Risk assessment in autonomous driving: a comprehensive survey of risk sources, methodologies, and system architectures

Abstract

As autonomous driving technology advances from assisted to higher levels of autonomy, the complexity of operational environments and the uncertainty of driving tasks continue to increase, posing significant challenges to system safety. The key to ensuring safety lies in conducting comprehensive and rational risk assessments to identify potential hazards and inform policy optimization. Consequently, risk assessment has emerged as a critical component for ensuring the safe operation of higher-level autonomous driving systems. This review focuses on research into risk assessment for autonomous driving. It systematically surveys the state-of-the-art literature from three key perspectives: risk sources, assessment methodologies, data foundations, and system architectures. For each perspective, the paper provides an in-depth analysis of representative technical approaches, modeling principles, and typical application scenarios, while summarizing their research characteristics and applicable boundaries. Finally, this paper synthesizes the three fundamental challenges that persist in current research and further explores future directions and development opportunities. It provides a theoretical foundation and methodological references for the development of autonomous driving systems that exhibit high safety and reliability.

Keywords

Autonomous driving / Risk assessment / Safety evaluation

References

[1] YangS., HuangY., LiL., FengS., NaX., ChenH., KhajepourA.. How to guarantee driving safety for autonomous vehicles in a real-world environment: a perspective on self-evolution mechanisms. IEEE Intell. Transp. Syst. Mag., 2024, 16(2): 41-54

[2] J. Cheng, Y. Chen, Q. Chen, Pluto: pushing the limit of imitation learning-based planning for autonomous driving (2024). arXiv preprint arXiv:2404.14327

[3] CaoZ., JiangK., ZhouW., XuS., PengH., YangD.. Continuous improvement of self-driving cars using dynamic confidence-aware reinforcement learning. Nat. Mach. Intell., 2023, 5(2): 145-158.

[4] DingW., XuC., AriefM., LinH., LiB., ZhaoD.. A survey on safety-critical driving scenario generation—a methodological perspective. IEEE Trans. Intell. Transp. Syst., 2023, 24(7): 6971-6988.

[5] YangS., LiS., HuangY., ChenH.. A safe self-evolution algorithm for autonomous driving based on data-driven risk quantification model. Accid. Anal. Prev., 2025, 214. 107941

[6] YuW., ZhaoC., WangH., LiuJ., MaX., YangY., LiJ., WangW., HuX., ZhaoD.. Online legal driving behavior monitoring for self-driving vehicles. Nat. Commun., 2024, 151. 408

[7] ZhaoR., WangK., XiaoY., GaoF., GaoZ.. Leveraging Monte Carlo dropout for uncertainty quantification in real-time object detection of autonomous vehicles. IEEE Access, 2024, 12: 33384-33399.

[8] C. Hu, B. Du, Z. Wang, Q. Zhang, R. Zhang, H. Gao, Perceptual uncertainty-aware motion planning for autonomous driving based on adaptive heuristic reinforcement learning. IEEE Trans. Intell. Transp. Syst. (2025)

[9] CatakF.O., YueT., AliS.. Prediction surface uncertainty quantification in object detection models for autonomous driving. 2021 IEEE International Conference on Artificial Intelligence Testing (AITest), 2021, Los Alamitos. IEEE. 93100.

[10] LandgrafS., HillemannM., KaplerT., UlrichM.. Efficient multi-task uncertainties for joint semantic segmentation and monocular depth estimation. DAGM German Conference on Pattern Recognition, 2024, Berlin. Springer. 348364

[11] H. Huang, C. Chen, J.-P. Monteuuis, J. Petit, F. Miao, Uncertainty quantification for collaborative object detection under adversarial attacks (2025). arXiv preprint arXiv:2502.02537

[12] H. Gao, C. Wang, R. Niu, X. Fang, J. Chen, Y. Sun, H. Jin, D. Wang, Driving risk assessment for intelligent vehicles based on entropy-informed graph neural networks and Gaussian distributions. IEEE Trans. Neural Netw. Learn. Syst. (2025)

[13] ZhouJ., OlofssonB., FriskE.. Interaction-aware motion planning for autonomous vehicles with multi-modal obstacle uncertainty predictions. IEEE Trans. Intell. Veh., 2023, 9(1): 1305-1319.

[14] Z. Xiong, S. Liu, N. Helgesen, J. Johnander, P.-E. Forssen, Catplan: loss-based collision prediction in end-to-end autonomous driving (2025). arXiv preprint arXiv:2503.07425

[15] HoelC.-J., WolffK., LaineL.. Ensemble quantile networks: uncertainty-aware reinforcement learning with applications in autonomous driving. IEEE Trans. Intell. Transp. Syst., 2023, 24(6): 6030-6041.

[16] KirişciM.. Interval-valued fermatean fuzzy based risk assessment for self-driving vehicles. Appl. Soft Comput., 2024, 152. 111265

[17] MbelekaniN.Y., BenglerK.. irisk: towards responsible ai-powered automated driving by assessing crash risk and prevention. Electronics, 2025, 1412. 2433

[18] H. Liao, H. Kong, B. Rao, B. Wang, C. Wang, G. Yu, Y. Huang, R. Tang, C. Xu, Z. Li, Safecast: risk-responsive motion forecasting for autonomous vehicles (2025). arXiv preprint arXiv:2503.22541

[19] HuJ., YaoM., WuL., LiH., FeiT., ZhengJ.. Srd: balancing safety and optimality based on rss and reinforcement learning for autonomous driving. 2024 7th International Symposium on Autonomous Systems (ISAS), 2024, Los Alamitos. IEEE. 16

[20] X. Cai, S. Ancha, L. Sharma, P.R. Osteen, B. Bucher, S. Phillips, J. Wang, M. Everett, N. Roy, J.P. How, Evora: deep evidential traversability learning for risk-aware off-road autonomy. IEEE Trans. Robot. (2024)

[21] K. Wang, Y. Chen, Q. Liu, X. Li, X. Gao, Dynamic residual safe reinforcement learning for multi-agent safety-critical scenarios decision-making (2025). arXiv preprint arXiv:2504.06670

[22] WeiZ., ZhouH., ZhouR.. Risk and complexity assessment of autonomous vehicle testing scenarios. Appl. Sci., 2024, 1421. 9866

[23] WangK., QuD., YangY., DaiS., WangT.. Risk-quantification method for car-following behavior considering driving-style propensity. Appl. Sci., 2024, 145. 1746

[24] S. Su, Y. Li, S. He, S. Han, C. Feng, C. Ding, F. Miao, Uncertainty quantification of collaborative detection for self-driving (2022). arXiv preprint arXiv:2209.08162

[25] Q. Liu, H. Huang, S. Zhao, L. Shi, S. Ahn, X. Li, Risknet: interaction-aware risk forecasting for autonomous driving in long-tail scenarios (2025). arXiv preprint arXiv:2504.15541

[26] R. Zhang, C. Sun, R. Valiollahimehrizi, K. Czarnecki, A. Khajepour, An uncertainty-aware, dual-tiered decision-making method for safe autonomous driving. IEEE Trans. Intell. Transp. Syst. (2024)

[27] LuJ., CuiC., MaY., BeraA., WangZ.. Quantifying uncertainty in motion prediction with variational Bayesian mixture. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 20241542815437

[28] K. Stachowicz, S. Levine, Racer: epistemic risk-sensitive rl enables fast driving with fewer crashes (2024). arXiv preprint arXiv:2405.04714

[29] LiK., ChenK., WangH., HongL., YeC., HanJ., ChenY., ZhangW., XuC., YeungD.-Y., et al.. Coda: a real-world road corner case dataset for object detection in autonomous driving. European Conference on Computer Vision, 2022, Berlin. Springer. 406423

[30] T. Puphal, V. Ramtekkar, K. Nishimiya, Risk-based filtering of valuable driving situations in the waymo open motion dataset (2025). arXiv preprint arXiv:2506.23433

[31] Y. Li, L. Zhang, X. Wang, H. Liu, B. Liang, Deepmf: deep motion factorization for closed-loop safety-critical driving scenario simulation (2024). arXiv preprint arXiv:2412.17487

[32] J. Zhao, D. Du, X. Yu, H. Li, Risk scenario generation for autonomous driving systems based on causal Bayesian networks (2024). arXiv preprint arXiv:2405.16063

[33] Y. Ding, X. Zhao, P. Yan, Y. Yao, H. Yang, Safety efficiency assessment of online car-hailing drivers based on the nonparametric method. Transp. Lett., 1–11 (2025)

[34] LeiJ., NiZ., PengZ., HuH., HongJ., FangX., YiC., RenC., WasayeM.A.. An intelligent network framework for driver distraction monitoring based on res-se-cnn. Sci. Rep., 2025, 151. 6916

[35] R. Yao, Y. Wang, H. Liu, R. Yang, Z. Peng, L. Zhu, J. Ma, Calmm-drive: confidence-aware autonomous driving with large multimodal model (2024). arXiv preprint arXiv:2412.04209

[36] LiuT., WangC., YinZ., MiZ., XiongX., GuoB.. Complexity quantification of driving scenarios with dynamic evolution characteristics. Entropy, 2024, 2612. 1033

[37] ZhaoN., HeQ., LiuR., SunM.. Research on the grading of driving safety risks under low visibility conditions on expressways based on driving simulation. International Conference on Artificial Intelligence and Autonomous Transportation, 2024, Berlin. Springer. 487494

[38] K. Wang, Q. Ma, C. Shen, J. Lu, Application of uncertainty to out-of-distribution detection for autonomous driving perception safety. IEEE Trans. Intell. Transp. Syst. (2025)

[39] Sathyamangalam ImranM.I.I., AwasthiS.S., KhayyatM., ArrigoniS., BraghinF.. Virtual validation and uncertainty quantification of an adaptive model predictive controller-based motion planner for autonomous driving systems. Future Transp., 2024, 4(4): 1537-1558.

[40] PengL., LiB., YuW., YangK., ShaoW., WangH.. Sotif entropy: online sotif risk quantification and mitigation for autonomous driving. IEEE Trans. Intell. Transp. Syst., 2023, 25(2): 1530-1546.

[41] B. Yao, S. Huang, P. Han, J. Lin, S. Duan, C. Liu, Sotif-oriented risk assessment: a multi-dimensional model for autonomous driving. IEEE Robot. Autom. Lett. (2024)

[42] CârlanC., CarlsonN., DwyerC., HirannaiahM., WagnerM.. The sotif meta-algorithm: quantitative analyses of the safety of autonomous behaviors. 2024 IEEE 35th International Symposium on Software Reliability Engineering Workshops (ISSREW), 2024, Los Alamitos. IEEE. 191198.

[43] LeeJ., CruzM.V.D., SturmR.. Quantifying integrated safety risk in highly automated vehicles: a probabilistic approach to perception sensor uncertainty. J. Transp. Eng., 2025, 19. 100310

[44] K. Moller, L. Schwarzmeier, J. Betz, From shadows to safety: occlusion tracking and risk mitigation for urban autonomous driving (2025). arXiv preprint arXiv:2504.01408

[45] AissaniS., OmarM., HamouidK.. Failure detection under sensing uncertainty in vehicular systems. 4th International Conference on Computer Technologies, 2025

[46] WangR., YangT., LiangC., WangM., CiY.. Reliable autonomous driving environment perception: uncertainty quantification of semantic segmentation. J. Transp. Eng., Part A, Syst., 2025, 1513. 04024117

[47] LiD., LiuB., HuangZ., HaoQ., ZhaoD., TianB.. Safe motion planning for autonomous vehicles by quantifying uncertainties of deep learning-enabled environment perception. IEEE Trans. Intell. Veh., 2023, 9(1): 2318-2332.

[48] WangK., WangY., LiuB., ChenJ.. Quantification of uncertainty and its applications to complex domain for autonomous vehicles perception system. IEEE Trans. Instrum. Meas., 2023, 72: 1-17

[49] X. Xing, T. Jia, J. Chen, L. Xiong, Z. Yu, An ontology-based method to identify triggering conditions for perception insufficiency of autonomous vehicles (2022). arXiv preprint arXiv:2210.08724

[50] Y. Zhang, G. Shen, W. Zhang, K. Ning, R. Jiang, X. Kong, Uncertainty-aware traffic accident risk prediction via multi-view hypergraph contrastive learning. Inf. Fusion 103331 (2025)

[51] W. Hu, Z. Deng, Y. Yang, P. Zhang, K. Cao, D. Chu, B. Zhang, D. Cao, Socially game-theoretic lane-change for autonomous heavy vehicle based on asymmetric driving aggressiveness. IEEE Trans. Veh. Technol. (2025)

[52] Z. Chen, W. Liu, L. Xiong, Z. Yu, C. Tang, Occlusion-aware trajectory planning with quantified risk constraint for deadlock mitigation in autonomous driving. IEEE Trans. Intell. Transp. Syst. (2025)

[53] LiG., LiZ., KnoopV.L., LintH.. Unravelling uncertainty in trajectory prediction using a non-parametric approach. Transp. Res., Part C, Emerg. Technol., 2024, 163. 104659

[54] ZhouZ., ShiJ., ZhangH., ChenQ., WangX., ChenH., WangY.. Crest: a credible spatiotemporal learning framework for uncertainty-aware traffic forecasting. Proceedings of the 17th ACM International Conference on Web Search and Data Mining, 2024985993.

[55] LiG., LiZ., KnoopV.L., LintJ.. How far ahead should autonomous vehicles start resolving predicted conflicts? Exploring uncertainty-based safety-efficiency trade-off. IEEE Trans. Intell. Transp. Syst., 2024, 25(10): 14183-14195.

[56] W. Shao, Y. Xu, L. Peng, J. Li, H. Wang, Failure detection for motion prediction of autonomous driving: an uncertainty perspective (2023). arXiv preprint arXiv:2301.04421

[57] G. Franchi, X. Yu, A. Bursuc, A. Tena, R. Kazmierczak, S. Dubuisson, E. Aldea, D. Filliat, Muad: multiple uncertainties for autonomous driving, a benchmark for multiple uncertainty types and tasks (2022). arXiv preprint arXiv:2203.01437

[58] WangH., HuJ., LiuH., LiuH.. On uncertainty quantification impact for autonomous driving decisions at intersections. 2024 IEEE International Conference on Unmanned Systems (ICUS), 2024, Los Alamitos. IEEE. 597602.

[59] YangK., TangX., LiJ., WangH., ZhongG., ChenJ., CaoD.. Uncertainties in onboard algorithms for autonomous vehicles: challenges, mitigation, and perspectives. IEEE Trans. Intell. Transp. Syst., 2023, 24(9): 8963-8987.

[60] R. Zhang, Dependable decision making for autonomous vehicles considering perception uncertainties. PhD thesis, University of Waterloo (2024)

[61] HuW., WangC., DengZ., YangY., WuY., CaoK., ZhangB., CaoD.. Uncertainty-aware decision making and planning for icv based on asymmetric driving aggressiveness. IEEE Trans. Intell. Veh., 2024, 9(3): 4432-4444.

[62] S. Qi, Z. Zhang, Z. Sun, S. Haesaert, Risk-aware autonomous driving with linear temporal logic specifications (2024). arXiv preprint arXiv:2409.09769

[63] LefèvreS., VasquezD., LaugierC.. A survey on motion prediction and risk assessment for intelligent vehicles. ROBOMECH J., 2014, 11. 1

[64] ChenC., LanZ., ZhanG., LyuY., NieB., LiS.E.. Quantifying the individual differences of drivers’ risk perception via potential damage risk model. IEEE Trans. Intell. Transp. Syst., 2024, 25(7): 8093-8104.

[65] YuR., ZhengY., QuX.. Dynamic driving environment complexity quantification method and its verification. Transp. Res., Part C, Emerg. Technol., 2021, 127. 103051

[66] E. Candela, Y. Feng, P. Angeloudis, Y. Demiris, Quantitative risk indices for autonomous vehicle training systems (2021). arXiv preprint arXiv:2104.12945

[67] MagalhãesR., BernardinoA.. Quantifying object detection uncertainty in autonomous driving with test-time augmentation. 2023 IEEE Intelligent Vehicles Symposium (IV), 2023, Los Alamitos. IEEE. 17

[68] KondohT., YamamuraT., KitazakiS., KugeN., BoerE.R.. Identification of visual cues and quantification of drivers’ perception of proximity risk to the lead vehicle in car-following situations. J. Mech. Syst. Transp. Logist., 2008, 1(2): 170-180.

[69] ChenH., ZhangY., BhattiU.A., HuangM.. Safe decision controller for autonomous drivingbased on deep reinforcement learning innondeterministic environment. Sensors, 2023, 233. 1198

[70] H. Tian, K. Reddy, Y. Feng, M. Quddus, Y. Demiris, P. Angeloudis, Enhancing autonomous vehicle training with language model integration and critical scenario generation (2024). arXiv preprint arXiv:2404.08570

[71] LiJ., LingM., ZangX., LuoQ., YangJ., ChenS., GuoX.. Quantifying risks of lane-changing behavior in highways with vehicle trajectory data under different driving environments. Int. J. Mod. Phys. C, 2024, 3511. 2450141

[72] YangS., LiQ., PangZ., SunB., FengX., WangR., GongT., CaoY.. A safety assessment method based on cloud model for decision-making of autonomous vehicles. 2024 IEEE 22nd International Conference on Industrial Informatics (INDIN), 2024, Los Alamitos. IEEE. 119

[73] WuX., HuQ., TsuchiyaT., HayashiM., OkadaM., MaL., ZhaoJ.. Evaluating the robustness of uncertainty quantification-based misbehavior predictors for autonomous driving systems: a case study. 2025 IEEE/ACM 1st International Workshop on Software Engineering for Autonomous Driving Systems (SE4ADS), 2025, Los Alamitos. IEEE. 1925.

[74] R. Nasri, J. Jamii, M. Mansouri, Z. Affi, V. Puig, A novel data-driven mpc framework using kde and kpca for autonomous vehicles. IEEE Access (2025)

[75] JungY., SeoS.-W., KimS.-W.. Fast point clouds upsampling with uncertainty quantification for autonomous vehicles. 2022 International Conference on Robotics and Automation (ICRA), 2022, Los Alamitos. IEEE. 77767782.

[76] SiamiM., NaderpourM., RamezaniF., LuJ.. Risk assessment through big data: an autonomous fuzzy decision support system. IEEE Trans. Intell. Transp. Syst., 2024, 25(8): 9016-9027.

[77] MerolaF., BernardeschiC., LamiG.. A risk assessment framework based on fuzzy logic for automotive systems. Safety, 2024, 102. 41

[78] WarrenC.W.. Global path planning using artificial potential fields. 1989 IEEE International Conference on Robotics and Automation, 1989, Los Alamitos. IEEE Comput. Soc.. 316317

[79] RenC., FuF., YinC., YanZ., ZhangR., WangZ.. Improved artificial potential field method based on robot local path information. Int. J. Adv. Robot. Syst., 2024, 215. 17298806241278172

[80] ChengY., LiuZ., GaoL., ZhaoY., GaoT.. Traffic risk environment impact analysis and complexity assessment of autonomous vehicles based on the potential field method. Int. J. Environ. Res. Public Health, 2022, 1916. 10337

[81] YangW., LiC., ZhouY.. A path planning method for autonomous vehicles based on risk assessment. World Electr. Veh. J., 2022, 1312. 234

[82] ChenY., QuD., WangT., CuiS., ShaoD.. Quantification method of driving risks for networked autonomous vehicles based on molecular potential fields. Appl. Sci., 2025, 153. 1306

[83] D. Chen, H. Li, Z. Jin, H. Tu, M. Zhu, Risk-anticipatory autonomous driving strategies considering vehicles’ weights based on hierarchical deep reinforcement learning. IEEE Trans. Intell. Transp. Syst. (2024)

[84] TanH., LuG., WangZ., HuaJ., LiuM.. A unified risk field-based driving behavior model for car-following and lane-changing behaviors simulation. Simul. Model. Pract. Theory, 2024, 136. 102991

[85] Q. Li, Z. Tian, X. Wang, J. Yang, Z. Lin, Adaptive field effect planner for safe interactive autonomous driving on curved roads (2025). arXiv preprint arXiv:2504.14747

[86] ZuoD., BianZ., ZuoF., OzbayK.. Toward an enhanced risk assessment sensitivity for autonomous vehicles with the safety potential field approach. 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), 2024, Los Alamitos. IEEE. 28892894.

[87] C. Zhao, D. Ding, C. Lei, S. Wang, Y. Ji, Y. Du, Safety field-based vehicle-infrastructure cooperative perception for autonomous driving using 3d point clouds. IEEE Trans. Intell. Transp. Syst. (2025)

[88] MacKayD.J.. A practical Bayesian framework for backpropagation networks. Neural Comput., 1992, 4(3): 448-472.

[89] DingL., LiD., LiuB., LanW., BaiB., HaoQ., CaoW., PeiK.. Capture uncertainties in deep neural networks for safe operation of autonomous driving vehicles. 2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), 2021, Los Alamitos. IEEE. 826835

[90] LebedeN., NadarajahS.. Enhancing autonomous systems with Bayesian neural networks: a probabilistic framework for navigation and decision-making. Front. Built Environ., 2025, 11. 1597255

[91] GrewalR., TonellaP., StoccoA.. Predicting safety misbehaviours in autonomous driving systems using uncertainty quantification. 2024 IEEE Conference on Software Testing, Verification and Validation (ICST), 2024, Los Alamitos. IEEE. 7081.

[92] ZhaoY., TianW., ChengH.. Pyramid Bayesian method for model uncertainty evaluation of semantic segmentation in autonomous driving. Automot. Innov., 2022, 5(1): 70-78.

[93] R. Sachdeva, R. Gakhar, S. Awasthi, K. Singh, A. Pandey, A.S. Parihar, Uncertainty and noise aware decision making for autonomous vehicles-a Bayesian approach. IEEE Trans. Veh. Technol. (2024)

[94] K. Madala, M. Solmaz, Scenario-based risk quantification approach for assuring safety in autonomous vehicles. Technical report, SAE Technical Paper (2023)

[95] L. Dai, B. Kantarci, Advancing autonomous vehicle safety: a combined fault tree analysis and Bayesian network approach (2025). arXiv preprint arXiv:2504.08206

[96] Stockem NovoA., HürtenC., BaumannR., SiebergP.. Self-evaluation of automated vehicles based on physics, state-of-the-art motion prediction and user experience. Sci. Rep., 2023, 131. 12692

[97] ChenS., MinH., FangY., WuX., LiB., ZhaoX.. Uncertainty-aware sensor data anomaly detection for autonomous vehicles. 2024 IEEE Intelligent Vehicles Symposium (IV), 2024, Los Alamitos. IEEE. 478483.

[98] ShangguanQ., FuT., WangJ., FangS., FuL.. A proactive lane-changing risk prediction framework considering driving intention recognition and different lane-changing patterns. Accid. Anal. Prev., 2022, 164. 106500

[99] HassanO.F., IbrahimA.F., GomaaA., MakhloufM., HafizB.. Real-time driver drowsiness detection using transformer architectures: a novel deep learning approach. Sci. Rep., 2025, 151. 17493

[100] K. Wang, Q. Ma, X. Li, C. Shen, R. Leng, J. Lu, Ubtransformer: uncertainty-based transformer model for complex scenarios detection in autonomous driving. IEEE Trans. Multimed. (2025)

[101] M. Lei, Z. Zhou, H. Li, J. Hu, J. Ma, Cooperrisk: a driving risk quantification pipeline with multi-agent cooperative perception and prediction (2025). arXiv preprint arXiv:2506.15868

[102] YangK., LiB., ShaoW., TangX., LiuX., WangH.. Prediction failure risk-aware decision-making for autonomous vehicles on signalized intersections. IEEE Trans. Intell. Transp. Syst., 2023, 24(11): 12806-12820.

[103] LingS., WanY., JiaX., DuN.. Improving explainable object-induced model through uncertainty for automated vehicles. Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, 2024443451.

[104] BaiC., JinS., JingJ., YangC., YaoW., RongD., AlagbéJ.A.. A multimodal data-driven approach for driving risk assessment. Transp. Res., Part E, Logist. Transp. Rev., 2024, 189. 103678

[105] LeeS., SongB., ShinJ.. Collision prediction in an integrated framework of scenario-based and data-driven approaches. IEEE Access, 2024, 12: 55234-55247.

[106] StoccoA., NunesP.J., d’AmorimM., TonellaP.. Thirdeye: attention maps for safe autonomous driving systems. Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering, 2022112

[107] W. Shao, J. Xu, Z. Cao, H. Wang, J. Li, Uncertainty-aware prediction and application in planning for autonomous driving: definitions, methods, and comparison (2024). arXiv preprint arXiv:2403.02297

[108] H. Gao, C. Wang, R. Niu, X. Fang, J. Chen, Y. Sun, H. Jin, D. Wang, Driving risk assessment for intelligent vehicles based on entropy-informed graph neural networks and Gaussian distributions. IEEE Trans. Neural Netw. Learn. Syst. (2025)

[109] ZhuZ., WangS., ZhaoH.. Uncertainty-aware deep imitation learning and deployment for autonomous navigation through crowded intersections. 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024, Los Alamitos. IEEE. 1398013987.

[110] GanW., DaoM.-S., ZettsuK.. Drive-clip: cross-modal contrastive safety-critical driving scenario representation learning and zero-shot driving risk analysis. International Conference on Multimedia Modeling, 2024, Berlin. Springer. 8297.

[111] WuS., TianD., DuanX., ZhouJ., ZhaoD., CaoD.. Continuous decision-making in lane changing and overtaking maneuvers for unmanned vehicles: a risk-aware reinforcement learning approach with task decomposition. IEEE Trans. Intell. Veh., 2024, 9(4): 4657-4674.

[112] YangK., TangX., QiuS., JinS., WeiZ., WangH.. Towards robust decision-making for autonomous driving on highway. IEEE Trans. Veh. Technol., 2023, 72(9): 11251-11263.

[113] WuJ., HuangZ., LvC.. Uncertainty-aware model-based reinforcement learning: methodology and application in autonomous driving. IEEE Trans. Intell. Veh., 2022, 8(1): 194-203.

[114] ZhaoS., DuanJ., WuS., GuX., LiC., YinK., WangH.. Genetic algorithm-based sotif scenario construction for complex traffic flow. Automot. Innov., 2023, 6(4): 531-546.

[115] GuoL., XuL., GeP., WangX.. How resource demands of nondriving-related tasks and engagement time affect drivers’ physiological response and takeover performance in conditional automated driving. IEEE Trans. Human-Mach. Syst., 2023, 53(3): 600-609.

[116] ConstantinidesP., MonteiroE., MathiassenL.. Human-ai joint task performance: learning from uncertainty in autonomous driving systems. Inf. Organ., 2024, 342. 100502

[117] C. Chen, Z. Lan, G. Zhan, Y. Lyu, B. Nie, S.E. Li, Quantifying the individual differences of driver’risk perception with just four interpretable parameters (2022). arXiv preprint arXiv:2211.10907

[118] KamelA., SayedT., KamelM.. Real-time combined safety-mobility assessment using self-driving vehicles collected data. Accid. Anal. Prev., 2024, 199. 107513

[119] YanX., FengS., LeBlancD.J., FlannaganC., LiuH.X.. Evaluation of automated driving system safety metrics with logged vehicle trajectory data. IEEE Trans. Intell. Transp. Syst., 2024, 25(8): 8913-8925.

[120] GeisslingerM., TrauthR., KaljavesiG., LienkampM.. Maximum acceptable risk as criterion for decision-making in autonomous vehicle trajectory planning. IEEE Open J. Intell. Transp. Syst., 2023, 4: 570-579.

[121] G. Wang, N. Zhang, J. Lai, C. Xie, Z. Zhang, J. Lai, J. Hu, Perceived risk quantification for automated vehicles: a method with unified metrics. J. Intell. Transp. Syst., 1–11 (2025)

[122] TongK., SolmazS., SikicH., ReckenzaunJ.. A generic risk assessment methodology and its implementation as a run-time monitoring device for automated vehicles. Transp. Res. Proc., 2023, 72: 303-310

[123] QuanteL., ZhangM., PreukK., SchießlC.. Human performance in critical scenarios as a benchmark for highly automated vehicles. Automot. Innov., 2021, 4(3): 274-283.

[124] KuoP.-F., HsuW.-T., LordD., PutraI.G.B.. Classification of autonomous vehicle crash severity: solving the problems of imbalanced datasets and small sample size. Accid. Anal. Prev., 2024, 205. 107666

[125] DongX., ZhangD., MuY., ZhangT., TangK.. Complexity of driving scenarios based on traffic accident data. Int. J. Automot. Technol., 2024, 25(1): 23-36.

[126] YangL., WeiH., HuZ., LvC.. A domain generalization method for deploying driver distraction detection models to practical application scenarios. Eng. Appl. Artif. Intell., 2025, 152. 110844

[127] ZhengH., ZhouT., HanT., LiS., YuC.. An interpretable prediction framework for multi-class situational awareness in conditionally automated driving. Adv. Eng. Inform., 2024, 62. 102683

[128] HouZ., LiuD., YangY., LiuH.. Assessing unknown hazards for sotif based on twin scenarios empowered autonomous driving. IEEE Internet Things J., 2024, 11(20): 32631-32644.

[129] R. Yu, C. Wang, Y. Zhang, F. Zhao, Decomposition and quantification of sotif requirements for perception systems of autonomous vehicles. IEEE Trans. Intell. Transp. Syst. (2025)

[130] L. Tang, R. Wang, Z. Liu, Y. Liang, Y. Niu, W. Zhu, Z. Duan, Scenario-based accelerated testing for sotif in autonomous driving: a review. IEEE Internet Things J. (2024)

[131] PutzeL., WesthofenL., KoopmannT., BödeE., NeurohrC.. On quantification for sotif validation of automated driving systems. 2023 IEEE Intelligent Vehicles Symposium (IV), 2023, Los Alamitos. IEEE. 18

Funding

National Key R&D Program of China under Grant(No2022YFB2502900)

National Natural Science Foundation of China(U23B2061)

RIGHTS & PERMISSIONS

The Author(s)