Situation-Aware Causal Inference-Driven Vehicle Lane-Changing Decision-Making
Source abstract
Abstract
For the decision-making challenge of ensuring vehicle lane-changing safety, this study proposes a context-dependent causal inference-based model for safe lane changes. Emphasizing multi-vehicle interactions within dynamic traffic scenarios, we construct a three-layer decision-making framework that relies on real-time data collection of speed, acceleration, and spacing information from both the target vehicle and adjacent-lane vehicles. The framework consists of (1) a context-aware layer that extracts standardized dynamic features; (2) an attention mechanism layer that dynamically assigns weights to critical risk factors; and (3) a counterfactual causal reasoning layer where lane-changing risks are quantified through virtual interventions, with multi-objective safety strategies optimized via particle swarm algorithms. The simulation results indicate significant enhancements in high-density traffic conditions. When compared to traditional safety distance models and built-in models from simulation software (SUMO v1.18.0), the proposed model achieves reductions in average conflict counts by 63.0% (from 12.7 to 4.7 instances) and by 37.3% (from 7.5 to 4.7 instances), respectively. Additionally, lane-changing durations are reduced by 10.9% (from 5.5 to 4.9 s) and by 31.9% (from 7.2 to 4.9 s), while fluctuations in risk values decrease by 53.3% (from 0.75 to 0.35) and by 36.4% (from 0.55 to 0.35), respectively. The experimental validation confirms that the integration of dynamic safety distance computation with causal reasoning significantly enhances decision-making robustness in complex scenarios through coordinated risk quantification and multi-objective optimization
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Autonomous Vehicle Technology and Safety · Traffic and Road Safety · Traffic control and management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic and Control Engineering, Chang’an University, Xi’an 710061, China
College of Electrical and Control Engineering, North China University of Technology, Beijing 100144, China
Funding
National Key Research and Development Program: Autonomous Transportation System Interoperability Technology
References (30)
Show source-provided references
1. (2025, January 17). Beijing Municipal People’s Government, from Now on Four Types of Traffic Law Will Be Snapped, Available online: https://www.beijing.gov.cn/fuwu/bmfw/sy/jrts/202501/t20250117_3991435.html.
2. Peng, T., Su, L., Zhang, R., Guan, Z., Zhao, H., Qiu, Z., Zong, C., and Xu, H. (2020). A new safe lane-change trajectory model and collision avoidance control method for automatic driving vehicles. Expert Syst. Appl., 141.10.1016/j.eswa.2019.112953 ↗
3. Yao, J., Chen, G., and Gao, Z. (2021). Target vehicle selection algorithm for adaptive cruise control based on lane-changing intention of preceding vehicle. Chin. J. Mech. Eng., 34.10.1186/s10033-021-00650-8 ↗
4. Ma, C., and Li, D. (2023). A review of vehicle lane change research. Phys. A Stat. Mech. Its Appl., 626.10.1016/j.physa.2023.129060 ↗
5. Simultaneous modeling of car-following and lane-changing behaviors using deep learning10.1016/j.trc.2019.05.021 ↗
6. Wu, J., Wen, H., and Qi, W. (2020). A new method of temporal and spatial risk estimation for lane change considering conventional recognition defects. Accid. Anal. Prev., 148.10.1016/j.aap.2020.105796 ↗
7. Li, M., Li, Z., Xu, C., and Liu, T. (2020). Short-term prediction of safety and operation impacts of lane changes in oscillations with empirical vehicle trajectories. Accid. Anal. Prev., 135.10.1016/j.aap.2019.105345 ↗
8. Das, A., Khan, M.N., and Ahmed, M.M. (2020). Detecting lane change maneuvers using SHRP2 naturalistic driving data: A comparative study machine learning techniques. Accid. Anal. Prev., 142.10.1016/j.aap.2020.105578 ↗
9. Guo, J., and Harmati, I. (2022). Lane-changing decision modelling in congested traffic with a game theory-based decomposition algorithm. Eng. Appl. Artif. Intell., 107.10.1016/j.engappai.2021.104530 ↗
10. Guo, H., Keyvan-Ekbatani, M., and Xie, K. (2022). Lane change detection and prediction using real-world connected vehicle data. Transp. Res. Part C Emerg. Technol., 142.10.1016/j.trc.2022.103785 ↗
11. Gao, H., Zhao, M., Zheng, X., Wang, C., Zhou, L., Wang, Y., Ma, L., Cheng, B., Wu, Z., and Li, Y. (2024). An improved hierarchical deep reinforcement learning algorithm for multi-intelligent vehicle lane change. Neurocomputing, 609.10.1016/j.neucom.2024.128482 ↗
12. A dynamic lane-changing trajectory planning model for automated vehicles10.1016/j.trc.2018.06.007 ↗
13. Wang, C., Sun, Q., Li, Z., and Zhang, H. (2020). Human-like lane change decision model for autonomous vehicles that considers the risk perception of drivers in mixed traffic. Sensors, 20.10.3390/s20082259 ↗
14. Luo, Q., Zang, X., Cai, X., Gong, H., Yuan, J., and Yang, J. (2021). Vehicle lane-changing safety pre-warning model under the environment of the vehicle networking. Sustainability, 13.10.3390/su13095146 ↗
15. Li, L., Gan, J., Zhou, K., Qu, X., and Ran, B. (2020). A novel lane-changing model of connected and automated vehicles: Using the safety potential field theory. Phys. A Stat. Mech. Its Appl., 559.10.1016/j.physa.2020.125039 ↗
16. He, Y., Feng, J., Wei, K., Cao, J., Chen, S., and Wan, Y. (2023). Modeling and simulation of lane-changing and collision avoiding autonomous vehicles on superhighways. Phys. A Stat. Mech. Its Appl., 609.10.1016/j.physa.2022.128328 ↗
17. Dynamic lane-changing trajectory planning for autonomous vehicles based on discrete global trajectory10.1109/TITS.2021.3083541 ↗
18. Wu, J., Chen, X., Bie, Y., and Zhou, W. (2023). A co-evolutionary lane-changing trajectory planning method for automated vehicles based on the instantaneous risk identification. Accid. Anal. Prev., 180.10.1016/j.aap.2022.106907 ↗
19. Kim, W., Yang, H., and Kim, J. (2023). Blind Spot Detection Radar System Design for Safe Driving of Smart Vehicles. Appl. Sci., 13.10.3390/app13106147 ↗
20. Muzammel, M., Yusoff, M.Z., Saad, M.N.M., Sheikh, F., and Awais, M.A. (2022). Blind-Spot Collision Detection System for Commercial Vehicles Using Multi Deep CNN Architecture. Sensors, 22.10.3390/s22166088 ↗
21. Yang, J., Xu, Z., Lai, H., Chen, H., Kong, S., Wu, Y., and Yang, H. (2024). Intelligent EC Rearview Mirror: Enhancing Driver Safety with Dynamic Glare Mitigation via Cloud Edge Collaboration. arXiv.
22. Qi, H. (2024). Research on Automatic Driving Safety Decision-Making Method Based on Counterfactual Reasoning. [Master’s Thesis, Shandong Jiaotong University].
23. Multi-task allocation of heterogeneous Unmanned Aerial Vehicles based on hybrid strategy multi-objective particle swarm optimization
24. Liu, Y.-T., Gu, J.-J., and Zhou, Q. (2025). City travel traffic prediction method based on structure of causal model. Comput. Sci., 1–14. Available online: http://kns.cnki.net/kcms/detail/50.1075.TP.20250310.1631.021.html.
25. Cao, Y., Shang, G., Arnoud, V., Chen, J., and Chai, L. (2025). Based on pattern matching attention mechanism of vehicle track prediction. China J. Highw. Transp., 1–15. Available online: http://kns.cnki.net/kcms/detail/61.1313.U.20250514.1522.002.html.
26. Solving multi-agent routing problems using deep attention mechanisms10.1109/TITS.2020.3009289 ↗
27. Multi-agent deep reinforcement learning to manage connected autonomous vehicles at tomorrow’s intersections10.1109/TVT.2022.3169907 ↗
28. Federated multi-agent deep reinforcement learning for resource allocation of vehicle-to-vehicle communications10.1109/TVT.2022.3173057 ↗
29. Press, W.H., Teukolsky, S.A., Vetterling, W.T., and Flannery, B.P. (2007). Numerical Recipes: The Art of Scientific Computing, Cambridge University Press. [3rd ed.].
30. A Potential Field-Based Approach for Safe Vehicle Following Control