自动驾驶汽车仿真测试场景自动生成综述
A Review of Autonomous Vehicle Simulation Test Scenario Automated Generation
摘要: 为了加快高级别自动驾驶汽车的发展与落地，基于场景的虚拟仿真测试变得至关重要。关于自动驾驶汽车的虚拟仿真测试，其测试场景具有多样性、可重复性、可解释性和高生成效率等优势，是验证自动驾驶系统可靠性和安全性的核心手段，已然是目前智能汽车行业的研究热点。本文通过广泛调研测试场景的自动生成方法，以测试场景的技术演进为主线，系统梳理从基础元素提取到智能场景生成的发展脉络，揭示各阶段技术特征及核心突破。要实现场景生成技术的终极目标自动化与测试全覆盖，未来研究应聚焦于：构建基于关键场景参数分布的高维风险估计模型，以精准定位潜在危险区域；融合多技术优势，设计兼顾真实性与效率的混合场景生成框架；并结合交通知识、物理约束与代理模型增量学习，构建“生成–反馈–迭代”的闭环机制，持续提升对高风险场景的覆盖与揭示能力，从而高效支撑自动驾驶系统的验证与安全保障。
Abstract: To accelerate the development and implementation of high-level autonomous vehicles, scenario-based virtual simulation testing has become crucial. Regarding virtual simulation testing for autonomous vehicles, its testing scenarios offer advantages such as diversity, repeatability, explainability, and high generation efficiency. It serves as a core method for verifying the reliability and safety of autonomous driving systems and has emerged as a research hotspot in the smart automotive industry. This paper conducts an extensive review of automated test scenario generation methods, with a focus on the technical evolution of testing scenarios. It systematically outlines the developmental trajectory from basic element extraction to intelligent scenario generation, revealing the technical characteristics and breakthroughs at each stage. To achieve the ultimate goals of automation and full coverage in scenario generation technology, future research should concentrate on: constructing a high-dimensional risk estimation model based on key scenario parameter distributions to precisely identify potential hazardous areas; integrating multiple technical strengths to design a hybrid scenario generation framework that balances realism and efficiency; and combining traffic knowledge, physical constraints, and surrogate model incremental learning to establish a “generate-feedback-iterate” closed-loop mechanism. This will continuously enhance the coverage and exposure of high-risk scenarios, thereby effectively supporting the verification and safety assurance of autonomous driving systems.
文章引用：卢宇航. 自动驾驶汽车仿真测试场景自动生成综述[J]. 计算机科学与应用, 2026, 16(2): 169-181. https://doi.org/10.12677/csa.2026.162049

参考文献

[1] Chan, V.W.S. (2021) Autonomous Vehicle Safety. IEEE Communications Magazine, 59, 4. [Google Scholar] [CrossRef] 
[2] Chougule, A., Chamola, V., Sam, A., Yu, F.R. and Sikdar, B. (2024) A Comprehensive Review on Limitations of Autonomous Driving and Its Impact on Accidents and Collisions. IEEE Open Journal of Vehicular Technology, 5, 142-161. [Google Scholar] [CrossRef] 
[3] Tao, J., Li, Y., Wotawa, F., Felbinger, H. and Nica, M. (2019) On the Industrial Application of Combinatorial Testing for Autonomous Driving Functions. 2019 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), Xi’an, 22-23 April 2019, 234-240. [Google Scholar] [CrossRef] 
[4] Li, L., Huang, W., Liu, Y., Zheng, N. and Wang, F. (2016) Intelligence Testing for Autonomous Vehicles: A New Approach. IEEE Transactions on Intelligent Vehicles, 1, 158-166. [Google Scholar] [CrossRef] 
[5] 王润民, 朱宇, 赵祥模, 等. 自动驾驶测试场景研究进展[J]. 交通运输工程学报, 2021, 21(2): 21-37.
[6] Anderson, J.M., Kalra, N., Stanley, K.D., et al. (2016) Autonomous Vehicle Technology: A Guide for Policy Makers.
https://www.rand.org/pubs/research_reports/RR443-2.html
[7] Klitzke, L., Koch, C., Haja, A. and Köster, F. (2019) Real-World Test Drive Vehicle Data Management System for Validation of Automated Driving Systems. Proceedings of the 5th International Conference on Vehicle Technology and Intelligent Transport Systems, Heraklion, 3-5 May 2019, 171-180. [Google Scholar] [CrossRef] 
[8] Park, S.W., Patil, K., Wilson, W., et al. (2020) Creating Driving Scenarios from Recorded Vehicle Data for Validating Lane Centering System in Highway Traffic. The MathWorks, Inc.
[9] Hsia, P., Samuel, J., Gao, J., Kung, D., Toyoshima, Y. and Chen, C. (1994) Formal Approach to Scenario Analysis. IEEE Software, 11, 33-41. [Google Scholar] [CrossRef] 
[10] Schieben, A., Heesen, M., Schindler, J., Kelsch, J. and Flemisch, F. (2009) The Theater-System Technique. Proceedings of the 1st International Conference on Automotive User Interfaces and Interactive Vehicular Applications, Essen, 21-22 September 2009, 43-46. [Google Scholar] [CrossRef] 
[11] Koskimies, K., Systa, T., Tuomi, J. and Mannisto, T. (1998) Automated Support for Modeling OO Software. IEEE Software, 15, 87-94. [Google Scholar] [CrossRef] 
[12] 邓伟文, 李江坤, 任秉韬, 等. 面向自动驾驶的仿真场景自动生成方法综述[J]. 中国公路学报, 2022, 35(1): 316-333.
[13] International Organization for Standardization (2022) Road Vehicles—Safety of the Intended Functionality: ISO 21448: 2022. ISO.
[14] International Organization for Standardization (2022) Road Vehicles—Test Scenarios for Automated Driving Systems—Vocabulary: ISO 34501: 2022. ISO.
[15] Menzel, T., Bagschik, G. and Maurer, M. (2018) Scenarios for Development, Test and Validation of Automated Vehicles. arXiv: 1801.08598.
https://arxiv.org/abs/1801.08598
[16] International Organization for Standardization (2022) Road Vehicles—Test Scenarios for Automated Driving Systems—Scenario Based Safety Evaluation Framework: ISO 34502: 2022. ISO.
[17] Breitenstein, J., Termohlen, J.A., Lipinski, D., et al. (2021) Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches. arXiv: 2102.05897.
https://arxiv.org/pdf/2102.05897
[18] Han, J., Liang, X., Xu, H,. et al. (2021) SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving. arXiv: 2106.11118.
https://arxiv.org/pdf/2106.11118
[19] Li, K., Chen, K., Wang, H., et al. (2022) CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving. arXiv: 2203.07724.
https://arxiv.org/pdf/2203.07724.
[20] Shi, Y., Shibasaki, R. and Shi, Z. (2008) Towards Automatic Road Mapping by Fusing Vehicle-Borne Multi-Sensor Data. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXXVII, 867-872.
[21] Xu, Y., Xie, Z., Feng, Y. and Chen, Z. (2018) Road Extraction from High-Resolution Remote Sensing Imagery Using Deep Learning. Remote Sensing, 10, Article 1461. [Google Scholar] [CrossRef] 
[22] Xin, J., Zhang, X., Zhang, Z. and Fang, W. (2019) Road Extraction of High-Resolution Remote Sensing Images Derived from Denseunet. Remote Sensing, 11, Article 2499. [Google Scholar] [CrossRef] 
[23] Filin, O., Zapara, A. and Panchenko, S. (2018) Road Detection with EOSResUNet and Post Vectorizing Algorithm. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, 18-22 June 2018, 201-2014. [Google Scholar] [CrossRef] 
[24] Wan, T., Lu, H., Lu, Q. and Luo, N. (2017) Classification of High-Resolution Remote-Sensing Image Using OpenStreetMap Information. IEEE Geoscience and Remote Sensing Letters, 14, 2305-2309. [Google Scholar] [CrossRef] 
[25] Kaur, J. and Singh, J. (2018) An Automated Approach for Quality Assessment of OpenStreetMap Data. 2018 International Conference on Computing, Power and Communication Technologies (GUCON), Greater Noida, 28-29 September 2018, 707-712. [Google Scholar] [CrossRef] 
[26] 张兴宇. 面向自动驾驶仿真测试的虚拟路网环境构建与场景自动生成算法研究及实现[D]: [硕士学位论文]. 西安: 长安大学, 2023.
[27] Geyer, S., Baltzer, M., Franz, B., Hakuli, S., Kauer, M., Kienle, M., et al. (2014) Concept and Development of a Unified Ontology for Generating Test and Use‐case Catalogues for Assisted and Automated Vehicle Guidance. IET Intelligent Transport Systems, 8, 183-189. [Google Scholar] [CrossRef] 
[28] Armand, A., Filliat, D. and Ibanez-Guzman, J. (2014) Ontology-Based Context Awareness for Driving Assistance Systems. 2014 IEEE Intelligent Vehicles Symposium Proceedings, Dearborn, 8-11 June 2014, 227-233. [Google Scholar] [CrossRef] 
[29] Chen, W. and Kloul, L. (2018) An Ontology-Based Approach to Generate the Advanced Driver Assistance Use Cases of Highway Traffic. Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, Seville, 18-20 September 2018, 75-83. [Google Scholar] [CrossRef] 
[30] Bagschik, G., Menzel, T. and Maurer, M. (2018) Ontology Based Scene Creation for the Development of Automated Vehicles. 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, 26-30 June 2018, 1813-1820. [Google Scholar] [CrossRef] 
[31] Aydin, M. and Akbas, M.I. (2021) Identification of Test Scenarios for Autonomous Vehicles Using Fatal Accident Data. SAE International Journal of Connected and Automated Vehicles, 4, 119-132. [Google Scholar] [CrossRef] 
[32] Wassim, G.N., John, D.S. and Mikio, Y. (2007) Pre-Crash Scenario Typology for Crash Avoidance Research.
https://rosap.ntl.bts.gov/view/dot/6281
[33] Nakamura, H., Muslim, H., Kato, R., Prefontaine-Watanabe, S., Nakamura, H., Kaneko, H., et al. (2022) Defining Reasonably Foreseeable Parameter Ranges Using Real-World Traffic Data for Scenario-Based Safety Assessment of Automated Vehicles. IEEE Access, 10, 37743-37760. [Google Scholar] [CrossRef] 
[34] Batsch, F., Daneshkhah, A., Cheah, M., Kanarachos, S. and Baxendale, A. (2019) Performance Boundary Identification for the Evaluation of Automated Vehicles Using Gaussian Process Classification. 2019 IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, 27-30 October 2019, 419-424. [Google Scholar] [CrossRef] 
[35] Li, S., Wang, W., Mo, Z. and Zhao, D. (2018) Cluster Naturalistic Driving Encounters Using Deep Unsupervised Learning. 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, 26-30 June 2018, 1354-1359. [Google Scholar] [CrossRef] 
[36] Ponn, T., Breitfus, M., Yu, X. and Diermeyer, F. (2020) Identification of Challenging Highway-Scenarios for the Safety Validation of Automated Vehicles Based on Real Driving Data. 2020 Fifteenth International Conference on Ecological Vehicles and Renewable Energies (EVER), Monte-Carlo, 10-12 September 2020, 1-10. [Google Scholar] [CrossRef] 
[37] 陈吉清, 舒孝雄, 兰凤崇, 等. 典型危险事故特征的自动驾驶测试场景构建[J]. 华南理工大学学报(自然科学版), 2021, 49(5): 1-8.
[38] Langner, J., Bach, J., Ries, L., Otten, S., Holzapfel, M. and Sax, E. (2018) Estimating the Uniqueness of Test Scenarios Derived from Recorded Real-World-Driving-Data Using Autoencoders. 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, 26-30 June 2018, 1860-1866. [Google Scholar] [CrossRef] 
[39] Nitsche, P., Thomas, P., Stuetz, R. and Welsh, R. (2017) Pre-Crash Scenarios at Road Junctions: A Clustering Method for Car Crash Data. Accident Analysis & Prevention, 107, 137-151. [Google Scholar] [CrossRef] [PubMed]
[40] Lenard, J., Badea-Romero, A. and Danton, R. (2014) Typical Pedestrian Accident Scenarios for the Development of Autonomous Emergency Braking Test Protocols. Accident Analysis & Prevention, 73, 73-80. [Google Scholar] [CrossRef] [PubMed]
[41] de Gelder, E., Hof, J., Cator, E., Paardekooper, J., Camp, O.O.d., Ploeg, J., et al. (2022) Scenario Parameter Generation Method and Scenario Representativeness Metric for Scenario-Based Assessment of Automated Vehicles. IEEE Transactions on Intelligent Transportation Systems, 23, 18794-18807. [Google Scholar] [CrossRef] 
[42] Jenkins, I.R., Gee, L.O., Knauss, A., Yin, H. and Schroeder, J. (2018) Accident Scenario Generation with Recurrent Neural Networks. 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, 4-7 November 2018, 3340-3345. [Google Scholar] [CrossRef] 
[43] Beglerovic, H., Stolz, M. and Horn, M. (2017) Testing of Autonomous Vehicles Using Surrogate Models and Stochastic Optimization. 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), Yokohama, 16-19 October 2017, 1-6. [Google Scholar] [CrossRef] 
[44] Qin, X., Aréchiga, N., Best, A., et al. (2021) Automatic Testing with Reusable Adversarial Agents. arXiv: 1910.13645.
https://arxiv.org/pdf/1910.13645
[45] Ding, W., Wang, W. and Zhao, D. (2019) A Multi-Vehicle Trajectories Generator to Simulate Vehicle-To-Vehicle Encountering Scenarios. 2019 International Conference on Robotics and Automation (ICRA), Montreal, 20-24 May 2019, 4255-4261. [Google Scholar] [CrossRef] 
[46] Ding, W., Chen, B., Xu, M. and Zhao, D. (2020) Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, 24 October 2020-24 January 2021, 2243-2250. [Google Scholar] [CrossRef] 
[47] Demetriou, A., Alfsvag, H., Rahrovani, S., et al. (2020) A Deep Learning Framework for Generation and Analysis of Driving Scenario Trajectories. arXiv: 2007.14524.
https://arxiv.org/pdf/2007.14524
[48] Krajewski, R., Moers, T., Nerger, D. and Eckstein, L. (2018) Data-Driven Maneuver Modeling Using Generative Adversarial Networks and Variational Autoencoders for Safety Validation of Highly Automated Vehicles. 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, 4-7 November 2018, 2383-2390. [Google Scholar] [CrossRef] 
[49] Xia, Q., Duan, J., Gao, F., Hu, Q. and He, Y. (2018) Test Scenario Design for Intelligent Driving System Ensuring Coverage and Effectiveness. International Journal of Automotive Technology, 19, 751-758. [Google Scholar] [CrossRef] 
[50] Gao, F., Duan, J., Han, Z. and He, Y. (2020) Automatic Virtual Test Technology for Intelligent Driving Systems Considering Both Coverage and Efficiency. IEEE Transactions on Vehicular Technology, 69, 14365-14376. [Google Scholar] [CrossRef] 
[51] Rocklage, E., Kraft, H., Karatas, A. and Seewig, J. (2017) Automated Scenario Generation for Regression Testing of Autonomous Vehicles. 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), Yokohama, 16-19 October 2017, 476-483. [Google Scholar] [CrossRef] 
[52] Shu, H., Lv, H., Liu, K., Yuan, K. and Tang, X. (2021) Test Scenarios Construction Based on Combinatorial Testing Strategy for Automated Vehicles. IEEE Access, 9, 115019-115029. [Google Scholar] [CrossRef] 
[53] 修海林. 有条件自动驾驶汽车测试与综合评价研究[D]: [硕士学位论文]. 重庆: 重庆大学, 2019.
[54] Feng, S., Yan, X., Sun, H., Feng, Y. and Liu, H.X. (2021) Intelligent Driving Intelligence Test for Autonomous Vehicles with Naturalistic and Adversarial Environment. Nature Communications, 12, Article No. 748. [Google Scholar] [CrossRef] [PubMed]
[55] Zhao, D., Lam, H., Peng, H., Bao, S., LeBlanc, D.J., Nobukawa, K., et al. (2017) Accelerated Evaluation of Automated Vehicles Safety in Lane-Change Scenarios Based on Importance Sampling Techniques. IEEE Transactions on Intelligent Transportation Systems, 18, 595-607. [Google Scholar] [CrossRef] [PubMed]
[56] Feng, S., Feng, Y., Sun, H., Zhang, Y. and Liu, H.X. (2022) Testing Scenario Library Generation for Connected and Automated Vehicles: An Adaptive Framework. IEEE Transactions on Intelligent Transportation Systems, 23, 1213-1222. [Google Scholar] [CrossRef] 
[57] Xia, Q., Chai, Y., Lv, H. and Shu, H. (2021) Research on Accelerated Testing of Cut-In Condition of Electric Automated Vehicles Based on Monte Carlo Simulation. Sustainability, 13, Article 12776. [Google Scholar] [CrossRef] 
[58] 邢星宇, 吴旭阳, 刘力豪, 等. 基于目标优化的自动驾驶决策规划系统自动化测试方法[J]. 同济大学学报(自然科学版), 2021, 49(8): 1162-1169.
[59] Duan, J., Gao, F. and He, Y. (2022) Test Scenario Generation and Optimization Technology for Intelligent Driving Systems. IEEE Intelligent Transportation Systems Magazine, 14, 115-127. [Google Scholar] [CrossRef] 
[60] Sun, J., Zhou, H., Xi, H., Zhang, H. and Tian, Y. (2022) Adaptive Design of Experiments for Safety Evaluation of Automated Vehicles. IEEE Transactions on Intelligent Transportation Systems, 23, 14497-14508. [Google Scholar] [CrossRef] 
[61] 朱冰, 范天昕, 赵健, 等. 基于危险边界搜索的自动驾驶系统加速测试方法[J]. 吉林大学学报(工学版), 2023, 53(3): 704-712.
[62] Huang, Z., Lam, H. and Zhao, D. (2017) An Accelerated Testing Approach for Automated Vehicles with Background Traffic Described by Joint Distributions. 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), Yokohama, 16-19 October 2017, 933-938. [Google Scholar] [CrossRef] 
[63] Koren, M., Alsaif, S., Lee, R. and Kochenderfer, M.J. (2018) Adaptive Stress Testing for Autonomous Vehicles. 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, 26-30 June 2018, 1-7. [Google Scholar] [CrossRef] 
[64] Chen, B., Chen, X., Wu, Q. and Li, L. (2022) Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarios. IEEE Transactions on Intelligent Transportation Systems, 23, 10333-10342. [Google Scholar] [CrossRef]