Modeling Automated Vehicle Crashes with a Focus on Vehicle At-Fault, Collision Type, and Injury Outcome
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 148, Issue 6
Abstract
Automated vehicle (AV) technology is expected to make roads safer. However, until recently only a handful of studies could test such hypotheses due to limited access to testing data. This study contributes to the literature by jointly analyzing the associated factors of three interrelated outcome variables—vehicle at fault, collision type, and injury outcome in AV-involved crashes. We use Bayesian networks to analyze the manually extracted data from reports of 333 AV-involved crashes that occurred in California between January 2017 and October 2021. The summary statistics indicate that rear-end collisions are the dominant (63.5%), while AVs are at fault for a small proportion of crashes (14.4%), and a majority of crashes (84.4%) are noninjury. The joint inferences of the Bayesian networks show that irrespective of the collision type, when the AV is at fault, the chance of the physical injury in a crash increases significantly. Further, the chance of an AV being at fault seems higher in parking locations, and during driving at wet pavements in unclear weather. The chances of AV rear-end collisions are lower in the parking lot, and when nonvehicular participants are involved but increase in high traffic flow roadways. We also find that the likelihood of physical injury is higher at high-speed locations, intersections, and wet pavements. These insights suggest specific areas (unsignalized intersections, less structured right-of-way rules, and wet pavements) where technological improvements could enhance the safety performance of AVs.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some data used in this study were extracted from California Department of Motor Vehicles and they are open-sourced through the website (California-DMV 2021). Some or all data, models, or code generated or used during the study are available in a repository online (California-DMV 2021) in accordance with funder data retention policies. Some models or code may be made available by direct request to the authors.
Acknowledgments
Authors would like to acknowledge the California Department of Motor Vehicles for the open-source AV-involved crashes used in this study.
References
Arbelaez Garces, G., A. Rakotondranaivo, and E. Bonjour. 2016. “Improving users’ product acceptability: An approach based on Bayesian networks and a simulated annealing algorithm.” Int. J. Prod. Res. 54 (17): 5151–5168. https://doi.org/10.1080/00207543.2016.1156183.
Bhavsar, P., P. Das, M. Paugh, K. Dey, and M. Chowdhury. 2017. “Risk analysis of autonomous vehicles in mixed traffic streams.” Transp. Res. Rec. 2625 (1): 51–61. https://doi.org/10.3141/2625-06.
Boggs, A. M., B. Wali, and A. J. Khattak. 2020. “Exploratory analysis of automated vehicle crashes in California: A text analytics & hierarchical Bayesian heterogeneity-based approach.” Accid. Anal. Prev. 135 (11): 105354. https://doi.org/10.1016/j.aap.2019.105354.
California-DMV. 2021. “Autonomous vehicle collision reports—California DMV.” Accessed November 17, 2021. https://www.dmv.ca.gov/portal/vehicle-industry-services/autonomous-vehicles/autonomous-vehicle-collision-reports/.
Carvalho, A. M. 2009. “Scoring functions for learning Bayesian networks.” Accessed December 29, 2020. http://www.lx.it.pt/∼asmc/pub/talks/09-TA/ta_pres.pdf.
Castillo, E., J. M. Gutiérrez, and A. S. Hadi. 1997. “Sensitivity analysis in discrete Bayesian networks.” IEEE Trans. Syst. Man Cyber. Part A: Syst. Humans 27 (4): 412–423. https://doi.org/10.1109/3468.594909.
Crowe, S. 2021. “Cruise, Waymo lead way in Calif.” Accessed December 6, 2021. https://www.therobotreport.com/cruise-waymo-lead-way-calif-autonomous-vehicle-tests/.
Das, S., A. Dutta, and I. Tsapakis. 2020. “Automated vehicle collisions in California: Applying Bayesian latent class model.” IATSS Res. 44 (4): 300–308. https://doi.org/10.1016/j.iatssr.2020.03.001.
De Campos, L. M. 2006. “A scoring function for learning Bayesian networks based on mutual information and conditional independence tests.” J. Mach. Learn. Res. 7 (32): 2149–2187.
Demiroluk, S., and K. Ozbay. 2014. “Adaptive learning in Bayesian networks for incident duration prediction.” Transp. Res. Rec. 2460 (1): 77–85. https://doi.org/10.3141/2460-09.
Favarò, F. M., N. Nader, S. O. Eurich, M. Tripp, and N. Varadaraju. 2017. “Examining accident reports involving autonomous vehicles in California.” PLoS One 12 (9): 156. https://doi.org/10.1371/journal.pone.0184952.
Horný, M. 2014. “Bayesian networks.” Accessed July 31, 2020. https://www.bu.edu/sph/files/2014/05/bayesian-networks-final.pdf.
Kidando, E., R. Moses, T. Sando, and E. E. Ozguven. 2018. “Probabilistic inference and prediction of travel time reliability: Empirical analysis of associated factors.” Accessed November 17, 2020. https://trid.trb.org/view/1497143.
Kim, J., and G. Wang. 2016. “Diagnosis and prediction of traffic congestion on urban road networks using Bayesian networks.” Transp. Res. Rec. 2595 (1): 108–118. https://doi.org/10.3141/2595-12.
Kitali, A. E., E. Kidando, B. Kutela, C. Kadeha, P. Alluri, and T. Sando. 2021. “Safety evaluation of high-occupancy toll facilities using Bayesian networks.” J. Transp. Eng. Part A: Syst. 147 (5). https://doi.org/10.1061/JTEPBS.0000523.
Kockelman, K. M., et al. 2016. Implications of connected and automated vehicles on the safety and operations of roadway networks. Austin, TX: Univ. of Texas at Austin.
Korb, K. B., and A. E. Nicholson. 2004. Bayesian artificial intelligence. London: CRC Press.
Kuhn, M. 2017. “Package ‘caret.’” Accessed June 1, 2021. https://cran.r-project.org/web/packages/caret/caret.pdf.
Kutela, B., R. E. Avelar, S. R. Geedipally, and A. Jhamb. 2021a. “Prediction of occurrence and severity of run-off-roadway (ROR) crashes on two-lane rural roadways using Bayesian networks.” Transp. Res. Rec. 2021 (Dec): 03611981211051351. https://doi.org/10.1177/03611981211051351.
Kutela, B., S. Das, and B. Dadashova. 2021b. “Mining patterns of autonomous vehicle crashes involving vulnerable road users to understand the associated factors.” Accid. Anal. Prev. 165 (Feb): 106473. https://doi.org/10.1016/J.AAP.2021.106473.
Kutela, B., and H. Teng. 2019a. “The influence of campus characteristics, temporal factors, and weather events on campuses-related daily bike-share trips.” J. Transp. Geogr. 78 (Jun): 160–169. https://doi.org/10.1016/j.jtrangeo.2019.06.002.
Kutela, B., and H. Teng. 2019b. “Prediction of drivers and pedestrians’ behaviors at signalized mid-block Danish offset crosswalks using Bayesian networks.” J. Saf. Res. 69 (Sep): 75–83. https://doi.org/10.1016/j.jsr.2019.02.008.
Kutela, B., H. Teng, and H. H. Harry. 2020. “Assessment of methodological alternatives for modeling the spatiotemporal crossing compliance of pedestrians at signalized midblock crosswalks.” J. Transp. Eng. Part A Syst. 146 (2): 04019062. https://doi.org/10.1061/JTEPBS.0000300.
Laskey, K. B. 1995. “Sensitivity analysis for probability assessments in Bayesian networks.” IEEE Trans. Syst. Man Cyber. 25 (6): 901–909. https://doi.org/10.1109/21.384252.
Markov, Z., and I. Russell. 2007. “Probabilistic reasoning with naïve Bayes and Bayesian networks.” Accessed June 24, 2021. https://pdfs.semanticscholar.org/39b3/17ce5eb9ea7d14a0a3e2755dbea105328efa.pdf.
Morando, M. M., Q. Tian, L. T. Truong, and H. L. Vu. 2018. “Studying the safety impact of autonomous vehicles using simulation-based surrogate safety measures.” J. Adv. Transp. 2018 (Apr): 22. https://doi.org/10.1155/2018/6135183.
Raftery, A. E. 1995. “Bayesian model selection in social research.” Sociol. Methodol. 25 (Sep): 111. https://doi.org/10.2307/271063.
R Core Team. 2021. “R: A language and environment for statistical computing R foundation for statistical computing.” Accessed August 17, 2021. https://www.r-project.org/.
RPubs. 2021. “RPubs—The t distribution and tests.” Accessed April 6, 2021. https://rpubs.com/kerkhoffa/TCommands.
Salum, J. H., B. Kutela, A. E. Kitali, and E. Kidando. 2021. “Stated preference analysis of automated vehicles among California residents using probabilistic inferences.” Transp. Res. Rec. 2021 (Sep): 036119812110398. https://doi.org/10.1177/03611981211039845.
Schoettle, B., and M. Sivak. 2015. “A preliminary analysis of real-world crashes involving self-driving vehicles.” Accessed November 22, 2020. http://www.umich.edu/∼umtriswt.
Scutari, M. 2010. “Learning Bayesian networks with the bnlearn R package.” J. Stat. Software 35 (3): 26. https://doi.org/10.18637/jss.v035.i03.
Teoh, E. R., and D. G. Kidd. 2016. “Rage against the machine? Google TMs self-driving cars versus human drivers.” J. Saf. Res. 63 (2): 57–60. https://doi.org/10.1016/j.jsr.2017.08.008.
Wang, S., and Z. Li. 2019. “Exploring the mechanism of crashes with automated vehicles using statistical modeling approaches.” PLoS One 14 (3): e0214550. https://doi.org/10.1371/journal.pone.0214550.
Wickham, H., et al. 2019. “Welcome to the Tidyverse.” J. Open Source Software 4 (43): 1686. https://doi.org/10.21105/joss.01686.
Xie, C., and S. Waller. 2010. “Estimation and application of a Bayesian network model for discrete travel choice analysis.” 2 (2): 125–144. https://doi.org/10.3328/TL.2010.02.02.125-144.
Zheng, Z., and P. A. Pavlou. 2009. “Toward a causal interpretation from observational data: A New Bayesian networks method for structural models with latent variables.” Inf. Syst. Res. Articles Adv. 21 (2): 1–27. https://doi.org/10.1287/isre.1080.0224.
Information & Authors
Information
Published In
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Aug 16, 2021
Accepted: Feb 2, 2022
Published online: Mar 22, 2022
Published in print: Jun 1, 2022
Discussion open until: Aug 22, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Sai Sneha Channamallu, Deema Almaskati, Sharareh Kermanshachi, Apurva Pamidimukkala, Enhancing AV Safety: A Bagging Classifier Approach for Predicting Crash Outcomes, International Conference on Transportation and Development 2024, 10.1061/9780784485514.047, (538-549), (2024).
- Song Wang, Zhixia Li, Yi Wang, Wenjing Zhao, Heng Wei, Quantification of safety improvements and human-machine tradeoffs in the transition to automated driving, Accident Analysis & Prevention, 10.1016/j.aap.2024.107523, 199, (107523), (2024).
- Yijing Zhang, Zhan Zhang, Zhenyu Wang, Tongtong Lyu, Xianing Wang, Linjun Lu, Accident Diagnosis and Evaluation System in Parking Lots Using Multisource Data Based on Bayesian Networks, Journal of Advanced Transportation, 10.1155/2023/3150003, 2023, (1-19), (2023).
- Song Yan, Chunxi Huang, Dengbo He, A comparison of patterns and contributing factors of ADAS and ADS involved crashes, Journal of Transportation Safety & Security, 10.1080/19439962.2023.2284175, (1-28), (2023).
- Lisa Miller, Public Sector Integration of Connected and Automated Vehicles: Considerations, Benefits and Sharing Data Across Borders, Road Vehicle Automation 10, 10.1007/978-3-031-34757-3_4, (40-50), (2023).
- Qingfan Wang, Qing Zhou, Miao Lin, Bingbing Nie, Human injury-based safety decision of automated vehicles, iScience, 10.1016/j.isci.2022.104703, 25, 8, (104703), (2022).