To better characterize the autonomous driving decision-making process driven by holistic vehicle perception and coupled interactions in a multi-dimensional environment, a multi-dimensional car-following model adopting a safety potential field force function to quantitatively describe inter-vehicle interaction relationships was proposed.First, dynamic interaction characteristics between vehicles and roads as well as among vehicles were depicted via road potential fields and vehicle interaction potential fields. Multi-dimensional vehicle operating mechanisms and corresponding force characteristics were analyzed from the perspective of safety potential fields. Second, traditional one-dimensional single-lane car-following models were improved by the introduction of two-dimensional vectors along longitudinal and lateral directions. Variations in inter-vehicle distances and required safety distances at arbitrary road positions and angles were captured through the improvement, and a unified multi-dimensional car-following model integrating the synergistic effects of three types of forces was constructed.Finally, undetermined parameters of the model were calibrated with particle swarm optimization algorithms and highway vehicle trajectory data. Simulation experiments covering multiple working scenarios are designed to assess the model's capacity to reproduce real vehicle following behaviors and its decision-making stability.Dynamic variations in vehicle behaviors under diverse operating states are effectively reflected by simulation results generated from the proposed model. Multi-dimensional and full-process autonomous decision-making under the action of safety potential fields is realized, and the application scope of traditional car-following models is expanded. High practicability, stability and safety are exhibited by the model, and a theoretical basis is laid for the enhancement of driving safety and traffic operation efficiency.
WangY L, BianN, ZhangL, et al. Coordinated lateral and longitudinal vehicle-following control of connected and automated vehicles considering nonlinear dynamics[J]. IEEE Control Systems Letters, 2020, 4(4): 1054-1059.
LiMeng-fan, QinWen-hu, YunZhong-hua. Multi-objective optimal car-following model with lateral and longitudinal control[J]. Application Research of Computers, 2022, 39(8): 2409-2413.
[4]
QinP, TanH, LiH, et al. Deep Reinforcement learning car-following model considering longitudinal and lateral control[J]. Sustainability, 2022, 14(24): No.16705.
[5]
NiH Y, YuG Z, ChenP, et al. An integrated framework of lateral and longitudinal behavior decision-making for autonomous driving using reinforcement learning[J]. IEEE Transactions on Vehicular Technology, 2024, 73(7): 9706-9720.
LiLin-heng, GanJing, QuXu, et al. Car-following model based on safety potential field theory under connected and automated vehicle environment[J]. China Journal of Highway and Transport, 2019, 32(12): 76-87.
LiLin-heng, GanJing, QuXu, et al. Lane-changing model based on safety potential field theory under the connected and automated vehicles environment[J]. China Journal of Highway and Transport, 2021, 34(6): 184-195.
JiaYan-feng, QuDa-yi, ZhaoZi-xu, et al. Car-following decision-making and model for connected and autonomous vehicles based on safety potential field[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(1): 85-97.
[12]
MaH, AnB, LiL, et al. Anisotropy safety potential field model under intelligent and connected vehicle environment and its application in car-following modeling[J]. Journal of Intelligent and Connected Vehicles, 2023, 6(2): 79-90.
[13]
ZhangY, ShuaiB, ZhangR, et al. Modeling and simulation of driving risk pulse field and its application in car following model[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(8): 8984-9000.
[14]
ShaoY, HanZ, ShiX, et al. Risk-informed longitudinal control in autonomous vehicles: a safety potential field modeling approach[J]. Physica A: Statistical Mechanics and its Applications, 2024, 633: No.129419.
ZhangShuo, KuangShi-qi, ZhaoXuan, et al. Research on global oriented path planning fusion algorithm for intelligent vehicles[J]. Automotive Engineering, 2024, 46(9): 1546-1555.
QuDa-yi, ZhaoZi-xu, JiaYan-feng, et al. Car-following dynamics characteristics and model based on Lennard-Jones potential[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(11): 2549-2557.
QuDa-yi, MengYi-ming, WangTao, et al. Car-following model and safety characteristics of connected autonomous vehicle based on molecular force field[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(6): 33-41.
[21]
DelpianoR, HerreraJ C, LavalJ, et al. A two-dimensional car-following model for two-dimensional traffic flow problems[J]. Transportation Research Part C: Emerging Technologies, 2020, 114: 504-516.
HuLi-wei, HouZhi, ZhaoXue-ting, et al. Improvement of highway traffic risk prediction method based on traffic accident text mining[J]. Journal of Southwest Jiaotong University, 2025, 60(6): 1487-1498.