All Issue

2025 Vol.43, Issue 6 Preview Page

Article

A Two-Dimensional Lane-Changing Model with Asymmetric Driving Behavior

비대칭 주행 행태를 반영한 2차원 차로 변경 모델

Sujae JEON1
,
Yeeun KIM2
,
Hwasoo YEO3*
전 수제1
,
김 예은2
,
여 화수3*
1Ph.D Course, Department of Civil and Environmental Engineering, KAIST, Daejeon 34141, Korea
2Postdoctoral Associate, Civil, Environmental and Construction Engineering, University of Central Florida, Florida 32816, USA
3Professor, Department of Civil and Environmental Engineering, KAIST, Daejeon 34141, Korea
1한국과학기술원 건설및환경공학과 박사과정
2중앙플로리다대학교 토목환경건설공학과 박사후연구원
3한국과학기술원 건설및환경공학과 교수
*Corresponding Author
31 December 2025. pp. 815-829
PDF XML Citation
Abstract

In recent years, traffic simulation has increasingly required models that capture not only safety and efficiency but also human-like driving behavior. While numerous models have been proposed to reflect human driving characteristicsm most have focused on one-dimensional car-following, considering only longitudinal movements. However, they lack smooth integration with lane-changing behavior, which restricts their ability to reproduce complex and context-aware driving behaviors. Therefore, this study proposes a two-dimensional driving behavior model that incorporates human-like characteristics. The model calculates both longitudinal and lateral accelerations using relational variables derived from an asymmetric repulsive force model. For longitudinal control, a weight-based approach is employed to simultaneously account for the influence of multiple surrounding vehicles, enabling more complex and human-like driving behavior. For lateral control, the model adopts a spring- mass-damper system, in which the spring coefficient is dynamically adjusted based on surrounding traffic conditions. This allows for flexible responses such as lane-change abandonment or timing adjustments. Simulation results show that the proposed model enables smoother behavior transitions and reduces the impact on surrounding traffic, while also reproducing adaptive behaviors such as lane-change abandonment under unsafe conditions.

Keywords
autonomous driving behavior
human-likeness
lane-changing
microscopic simulation
two-dimensional driving model

최근 교통 시뮬레이션에서는 안전성과 효율성뿐만 아니라 실제 운전자와 유사한 주행 행태를 재현할 수 있는 모델에 대한 수요가 증가하고 있다. 기존의 다양한 모델들이 인간 운전자의 특성을 반영하기 위해 제안되었으나, 대부분은 1차원 차량 추종에 초점을 맞추어 종방향 움직임만을 고려하였다. 그러나 이러한 모델들은 차로 변경 행태와의 매끄러운 통합이 부족하여 복잡하고 상황 인지적인 주행 행태를 재현하는 데 한계가 있다. 이에 본 연구에서는 인간과 유사한 특성을 반영한 2차원 주행 행태 모델을 제안한다. 제안된 모델은 비대칭 반발력 모델에서 도출된 관계 변수를 활용하여 종방향 및 횡방향 가속도를 종합적으로 계산한다. 종방향 제어에서는 가중치 기반 접근법을 적용하여 다수의 주변 차량이 미치는 영향을 동시에 고려함으로써 보다 복잡하고 인간적인 주행 행태를 구현한다. 횡방향 제어에서는 주변 교통 상황에 따라 스프링 계수를 동적으로 조정하는 스프링-질량-댐퍼 시스템을 채택하여, 차로 변경 포기나 시점 조정과 같은 유연한 대응이 가능하다. 시뮬레이션 결과, 제안된 모델은 주행 행태 전환을 더욱 부드럽게 하고 주변 교통에 미치는 영향을 줄이며, 안전하지 않은 상황에서의 차로 변경 포기와 같은 적응적 행태를 재현할 수 있음을 보여준다.

키워드
자율주행 행태
인간 운전자 주행 행태
미시적 교통 시뮬레이션
2차원 주행 모델
차로 변경
References
1

Delpiano R., Herrera J. C., Laval J., Coeymans J. E. (2020), A Two-Dimensional Car-Following Model for Two-Dimensional Traffic Flow Problems, Transp. Res. C Emerg. Technol., 114, 504-516.

10.1016/j.trc.2020.02.025
2

El Sallab A., Abdou M., Perot E., Yogamani S. (2017), Deep Reinforcement Learning Framework for Autonomous Driving, arXiv Preprint, arXiv:1704.02532.

10.2352/ISSN.2470-1173.2017.19.AVM-023
3

Fu R., Lu Y., Zhang Y., Zhou Y., Wang J. (2019), Human-Like Car-Following Model for Autonomous Vehicles Considering the Cut-In Behavior of Other Vehicles in Mixed Traffic, Accid. Anal. Prev., 132, 105260.

10.1016/j.aap.2019.105260
4

Kim Y., Yeo H. (2024), Asymmetric Repulsive Force Model: A New Car-Following Model with Psycho-Physical Characteristics, Transp. Res. C Emerg. Technol., 161, 104571.

10.1016/j.trc.2024.104571
5

Ozbay K., Yang H., Bartin B., Mudigonda S. (2008), Derivation and Validation of New Simulation-Based Surrogate Safety Measure, Transp. Res. Rec., 2083(1), 105-113.

10.3141/2083-12
6

Qi H., Lin J., Ying Y., Zhang J. (2022), Stochastic Two-Dimensional Car-Following Model by Stochastic Differential Equation, Proc. IEEE Int. Conf. Intell. Transp. Syst. (ITSC), 224-229.

10.1109/ITSC55140.2022.9921829
7

Sharath M. N., Velaga N. R. (2020), Enhanced Intelligent Driver Model for Two-Dimensional Motion Planning in Mixed Traffic, Transp. Res. C Emerg. Technol., 120, 102780.

10.1016/j.trc.2020.102780
8

Toledo T., Zohar D. (2007), Modeling Duration of Lane Changes, Transportation Research Record, 1999(1), 71-78.

10.3141/1999-08
9

Treiber M., Hennecke A., Helbing D. (2000), Congested Traffic States in Empirical Observations and Microscopic Simulations, Physical Review E, 62(2), 1805.

10.1103/PhysRevE.62.1805
10

Xie D. F., Fang Z. Z., Jia B., He Z. (2019), A Data-Driven Lane-Changing Model Based on Deep Learning, Transp. Res. C Emerg. Technol., 106, 41-60.

10.1016/j.trc.2019.07.002
11

Xu D., Ding Z., He X., Zhao H., Moze M., Aioun F. et al. (2020), Learning From Naturalistic Driving Data for Human-Like Autonomous Highway Driving, IEEE Trans. Intell. Transp. Syst., 22(12), 7341-7354.

10.1109/TITS.2020.3001131
12

Yang M., Wang X., Quddus M. (2019), Examining lane change gap acceptance, duration and impact using naturalistic driving data, Transportation research part C: emerging technologies, 104, 317-331.

10.1016/j.trc.2019.05.024
13

Yeo H., Skabardonis A., Halkias J., Colyar J., Alexiadis V. (2008), Oversaturated Freeway Flow Algorithm for Use in Next Generation Simulation, Transp. Res. Rec., 2088(1), 68-79.

10.3141/2088-08
14

Yu H., Tseng H. E., Langari R. (2018), A Human-Like Game Theory-Based Controller for Automatic Lane Changing, Transp. Res. C Emerg. Technol., 88, 140-158.

10.1016/j.trc.2018.01.016
15

Zhang J., Chang C., Zeng X., Li L. (2022), Multi-Agent DRL-Based Lane Change with Right-Of-Way Collaboration Awareness, IEEE Trans. Intell. Transp. Syst., 24(1), 854-869.

10.1109/TITS.2022.3216288
16

Zhang T., Zhan J., Shi J., Xin J., Zheng N. (2023), Human-Like Decision-Making of Autonomous Vehicles in Dynamic Traffic Scenarios, IEEE/CAA J. Autom. Sin., 10(10), 1905-1917.

10.1109/JAS.2023.123696
17

Zhang X., Sun J., Qi X., Sun J. (2019), Simultaneous Modeling of Car-Following and Lane-Changing Behaviors Using Deep Learning, Transp. Res. C Emerg. Technol., 104, 287-304.

10.1016/j.trc.2019.05.021
18

Zhu M., Wang X., Wang Y. (2018), Human-Like Autonomous Car-Following Model with Deep Reinforcement Learning, Transp. Res. C Emerg. Technol., 97, 348-368.

10.1016/j.trc.2018.10.024
Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 43
  • No :6
  • Pages :815-829
  • Received Date : 2025-08-25
  • Revised Date : 2025-09-12
  • Accepted Date : 2025-09-28
  • DOI :https://doi.org/10.7470/jkst.2025.43.6.815
Journal Informaiton Journal of Korean Society of Transportation Journal of Korean Society of Transportation
Archives
: 2015 Vol.34~
  • NRF
  • KOFST
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close