A Study on Autonomous Vehicle Crash Hierarchy Analysis and Severity Model Based on Bayesian Probabilistic Inference

Songha Lee; Juneyoung Park

doi:10.7470/jkst.2024.42.1.077

All Issue

2024 Vol.42, Issue 1 Preview Page Next Page

Article

A Study on Autonomous Vehicle Crash Hierarchy Analysis and Severity Model Based on Bayesian Probabilistic Inference 베이지안 확률 추론 기반의 자율주행차 사고 계층분석 및 사고 심각도 모형 연구

29 February 2024. pp. 77-93

PDF XML

Abstract

With the advancement of Advanced Driver Assistance System technology, autonomous driving technology is get a attention as a key component of smart transportation systems. However, verification of safety about autonomous vehicle is required due to the continuous traffic crash involving autonomous vehicles. In particular, to ensure the safety of vulnerable road users such as pedestrians as well as autonomous vehicle on handicap sections where autonomous mode is unexpectedly disengaged and the driver's response time is insufficient, this requires a technical/institutional approach and a continuous understanding for autonomous vehicle crashes. Therefore, this study used autonomous vehicle crash record data to extract impact factors from the autonomous vehicle collision reports provided by the California Department of Motor Vehicles, and used latent class analysis and ordered probit model with Bayesian probability inference to deal with the traffic crash sample. As a result, traffic crash involving vulnerable road users such as pedestrians and cyclists, scooter, mainly occur at bus stops or bicycle lanes where road users cross, and the traffic crash severity increases when light condition is dark street. On the other hand, for the traffic crash which is not involve vulnerable road users, the crash classes were divided and the traffic crash severity increased depending on weather conditions, autonomous vehicle movement, day and night, etc. When considering unobserved heterogeneity in geometry and weather conditions, it was found that the the variance size was smaller and the confidence interval was narrower based on the Bayesian ordered probit model with random effects unlike fixed effects. Specifically, the traffic crash severity increased mainly in movements including turns around signalized intersections and for the other crash, which does not include the vulnerable road users. This means that intersections require an exploring of vehicle movements due to the cross to the various road users, complexity of traffic flow, and unpredictability of vehicles and pedestrians. By developing a detailed autonomous vehicle safety evaluation scenario on these study, it is expected that more efficient and reasonable safety evaluation of level 4 to level 5 autonomous driving technology will be possible.

Keywords

autonomous vehicle collision report

bayesian latent class

random effect

traffic crash severity

text mining

첨단 운전자지원 시스템 기술 고도화에 따라 자율 주행 기술은 미래의 스마트 교통 시스템 주요 구성 요소로 주목받고 있지만 꾸준히 발생하는 자율주행차의 사고로 인해 안전성에 대한 체계적인 검증이 요구되고 있다. 특히, 예상치 못하게 제어권이 해제되어 운전자의 대응 시간이 충분하지 않은 상황적 범위라고 칭할 수 있는 핸디캡 구간이 반복적으로 발생하는 도시부 도로에서 자율주행차뿐만 아니라 보행자와 같은 취약한 도로 이용자들의 안전성을 확보하기 위해서는 기술적/ 제도적 접근과 자율 차 사고 원인에 대한 지속적인 이해가 필요하다. 따라서 본 연구는 캘리포니아 자동차관리국에서 제공하는 자율 차 사고 보고서 중 세부 영향 요인과 변수를 추출하기 위해 사고 세부 기록 데이터를 이용하였고 사고 표본 보완을 위해 베이지안 확률추론 기반의 잠재 계층분석과 순서형 프로빗 모형을 통해 계층별 사고 심각도와 설명 변수 간 상관성을 설명하였다. 그 결과 보행자, 자전거 이용자와 같은 취약한 도로 이용자와 관련된 사고는 주로 도로 이용자들이 교차가 발생하는 버스정류장 또는 자전거 도로가 있는 공간에서 발생하고 어두운 조명시설일 때 사고 심각도가 증가하였다. 반면에 나머지 사고의 경우, 기상 조건, 자율 차의 움직임, 주야 등에 따라 계층이 세분화되고 사고 심각도가 증가하였다. 특히, 그리고 기하구조와 기상 조건에 대한 이질성을 고려하였을 때, 고정 효과에 비해 임의 효과를 이용한 베이지안 순서형 프로빗 모형 경우, 분산의 크기가 작아져 신뢰구간 범위가 좁아진 것을 확인할 수 있었다. 이러한 연구 결과를 바탕으로 세분화된 자율 차 안전성 평가시나리오를 구성하면 Level 4-Level 5 수준의 자율 주행 기술에 대한 보다 효율적이고 합리적인 안전성 평가가 가능할 것이라고 기대한다.

키워드

자율주행차 사고 보고서

베이지안 잠재 계층분석

임의 효과

사고 심각도

텍스트마이닝

References

Ahlmann-Eltze C., Yau C. (2018), MixDir: Scalable Bayesian Clustering for High-Dimensional Categorical Data, In 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), 526-539, IEEE. 10.1109/DSAA.2018.00068

Arteaga C., Paz A., Park J. (2020), Injury Severity on Traffic Crashes: A Text Mining with an Interpretable Machine-Learning Approach, Safety Science, 132, 104988. 10.1016/j.ssci.2020.104988

Asgarzadeh M., Fischer D., Verma S. K., Courtney T. K., Christiani D. C. (2018), The Impact of Weather, Road Surface, Time‐of‐Day, and Light Conditions on Severity of Bicycle‐Motor Vehicle Crash Injuries, American Journal of Industrial Medicine, 61(7), 556-565. 10.1002/ajim.2284929635849

Ashraf M. T., Dey K., Mishra S., Rahman M. T. (2021), Extracting Rules from Autonomous-Vehicle-Involved Crashes by Applying Decision Tree and Association Rule Methods, Transportation Research Record, 2675(11), 522-533. 10.1177/03611981211018461

Chan C. Y. (2006), Defining Safety Performance Measures of Driver-Assistance Systems for Intersection Left-Turn Conflicts, In 2006 IEEE Intelligent Vehicles Symposium, 25-30, IEEE.

Chen Y., Luo R., Yang H., King M., Shi Q. (2020), Applying Latent Class Analysis to Investigate Rural Highway Single-Vehicle Fatal Crashes in China, Accident Analysis & Prevention, 148, 105840. 10.1016/j.aap.2020.10584033166878

Das S., Dutta A., Tsapakis I. (2020), Automated Vehicle Collisions in California: Applying Bayesian Latent Class Model, IATSS Research, 44(4), 300-308. 10.1016/j.iatssr.2020.03.001

Deb S., Strawderman L., Carruth D. W., DuBien J., Smith B., Garrison T. M. (2017), Development and Validation of a Questionnaire to Assess Pedestrian Receptivity Toward Fully Autonomous Vehicles, Transportation Research Part C: Emerging Technologies, 84, 178-195. 10.1016/j.trc.2017.08.029

Guo Y., Liu P., Wu Y., Chen J. (2020), Evaluating How Right-Turn Treatments Affect Right-Turn-on-Red Conflicts at Signalized Intersections, Journal of Transportation Safety & Security, 12(3), 419-440. 10.1080/19439962.2018.1490368

Hagenzieker M. P., Van Der Kint S., Vissers L., Van Schagen I. N. G., De Bruin J., Van Gent P., Commandeur J. J. (2020), Interactions Between Cyclists and Automated Vehicles: Results of a Photo Experiment, Journal of Transportation Safety & Security, 12(1), 94-115. 10.1080/19439962.2019.1591556

Hoogendoorn R., Van Arem B., Hoogendoorn S. (2014), Automated Driving, Traffic Flow Efficiency, and Human Factors, Transportation Research Record, 2422, 113-120. 10.3141/2422-13

Jeon H., Kim J. (2021), Analysis on Handicaps of Automated Vehicle and Their Causes Using IPA and FGI, The Journal of The Korea Institute of Intelligent Transport Systems, 20(3), 34-46. 10.12815/kits.2021.20.3.34

KICT (2020), Improvement Road Infrastructures to Strengthen Driving Safety of Automated DrivingCar, The Second report, South Korea.

Kutela B., Das S., Dadashova B. (2022), Mining Patterns of Autonomous Vehicle Crashes Involving Vulnerable Road Users to Understand the Associated Factors, Accident Analysis & Prevention, 165, 106473. 10.1016/j.aap.2021.10647334774280

Kwayu K. M., Kwigizile V., Lee K., Oh J. S. (2021), Discovering Latent Themes in Traffic Fatal Crash Narratives Using Text Mining Analytics and Network Topology, Accident Analysis & Prevention, 150, 105899. 10.1016/j.aap.2020.10589933285445

Kwayu K. M., Kwigizile V., Zhang J., Oh J. S. (2020), Semantic N-gram Feature Analysis and Machine Learning: Based Classification of Drivers' Hazardous Actions at Signal-Controlled Intersections, Journal of Computing in Civil Engineering, 34(4), 04020015. 10.1061/(ASCE)CP.1943-5487.0000895

Lee H. J., Kang M. H., Song J. I., Hwang K. Y. (2023a), Development of Autonomous Vehicle Traffic Accident Scenarios in Urban Areas Based on Real-World Accident Data Using Association Rule Mining, J. Korean Soc. Transp., 41(3), Korean Society of Transportation, 375-393. 10.7470/jkst.2023.41.3.375

Lee S. Y., Han S. J., Chung Y. S. (2020), Injury Severity of Freeway Crashes in Rainy Weather Using an Ordered Probit Model, J. Transp. Res, 27(1), 1-11.

Lee S., Arvin R., Khattak A. J. (2023b), Advancing Investigation of Automated Vehicle Cashes Using Text Analytics of Crash Narratives and Bayesian Analysis, Accident Analysis & Prevention, 181, 106932. 10.1016/j.aap.2022.10693236580765

Li Y., Lord-Bessen J., Shiyko M., Loeb R. (2018), Bayesian Latent Class Analysis Tutorial, Multivariate Behavioral Research, 53(3), 430-451. 10.1080/00273171.2018.142889229424559PMC6364555

Millard-Ball A. (2018), Pedestrians, Autonomous Vehicles, and Cities, Journal of Planning Education and Research, 38(1), 6-12. 10.1177/0739456X16675674

Morando M. M., Tian Q., Truong L. T., Vu H. L. (2018), Studying the Safety Impact of Autonomous Vehicles Using Simulation-Based Surrogate Safety Measures, Journal of Advanced Transportation. 10.1155/2018/6135183

Morris A. P., Haworth N., Filtness A., Nguatem D. P. A., Brown L., Rakotonirainy A., Glaser S. (2021), Autonomous Vehicles and Vulnerable Road-Users-Important Considerations and Requirements Based on Crash Data from Two Countries, Behavioral Sciences, 11(7), 101. 10.3390/bs1107010134356718PMC8300997

Novat N., Kidando E., Kutela B., Kitali A. E. (2023), A Comparative Study of Collision Types Between Automated and Conventional Vehicles Using Bayesian Probabilistic Inferences, Journal of Safety Research, 84, 251-260. 10.1016/j.jsr.2022.11.00136868654

Olszewski P., Szagała P., Rabczenko D., Zielińska A. (2019), Investigating Safety of Vulnerable Road Users in Selected EU Countries, Journal of Safety Research, 68, 49-57. 10.1016/j.jsr.2018.12.00130876520

Salon Deborah, Andrew McIntyre (2018), Determinants of Pedestrian and Bicyclist Crash Severity By Party at Fault in San Francisco, CA, Accident Analysis & Prevention, 110, 149-160. 10.1016/j.aap.2017.11.00729136559

Sohrabi S., Khodadadi A., Mousavi S. M., Dadashova B., Lord D. (2021), Quantifying the Automated Vehicle Safety Performance: A Scoping Review of the Literature, Evaluation of Methods, and Directions for Future Research, Accident Analysis & Prevention, 152, 106003. 10.1016/j.aap.2021.10600333571922

Spiegelhalter D. J., Best N. G., Carlin B. P., van der Linde A. (2002), Bayesian Measures of Model Complexity and Fit (with discussion), Journal of the Royal Statistical Society, Series B, 64, 583-639. 10.1111/1467-9868.00353

Wang X., Zhao D., Peng H., LeBlanc D. J. (2017), Analysis of Unprotected Intersection Left-Turn Conflicts Based on Naturalistic Driving Data, In 2017 IEEE Intelligent Vehicles Symposium (IV), 218-223, IEEE. 10.1109/IVS.2017.7995723

White A., Murphy T. B. (2014), BayesLCA: An R Package for Bayesian Latent Class Analysis, Journal of Statistical Software, 61, 1-28. 10.18637/jss.v061.i13

Xie Y., Zhang Y., Liang F. (2009), Crash Injury Severity Analysis Using Bayesian Ordered Probit Models, Journal of Transportation Engineering, 135(1), 18-25. 10.1061/(ASCE)0733-947X(2009)135:1(18)

Yuan Q., Xu X., Wang T., Chen Y. (2022a), Investigating Safety and Liability of Autonomous Vehicles: Bayesian Random Parameter Ordered Probit Model Analysis, Journal of Intelligent and Connected Vehicles, 5(3), 199-205. 10.1108/JICV-04-2022-0012

Yuan Q., Zhai X., Ji W., Yang T., Yu Y., Yu S. (2022b), Correlation Analysis on Accident Injury and Risky Behavior of Vulnerable Road Users Based on Bayesian General Ordinal Logit Model, Sustainability, 14(23), 16048. 10.3390/su142316048

Zhu H., Zhu S., Iryo-Asano M., Nakamura H. (2022), Investigating Driver Reactions to Movements of Autonomous Vehicle in Permitted Right Turn Through Driving Simulator Experiments, Transportation Research Part F: Traffic Psychology and Behaviour, 89, 385-398. 10.1016/j.trf.2022.06.018

Zhu S., Meng Q. (2022), What Can We Learn from Autonomous Vehicle Collision Data on Crash Severity? A Cost-Sensitive CART Approach, Accident Analysis & Prevention, 174, 106769. 10.1016/j.aap.2022.10676935858521

Information

Publisher :Korean Society of Transportation
Publisher(Ko) :대한교통학회
Journal Title :Journal of Korean Society of Transportation
Journal Title(Ko) :대한교통학회지
Volume : 42
No :1
Pages :77-93
Received Date : 2023-12-04
Revised Date : 2023-12-06
Accepted Date : 2023-01-15
DOI :https://doi.org/10.7470/jkst.2024.42.1.077

Journal of Korean Society of Transportation ISSN:1229-1366(Print) 2234-4217(Online) 대한교통학회지

All Issue