Specific Scenario Generation Method for Trustworthiness Testing of Autonomous Vehicles Based on Interaction Coding
Source abstract
Abstract
In response to the problems of rough modeling and insufficient coverage of edge interaction scenarios in autonomous driving tests, this paper proposes a scene generation method based on interaction coding. The method constructs a hierarchical parameter system of function–logic–specific scene, uses the time difference of arrival at interaction points (TTC_diff) to determine the critical state of interaction, and realizes the efficient generation and iterative optimization of high-risk scenes. Taking the unprotected left turn at the signal intersection of urban roads as an example, the interaction coding combination is determined in combination with real traffic data, the test scene compatible with OpenSCENARIO is generated, and CARLA0.9.15 is called for test verification. The results show that the interaction intensity is significantly negatively correlated with the trustworthiness score (−0.815), the generated scene has high coverage, and both safety and challenge are taken into account. Compared with the simulated annealing method, the method in this paper performs better in terms of iteration efficiency, scene difficulty control, and score stability, which provides an efficient and reliable test strategy for the trustworthiness evaluation of autonomous driving.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Autonomous Vehicle Technology and Safety · Adversarial Robustness in Machine Learning · Safety Systems Engineering in Autonomy
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The Key Laboratory of Road and Traffic Engineering, Ministry of Education, China Tongji University, Shanghai 201804, China
References (31)
Show source-provided references
1. Automatic Driving Edge Scene Generation Method Based on Scene Dynamics and Reinforcement Learning
2. Driving to safety: How many miles of driving would it take to demonstrate autonomous vehicle reliability?10.1016/j.tra.2016.09.010 ↗
3. Wei, P., and Yuan, M. (2023). Construction of Car Following Critical Scenarios based on Natural Driving Data. China Auto, 39–44.
4. Method of automatic driving testing case generation for AES scene
5. Test Cases Extraction for Autonomous Driving Autonomous Emergency Braking System Critical Scenarios
6. Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment10.1038/s41467-021-21007-8 ↗
7. Dense reinforcement learning for safety validation of autonomous vehicles10.1038/s41586-023-05732-2 ↗
8. Karunakaran, D., Berrio Perez, J.S., and Worrall, S. (2023). Generating Edge Cases for Testing Autonomous Vehicles Using Real-World Data. Sensors, 24.10.3390/s24010108 ↗
9. Dong, Q.J. (2024). Fusion of Virtual and Real Simulation Research on Vehicle Dynamic Interaction in Cut-in Scenarios, Jilin University.
10. Krajewski, R., Moers, T., Nerger, D., and Eckstein, L. (2018, January 4–7). Data-Driven Maneuver Modeling using Generative Adversarial Networks and Variational Autoencoders for Safety Validation of Highly Automated Vehicles. Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, USA.10.1109/ITSC.2018.8569971 ↗
11. Interactive Critical Scenario Generation for Autonomous Vehicles Testing Based on In-depth Crash Data Using Reinforcement Learning10.1109/TIV.2024.3415961 ↗
12. Hao, K., Liu, L., Cui, W., Zhang, J., Yan, S., Pan, Y., and Yang, Z. (2024). Bridging data-driven and knowledge-driven approaches for safety-critical scenario generation in Automated Vehicle Validation. arXiv.10.1109/QRS-C63300.2024.00129 ↗
13. (2021). Road Vehicles-Scenario-Based Safety Evaluation Framework for Automated Driving Systems (Standard No. ISO/DIS 34502).
14. Critical scenario identification for realistic testing of autonomous driving systems10.1007/s11219-022-09604-2 ↗
15. Althoff, M. (2019, January 9–12). Generating Critical Test Scenarios for Automated Vehicles with Evolutionary Algorithms. Proceedings of the 2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France.
16. Wang, J., Pun, A., Tu, J., Manivasagam, S., Sadat, A., Casas, S., Ren, M., and Urtasun, R. (2021, January 20–25). AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00978 ↗
17. Chang, Y., Zhou, S., and Xi, C. (2025, January 5–9). Scenario generation strategies for trustworthiness testing of autonomous vehicles. Proceedings of the Transportation Research Board Annual Meeting (TRB), Washington, DC, USA.
18. Lawitzky, A., Althoff, D., Passenberg, C.F., Tanzmeister, G., Wollherr, D., and Buss, M. (2013, January 23–26). Interactive scene prediction for automotive applications. Proceedings of the 2013 IEEE Intelligent Vehicles Symposium (IV), Gold Coast, QLD, Australia.10.1109/IVS.2013.6629601 ↗
19. Chang, C., Zhang, J., Ge, J., Zhang, Z., Wei, J., and Li, L. (2024). Vista Scenario: Interaction Scenario Engineering for Vehicles with Intelligent Systems for Transport Automation. IEEE Trans. Intell. Veh., 1–17.10.1109/TIV.2024.3400323 ↗
20. Birkemeyer, L., Pett, T., Vogelsang, A., Seidl, C., and Schaefer, I. (2022, January 23–25). Feature-Interaction Sampling for Scenario-based Testing of Advanced Driver Assistance Systems. Proceedings of the 16th International Working Conference on Variability Modelling of Software-Intensive Systems, Florence, Italy.10.1145/3510466.3510474 ↗
21. Full Bayesian conflict-based models for real-time safety evaluation of signalized intersections10.1016/j.aap.2018.09.017 ↗
22. Comparison of Traffic Conflict Indicators for Crash Estimation using Peak Over Threshold Approach10.1177/0361198119841556 ↗
23. Analysis of Autonomous Vehicles Interaction Strategy in Unprotected Turn Scenarios
24. Wang, S., Sun, G., Ma, F., Hu, T., Qin, Q., Song, Y., Zhu, L., and Liang, J. (2024, January 14–18). DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving. Proceedings of the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Abu Dhabi, United Arab Emirates.10.1109/IROS58592.2024.10801623 ↗
25. Yan, S., Zhang, X., Hao, K., Xin, H., Luo, Y., Yang, J., Fan, M., Yang, C., Sun, J., and Yang, Z. (2025). On-Demand Scenario Generation for Testing Automated Driving Systems. arXiv.10.1145/3715722 ↗
26. Finding Critical Scenarios for Automated Driving Systems: A Systematic Mapping Study10.1109/TSE.2022.3170122 ↗
27. Traffic Conflict Characteristics and Influential Factors at Signalized Intersections
28. Tarek, S., and Sany, Z. (1998, January 10–13). Traffic Conflict Models and Standards for Signalized and Unsignalized Intersections. Proceedings of the Canadian Society for Civil Engineering Annual Conference, Halifax, NS, Canada.
29. Trajectory Data Driven Driving Style Recognition for Autonomous Vehicles Using Unsupervised Clustering10.52783/cana.v31.1314 ↗
30. A Review on Driving Styles and Non-Driving Related Tasks in Automated Vehicle
31. Chang, Y.T., Zhang, B.H., and Zhou, S.Q. (2024, January 24–26). Research on scenario-based trustworthiness evaluation method of autonomous vehicles. Proceedings of the Ninth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2024), Guilin, China.10.1117/12.3039710 ↗