{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T20:48:24Z","timestamp":1769028504015,"version":"3.49.0"},"reference-count":53,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T00:00:00Z","timestamp":1768780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Research Foundation of China","award":["52502401"],"award-info":[{"award-number":["52502401"]}]},{"name":"National Natural Research Foundation of China","award":["52202399"],"award-info":[{"award-number":["52202399"]}]},{"name":"National Natural Research Foundation of China","award":["52372314"],"award-info":[{"award-number":["52372314"]}]},{"name":"National Natural Research Foundation of China","award":["52432010"],"award-info":[{"award-number":["52432010"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundations","doi-asserted-by":"crossref","award":["2022M710679"],"award-info":[{"award-number":["2022M710679"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Postgraduate Research & Practice Innovation Program of Jiangsu Province","award":["KYCX22_0286"],"award-info":[{"award-number":["KYCX22_0286"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>The rapid advancement of autonomous vehicle systems (AVS) has introduced complex challenges to road safety. While some studies have investigated the contribution of factors influencing AV-involved crashes, few have focused on the impact of vehicle-specific factors within AVS on crash outcomes, a focus that gains importance due to the absence of a human driver. To address this gap, the advanced machine learning algorithm, LightGBM (v4.4.0), is employed to quantify the potential effects of vehicle factors on crash severity and collision types based on the Autonomous Vehicle Operation Incident Dataset (AVOID). The joint effects of different vehicle factors and the interactive effects of vehicle factors and environmental factors are studied. Compared with other frequently utilized machine learning techniques, LightGBM demonstrates superior performance. Furthermore, the SHapley Additive exPlanation (SHAP) approach is employed to interpret the results of LightGBM. The analysis of crash severity revealed the importance of investigating the vehicle characteristics of AVs. Operator type is the most predictive factor. For road types, highways and streets show a positive association with the model\u2019s prediction of serious crashes. Crashes involving vulnerable road users can be attributed to different factors. The road type is the most significant factor, followed by precrash speed and mileage. This study identifies key predictive associations for the development of safer AV systems and provides data-driven insights to support regulatory strategies for autonomous driving technologies.<\/jats:p>","DOI":"10.3390\/systems14010104","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T09:57:02Z","timestamp":1768816622000},"page":"104","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deciphering the Crash Mechanisms in Autonomous Vehicle Systems via Explainable AI"],"prefix":"10.3390","volume":"14","author":[{"given":"Zhe","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Mianyang Normal University, Mianyang 621000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wentao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Transportation, Southeast University, Jiulonghu Campus, Nanjing 211100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3242-8071","authenticated-orcid":false,"given":"Qi","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Transportation, Southeast University, Jiulonghu Campus, Nanjing 211100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Song","sequence":"additional","affiliation":[{"name":"Transportation Institute, Inner Mongolia University, Huhehaote 010020, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8246-5973","authenticated-orcid":false,"given":"Jingfeng","family":"Ma","sequence":"additional","affiliation":[{"name":"Faculty of Transportation Engineering, Kunming University of Science and Technology, Kunming 650500, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Transportation, Southeast University, Jiulonghu Campus, Nanjing 211100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2299-5435","authenticated-orcid":false,"given":"Changjian","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Transportation, Southeast University, Jiulonghu Campus, Nanjing 211100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"120929","DOI":"10.1016\/j.eswa.2023.120929","article-title":"A comprehensive study on lane detecting autonomous car using computer vision","volume":"233","author":"Gajjar","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1080\/15389588.2023.2227304","article-title":"Adaptive autonomous emergency braking model based on weather conditions","volume":"24","author":"Han","year":"2023","journal-title":"Traffic Inj. Prev."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Reinke, A., Chen, X., and Stachniss, C. (June, January 30). Simple But Effective Redundant Odometry for Autonomous Vehicles. Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi\u2019an, China.","DOI":"10.1109\/ICRA48506.2021.9562023"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1016\/j.procs.2021.12.315","article-title":"An overview of sensors in Autonomous Vehicles","volume":"198","author":"Ignatious","year":"2022","journal-title":"Procedia Comput. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1109\/MSP.2020.2984801","article-title":"Object Detection Under Rainy Conditions for Autonomous Vehicles: A Review of State-of-the-Art and Emerging Techniques","volume":"38","author":"Hnewa","year":"2021","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1111\/mice.12507","article-title":"Behavioral decision-making model of the intelligent vehicle based on driving risk assessment","volume":"36","author":"Zheng","year":"2021","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1109\/TASE.2022.3227964","article-title":"Interactive left-turning of autonomous vehicles at uncontrolled intersections","volume":"21","author":"Sun","year":"2022","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Kotur, M., Luki\u0107, N., Kruni\u0107, M., and Luka\u010d, \u017d. (2021, January 26\u201327). Camera and LiDAR Sensor Fusion for 3D Object Tracking in a Collision Avoidance System. Proceedings of the 2021 Zooming Innovation in Consumer Technologies Conference (ZINC), Novi Sad, Serbia.","DOI":"10.1109\/ZINC52049.2021.9499281"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"104248","DOI":"10.1016\/j.aei.2025.104248","article-title":"REACT: Runtime-Enabled active collision-avoidance technique for autonomous driving","volume":"71","author":"Huang","year":"2026","journal-title":"Adv. Eng. Inform."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"105805","DOI":"10.1016\/j.aap.2020.105805","article-title":"Risk perception and the warning strategy based on safety potential field theory","volume":"148","author":"Li","year":"2020","journal-title":"Accid. Anal. Prev."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Grewal, R., Tonella, P., and Stocco, A. (2024, January 27\u201331). Predicting safety misbehaviours in autonomous driving systems using uncertainty quantification. Proceedings of the 2024 IEEE Conference on Software Testing, Verification and Validation (ICST), Toronto, ON, Canada.","DOI":"10.1109\/ICST60714.2024.00016"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1080\/00423114.2018.1537494","article-title":"Emergency steering control of autonomous vehicle for collision avoidance and stabilisation","volume":"57","author":"He","year":"2019","journal-title":"Veh. Syst. Dyn."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3230","DOI":"10.1109\/TITS.2016.2544791","article-title":"Nonlinear coordinated steering and braking control of vision-based autonomous vehicles in emergency obstacle avoidance","volume":"17","author":"Guo","year":"2016","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5229","DOI":"10.1109\/TIV.2024.3519766","article-title":"Autonomous Emergency Collision Avoidance and Collaborative Stability Control Technologies for Intelligent Vehicles: A Survey","volume":"10","author":"Tan","year":"2025","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"King, C., Ries, L., Langner, J., and Sax, E. (November, January 12). A Taxonomy and Survey on Validation Approaches for Automated Driving Systems. Proceedings of the 2020 IEEE International Symposium on Systems Engineering (ISSE), Vienna, Austria.","DOI":"10.1109\/ISSE49799.2020.9272219"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kaur, P., Taghavi, S., Tian, Z., and Shi, W. (2021, January 28\u201329). A Survey on Simulators for Testing Self-Driving Cars. Proceedings of the 2021 Fourth International Conference on Connected and Autonomous Driving (MetroCAD), Detroit, MI, USA.","DOI":"10.1109\/MetroCAD51599.2021.00018"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"120049","DOI":"10.1109\/ACCESS.2023.3327918","article-title":"Safety Testing of Automated Driving Systems: A Literature Review","volume":"11","author":"Khan","year":"2023","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Hamidaoui, M., Talhaoui, M.Z., Li, M., Midoun, M.A., Haouassi, S., Mekkaoui, D.E., Smaili, A., Cherraf, A., and Benyoub, F.Z. (2025). Survey of autonomous vehicles\u2019 collision avoidance algorithms. Sensors, 25.","DOI":"10.3390\/s25020395"},{"key":"ref_19","first-page":"100124","article-title":"The joint effect of weather and lighting conditions on injury severities of single-vehicle accidents","volume":"27","author":"Fountas","year":"2020","journal-title":"Anal. Methods Accid. Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"107235","DOI":"10.1016\/j.aap.2023.107235","article-title":"A hybrid approach of random forest and random parameters logit model of injury severity modeling of vulnerable road users involved crashes","volume":"192","author":"Sun","year":"2023","journal-title":"Accid. Anal. Prev."},{"key":"ref_21","first-page":"100113","article-title":"Big data, traditional data and the tradeoffs between prediction and causality in highway-safety analysis","volume":"25","author":"Mannering","year":"2020","journal-title":"Anal. Methods Accid. Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.aap.2017.08.008","article-title":"Comparison of four statistical and machine learning methods for crash severity prediction","volume":"108","author":"Iranitalab","year":"2017","journal-title":"Accid. Anal. Prev."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.aap.2017.12.026","article-title":"Non-linear effects of the built environment on automobile-involved pedestrian crash frequency: A machine learning approach","volume":"112","author":"Ding","year":"2018","journal-title":"Accid. Anal. Prev."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"106545","DOI":"10.1016\/j.aap.2021.106545","article-title":"Predicting effects of built environment on fatal pedestrian accidents at location-specific level: Application of XGBoost and SHAP","volume":"166","author":"Chang","year":"2022","journal-title":"Accid. Anal. Prev."},{"key":"ref_26","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017, January 4\u20139). Lightgbm: A highly efficient gradient boosting decision tree. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"105405","DOI":"10.1016\/j.aap.2019.105405","article-title":"Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis","volume":"136","author":"Parsa","year":"2020","journal-title":"Accid. Anal. Prev."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"106153","DOI":"10.1016\/j.aap.2021.106153","article-title":"The application of XGBoost and SHAP to examining the factors in freight truck-related crashes: An exploratory analysis","volume":"158","author":"Yang","year":"2021","journal-title":"Accid. Anal. Prev."},{"key":"ref_29","unstructured":"Zheng, O., Abdel-Aty, M., Wang, Z., Ding, S., Wang, D., and Huang, Y. (2023). Avoid: Autonomous vehicle operation incident dataset across the globe. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"106393","DOI":"10.1016\/j.infsof.2020.106393","article-title":"Assessing safety-critical systems from operational testing: A study on autonomous vehicles","volume":"128","author":"Zhao","year":"2020","journal-title":"Inf. Softw. Technol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1177\/03611981211018461","article-title":"Extracting rules from autonomous-vehicle-involved crashes by applying decision tree and association rule methods","volume":"2675","author":"Ashraf","year":"2021","journal-title":"Transp. Res. Rec."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"8881545","DOI":"10.1155\/2020\/8881545","article-title":"Analysis of Factors Affecting the Severity of Automated Vehicle Crashes Using XGBoost Model Combining POI Data","volume":"2020","author":"Chen","year":"2020","journal-title":"J. Adv. Transp."},{"key":"ref_33","first-page":"5524356","article-title":"Exploring the Mechanism of Crashes with Autonomous Vehicles Using Machine Learning","volume":"2021","author":"Chen","year":"2021","journal-title":"Math. Probl. Eng."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Sinha, A., Vu, V., Chand, S., Wijayaratna, K., and Dixit, V. (2021). A Crash Injury Model Involving Autonomous Vehicle: Investigating of Crash and Disengagement Reports. Sustainability, 13.","DOI":"10.3390\/su13147938"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"106769","DOI":"10.1016\/j.aap.2022.106769","article-title":"What can we learn from autonomous vehicle collision data on crash severity? A cost-sensitive CART approach","volume":"174","author":"Zhu","year":"2022","journal-title":"Accid. Anal. Prev."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.jsr.2019.09.001","article-title":"Statistical analysis of the patterns and characteristics of connected and autonomous vehicle involved crashes","volume":"71","author":"Xu","year":"2019","journal-title":"J. Saf. Res."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"04022024","DOI":"10.1061\/JTEPBS.0000680","article-title":"Modeling Automated Vehicle Crashes with a Focus on Vehicle At-Fault, Collision Type, and Injury Outcome","volume":"148","author":"Kutela","year":"2022","journal-title":"J. Transp. Eng. Part A Syst."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.jsr.2022.11.001","article-title":"A comparative study of collision types between automated and conventional vehicles using Bayesian probabilistic inferences","volume":"84","author":"Novat","year":"2023","journal-title":"J. Saf. Res."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"106473","DOI":"10.1016\/j.aap.2021.106473","article-title":"Mining patterns of autonomous vehicle crashes involving vulnerable road users to understand the associated factors","volume":"165","author":"Kutela","year":"2022","journal-title":"Accid. Anal. Prev."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"105354","DOI":"10.1016\/j.aap.2019.105354","article-title":"Exploratory analysis of automated vehicle crashes in California: A text analytics & hierarchical Bayesian heterogeneity-based approach","volume":"135","author":"Boggs","year":"2020","journal-title":"Accid. Anal. Prev."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"106932","DOI":"10.1016\/j.aap.2022.106932","article-title":"Advancing investigation of automated vehicle crashes using text analytics of crash narratives and Bayesian analysis","volume":"181","author":"Lee","year":"2023","journal-title":"Accid. Anal. Prev."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"107692","DOI":"10.1016\/j.aap.2024.107692","article-title":"Exploratory analysis of injury severity under different levels of driving automation (SAE Levels 2 and 4) using multi-source data","volume":"206","author":"Ding","year":"2024","journal-title":"Accid. Anal. Prev."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"103193","DOI":"10.1016\/j.simpat.2025.103193","article-title":"Modeling proactive effects of connected autonomous vehicles on urban traffic in adverse weather","volume":"144","author":"Wang","year":"2025","journal-title":"Simul. Model. Pract. Theory"},{"key":"ref_44","unstructured":"Lundberg, S.M., and Lee, S.-I. (2017, January 4\u20139). A unified approach to interpreting model predictions. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.eswa.2016.12.035","article-title":"Learning from class-imbalanced data: Review of methods and applications","volume":"73","author":"Haixiang","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"106261","DOI":"10.1016\/j.aap.2021.106261","article-title":"Quantifying and comparing the effects of key risk factors on various types of roadway segment crashes with LightGBM and SHAP","volume":"159","author":"Wen","year":"2021","journal-title":"Accid. Anal. Prev."},{"key":"ref_47","unstructured":"Snoek, J., Larochelle, H., and Adams, R.P. (2012, January 3\u20136). Practical bayesian optimization of machine learning algorithms. Proceedings of the 26th Annual Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_48","unstructured":"Lundberg, S.M., Erion, G.G., and Lee, S.-I. (2018). Consistent individualized feature attribution for tree ensembles. arXiv."},{"key":"ref_49","first-page":"376","article-title":"How do environmental and road factors impact automated vehicle crashes? An evidence from ADAS and ADS","volume":"17","author":"Dong","year":"2025","journal-title":"J. Transp. Saf. Secur."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"106704","DOI":"10.1016\/j.aap.2022.106704","article-title":"New needs to consider during accident analysis: Implications of autonomous vehicles with collision reconfiguration systems","volume":"173","author":"Parseh","year":"2022","journal-title":"Accid. Anal. Prev."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"268","DOI":"10.7326\/M16-2607","article-title":"Sensitivity analysis in observational research: Introducing the E-value","volume":"167","author":"VanderWeele","year":"2017","journal-title":"Ann. Intern. Med."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1111\/rssb.12348","article-title":"Making sense of sensitivity: Extending omitted variable bias","volume":"82","author":"Cinelli","year":"2020","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"1969","DOI":"10.1093\/ije\/dyu149","article-title":"Good practices for quantitative bias analysis","volume":"43","author":"Lash","year":"2014","journal-title":"Int. J. Epidemiol."}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/104\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T05:17:08Z","timestamp":1768972628000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,19]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["systems14010104"],"URL":"https:\/\/doi.org\/10.3390\/systems14010104","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,19]]}}}