannila, H. (2003, January 10–13). Finding recurrent sources in sequences. Proceedings of the Seventh Annual International Conference on Research in Computational Molecular Biology, Berlin, Germany.10.1145/640075.640091 ↗
30. A review of subsequence time series clustering10.1155/2014/312521 ↗
31. Clustering of time-series subsequences is meaningless: Implications for previous and future research10.1007/s10115-004-0172-7 ↗
32. Traffic Administration Bureau of the Ministry of Public Security, Ministry of Public Security, China (2023, April 20). The Number of Drivers in Our Country Is Growing Rapidly, with an Average Annual Increase of 25 Million People. The Total Number of Drivers Exceeds 500 Million, Ranking First in the World, Available online: https://app.mps.gov.cn/gdnps/pc/content.jsp?id=8794518.
33. Traffic Administration Bureau of the Ministry of Public Security, Ministry of Public Security, China (2023, April 20). In 2021, the Number of Motor Vehicles in the Country Reached 395 Million, and the Number of New Energy Vehicles Increased by 59.25% Year-on-Year, Available online: https://app.mps.gov.cn/gdnps/pc/content.jsp?id=8322369.
34. Longitudinal driving behavior with integrated crash-warning system: Evaluation from naturalistic driving data10.3141/2365-03 ↗
35. Detecting Distraction Behavior of Drivers Using Naturalistic Driving Data
36. Hallac, D., Vare, S., Boyd, S., and Leskovec, J. (2017, January 13–17). Toeplitz inverse covariance-based clustering of multivariate time series data. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada.10.1145/3097983.3098060 ↗
37. Greedy Gaussian segmentation of multivariate time series10.1007/s11634-018-0335-0 ↗
38. Himberg, J., Korpiaho, K., Mannila, H., Tikanmaki, J., and Toivonen, H.T. (December, January 29). Time series segmentation for context recognition in mobile devices. Proceedings of the 2001 IEEE International Conference on Data Mining, San Jose, CA, USA.
39. Begum, N., Ulanova, L., Wang, J., and Keogh, E. (2015, January 10–13). Accelerating dynamic time warping clustering with a novel admissible pruning strategy. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, NSW, Australia.10.1145/2783258.2783286 ↗
40. Smyth, P. (1996). Clustering sequences with hidden Markov models. Adv. Neural Inf. Process. Syst., 9.
41. Berndt, D.J., and Clifford, J. (August, January 31). Using dynamic time warping to find patterns in time series. Proceedings of the KDD Workshop, Seattle, WA, USA.
42. Dai, L., Li, Y., and Zhang, M. (2023). Detection of Operator Fatigue in the Main Control Room of a Nuclear Power Plant Based on Eye Blink Rate, PERCLOS and Mouse Velocity. Appl. Sci., 13.10.3390/app13042718 ↗
43. Stock index pattern discovery via toeplitz inverse covariance-based clustering
44. Yang, X. (2021, January 19–26). Multi-series Time-aware Sequence Partitioning for Disease Progression Modeling. Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI), Montreal-Themed Virtual Reality.10.24963/ijcai.2021/493 ↗
45. Calibration and validation of psychophysical car-following model using driver’s action points and perception thresholds10.1061/JTEPBS.0000264 ↗
46. Calibrating Wiedemann-99 model parameters to trajectory data of mixed vehicular traffic10.1177/03611981211037543 ↗
47. Assessment of car-following models by driver type and under different traffic, weather conditions using data from an instrumented vehicle10.1016/j.simpat.2013.10.002 ↗
48. Analysis and comparison of microscopic traffic flow models with real traffic microscopic data10.1177/0361198105193400106 ↗
49. Microscopic calibration and validation of car-following models—A systematic approach10.1016/j.sbspro.2013.05.050 ↗
50. Speed or spacing? Cumulative variables, and convolution of model errors and time in traffic flow models validation and calibration10.1016/j.trb.2016.04.012 ↗
51. Can results of car-following model calibration based on trajectory data be trusted?10.3141/2315-02 ↗
52. Ciuffo, B., and Punzo, V. (2010, January 10–14). Verification of traffic micro-simulation model calibration procedures: Analysis of goodness-of-fit measures. Proceedings of the 89th Annual Meeting of the Transportation Research Record, Washington, DC, USA.
53. Identifying driver heterogeneity in car-following based on a random coefficient model10.1016/j.trc.2013.08.003 ↗
54. Profiling drivers based on driver dependent vehicle driving features10.1007/s10489-015-0722-6 ↗
55. Kapp, V., May, M.C., Lanza, G., and Wuest, T. (2020). Pattern recognition in multivariate time series: Towards an automated event detection method for smart manufacturing systems. J. Manuf. Mater. Process., 4.10.3390/jmmp4030088 ↗
56. How close is the sample covariance matrix to the actual covariance matrix?10.1007/s10959-010-0338-z ↗
57. Sparse inverse covariance estimation with the graphical lasso10.1093/biostatistics/kxm045 ↗
58. Asynchronous distributed ADMM for large-scale optimization—Part I: Algorithm and convergence analysis10.1109/TSP.2016.2537271 ↗