Development of Autonomous Vehicle Traffic Accident Scenarios in Urban Areas Based on Real-World Accident Data Using Association Rule Mining

Hojun Lee; Minhee Kang; Jaein Song; Keeyeon Hwang

doi:10.7470/jkst.2023.41.3.375

All Issue

2023 Vol.41, Issue 3 Preview Page

Article

Development of Autonomous Vehicle Traffic Accident Scenarios in Urban Areas Based on Real-World Accident Data Using Association Rule Mining 자율주행차 실사고 데이터를 활용한 연관규칙 분석 기반 자율주행차 도심부 사고 시나리오 방법론 개발

30 June 2023. pp. 375-393

PDF XML

Abstract

Although traffic accidents are expected to decrease with the development of autonomous vehicles, safety and reliability issues are emerging as traffic accidents with autonomous vehicles are constantly occurring. To address this issue, an autonomous vehicle safety evaluation scenario is utilized that is directly linked to vehicle safety. Therefore, ensuring the reliability and specificity of the scenario is crucial. Accordingly, we proposed a methodology for creating a reliable and specific autonomous vehicle accident scenario in urban areas to evaluate the safety of autonomous vehicles. To ensure the reliability of the scenario, we utilized the DMV collision report, which contains autonomous vehicle accident data. Additionally, to improve specificity, we employed the Apriori algorithm of association rule analysis, a data mining technique. After analyzing the association rules using the DMV collision report, we identified approximately 300,000 association rules and derived a combination of various accident factors that were highly related to the type of vehicle collision. To provide specific scenarios for evaluating the safety of autonomous vehicles, we analyzed the PEGASUS project and the CETRAN project and finally selected nine scenario factors. Based on the association rules that included all of the scenario factors, we presented six autonomous vehicle traffic accident scenarios in the urban areas. These scenarios are expected to be utilized as a standardized benchmark for evaluating the safety of autonomous vehicles.

Keywords

apriori algorithm

association rule mining

autonomous vehicle

dmv collision report

traffic accident scenario

자율주행차 개발에 따라 교통사고 감소 등이 기대되고 있으나, 자율주행차 사고가 끊임없이 발생하고 있어 안전성 및 신뢰성 문제가 대두되고 있다. 이를 해소하기 위해 자율주행차 안전성 평가 시나리오가 활용되고 있으며, 이는 차량의 안전과 직결되어 있어 시나리오의 신뢰성 및 구체성이 필수적으로 요구된다. 이에 본 연구는 자율주행차 안전성 평가를 위해 신뢰성과 구체성을 확보한 자율주행차의 도심부 사고 시나리오 생성 방법론을 제안하였다. 시나리오의 신뢰성을 확보하기 위해 자율주행차 실사고 데이터인 DMV collision report를 활용하였으며, 구체성을 확보하기 위해 데이터 마이닝 기법인 연관규칙 분석의 Apriori 알고리즘을 활용하였다. DMV collision report를 활용하여 연관규칙을 분석한 결과, 약 300,000개의 연관규칙이 확인되었으며, 차량 충돌 형태와 연관성이 높은 다양한 사고 요인의 조합을 도출하였다. 구체적인 시나리오를 제시하기 위해 PEGASUS 프로젝트와 CETRAN 프로젝트를 분석하여 최종적으로 9개의 시나리오 요인을 선별하였으며, 해당 시나리오 요인을 모두 포함한 연관규칙을 기반으로 6개의 자율주행차 도심부 사고 시나리오를 제시하였다. 본 연구에서 제시한 6개의 시나리오는 자율주행차의 안전성 평가를 위한 시나리오로 활용 가능할 것으로 기대된다.

키워드

Apriori 알고리즘

연관규칙 분석

자율주행차

DMV 사고 보고서

사고 시나리오

References

Agrawal R., Srikant R. (1994), Fast Algorithms for Mining Association Rules, In Proc. 20th int. conf. Very Large Data Bases, VLDB, 1215, 487-499.

Alambeigi H., McDonald A. D., Tankasala S. R. (2020), Crash Themes in Automated Vehicles: A Topic Modeling Analysis of the California Department of Motor Vehicles Automated Vehicle Crash Database, arXiv preprint arXiv:2001.11087.

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

Bahiru T. K., Singh D. K., Tessfaw E. A. (2018), Comparative Study on Data Mining Classification Algorithms for Predicting Road Traffic Accident Severity, In 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), 1655-1660, IEEE. 10.1109/ICICCT.2018.8473265

Bhin M. Y., Son S. K. (2018), Analysis of Factors Influencing Traffic Accident Severity According to Gender of Bus Drivers, J. Korean Soc. Transp., 36(6), Korean Society of Transportation, 440-451. 10.7470/jkst.2018.36.6.440

Bhin M. Y., Son S. K., Kim J. Y., Chae W. R. (2020), A Study on the Analysis of Traffic Accidents by Road Type considering Traffic Safety Signs on the Urban Road, J. Korean Soc. Transp., 38(5), Korean Society of Transportation, 390-403. 10.7470/jkst.2020.38.5.390

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

de Gelder E., den Camp O. O., de Boer N. (2020), Scenario Categories for the Assessment of Automated Vehicles, CETRAN, Singapore, Version, 1.

DrissiTouzani H., Faquir S., Yahyaouy A. (2020), Data Mining Techniques to Analyze Traffic Accidents Data: Case Application in Morocco, In 2020 Fourth International Conference On Intelligent Computing in Data Sciences (ICDS), 1-4, IEEE. 10.1109/ICDS50568.2020.9268729

Favarò F. M., Nader N., Eurich S. O., Tripp M., Varadaraju N. (2017), Examining Accident Reports Involving Autonomous Vehicles in California, PLoS one, 12(9), e0184952. 10.1371/journal.pone.018495228931022PMC5607180

Goodall N. J. (2014), Ethical Decision Making During Automated Vehicle Crashes, Transportation Research Record, 2424(1), 58-65. 10.3141/2424-07

https://www.dmv.ca.gov

ISO (2018), 26262 - Road vehicles - Functional Safety.

Kang M., Im I. J., Song J., Hwang K. (2022a), Is Only the Dedicated Lane for Automated Vehicles Essential in the Future? The Dedicated Lanes Optimal Operating System Evaluation, Sustainability, 14(18), 11490. 10.3390/su141811490

Kang M., Lee W., Hwang K., Yoon Y. (2022b), Vision Transformer for Detecting Critical Situations and Extracting Functional Scenario for Automated Vehicle Safety Assessment, Sustainability, 14(15), 9680. 10.3390/su14159680

Kang M., Song J., Hwang K. (2022c), The Extraction of Automated Vehicles Traffic Accident Factors and Scenarios Using Real-World Data, In Congress on Intelligent Systems: Proceedings of CIS 2021, 1, 1-15, Singapore: Springer Nature Singapore. 10.1007/978-981-16-9416-5_1

Kang M., Song J., Hwang K. (2020), For Preventative Automated Driving System (PADS): Traffic Accident Context Analysis Based on Deep Neural Networks, Electronics, 9(11), 1829. 10.3390/electronics9111829

Kim H. J., Jeon G. S., Jang J. A., Yoon I. S. (2020), Analysis of Factors Affecting Buses and Trucks Crash Severity Using Meta Analysis, J. Korean Soc. Transp., 38(6), Korean Society of Transportation, 520-535. 10.7470/jkst.2020.38.6.520

Kumar S., Toshniwal D. (2016), A Data Mining Approach to Characterize road Accident Locations, Journal of Modern Transportation, 24, 62-72. 10.1007/s40534-016-0095-5

Leilabadi S. H., Schmidt S. (2019), In-depth Analysis of Autonomous Vehicle Collisions in California, In 2019 IEEE Intelligent Transportation Systems Conference (ITSC), 889-893, IEEE. 10.1109/ITSC.2019.8916775

Lenard J., Badea-Romero A., Danton R. (2014), Typical Pedestrian Accident Scenarios for the Development of Autonomous Emergency Braking Test Protocols, Accident Analysis & Prevention, 73, 73-80. 10.1016/j.aap.2014.08.01225180785

Li L., Shrestha S., Hu G. (2017), Analysis of Road Traffic Fatal Accidents Using Data Mining Techniques, In 2017 IEEE 15th International Conference on Software Engineering Research, Management and Applications (SERA), 363-370, IEEE. 10.1109/SERA.2017.7965753

Liu Q., Wang X., Wu X., Glaser Y., He L. (2021), Crash Comparison of Autonomous and Conventional Vehicles Using Pre-crash Scenario Typology, Accident Analysis & Prevention, 159, 106281. 10.1016/j.aap.2021.10628134273622

Muhammad L. J., Sani S., Yakubu A., Yusuf M. M., Elrufai T. A., Mohammed I. A., Nuhu A. M. (2017), Using Decision Tree Data Mining Algorithm to Predict Causes of Road Traffic Accidents, Its Prone Locations and Yime Along Kano-Wudil Highway, Int J Database Theory Appl, 10(11), 197-208. 10.14257/ijdta.2017.10.1.18

Najm W. G., Smith J. D., Yanagisawa M. (2007), Pre-crash Scenario Typology for Crash Avoidance Research (No.DOT-VNTSC-NHTSA-06-02), United States. National Highway Traffic Safety Administration.

Nitsche P., Thomas P., Stuetz R., Welsh R. (2017), Pre-crash Scenarios at Road Junctions: A Clustering Method for Car Crash Data, Accident Analysis & Prevention, 107, 137-151. 10.1016/j.aap.2017.07.01128841448

Park J. S., Kim T. Y., Yoo D. S. (2006), Development of Traffic Accident Prediction Models by Correlation between Environment factor and Traffic Accident, The 53rd Conference of KST, Korean Society of Transportation, 350-359.

PEGASUS Project Consortium (2019), PEGASUS Method: An Overview, Available: https://www.pegasusprojekt.de/?les/tmpl/Pegasus-Abschlussveranstaltung/PEGASUSGesamtmethode.Pdf

Riedmaier S., Ponn T., Ludwig D., Schick B., Diermeyer F. (2020), Survey on Scenario-based Safety Assessment of Automated Vehicles, IEEE, 8, 87456-87477. 10.1109/ACCESS.2020.2993730

Shanthi S., Ramani R. G. (2012), Feature Relevance Analysis and Classification of Road Traffic Accident Data Through Data Mining Techniques, In Proceedings of the world congress on engineering and computer science, 1, 24-26, sn.

Son S. N., Lee J. Y., Jang K. H. (2021), Development of Demonstration Scenarios for Autonomous Cooperative Driving on Urban Roads, Transportation Technology and Policy, 18(5), Korean Society of Transportation, 61-68.

Song Y., Chitturi M. V., Noyce D. A. (2021), Automated Vehicle Crash Sequences: Patterns and Potential Uses in Safety Testing, Accident Analysis & Prevention, 153, 106017. 10.1016/j.aap.2021.10601733578268

Steimle M., Menzel T., Maurer M. (2021), ‘Toward a Consistent Taxonomy for Scenario-Based Development and Test Approaches for Automated Vehicles: A Proposal for a Structuring Framework, a Basic Vocabulary, and Its Application, IEEE, 9, 147828-147854. 10.1109/ACCESS.2021.3123504

Sui B., Lubbe N., Bärgman J. (2019), A cCustering Approach to Developing Car-to-two-wheeler Test Scenarios for the Assessment of Automated Emergency Braking in China Using in-depth Chinese crash data, Accident Analysis & Prevention, 132, 105242. 10.1016/j.aap.2019.07.01831446097

Taamneh M., Alkheder S., Taamneh S. (2017), Data-mining Techniques for Traffic Accident Modeling and Prediction in the United Arab Emirates, Journal of Transportation Safety & Security, 9(2), 146-166. 10.1080/19439962.2016.1152338

Torres J., Li Y., Zhang J. (2021), Investigating Traffic Crashes Involving Autonomous Vehicles, In IIE Annual Conference, Proceedings (1046-1051), Institute of Industrial and Systems Engineers (IISE).

Yu R., Ai H., Gao Z. (2020), Identifying High Risk Driving Scenarios Utilizing a CNN-LSTM Analysis Approach, In 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), 1-6, IEEE. 10.1109/ITSC45102.2020.9294547

Yuan Q., Xu X., Zhau J. (2020), Paving the Way for Autonomous Vehicle Testing in Accident Scenario Analysis of Yizhuang Development Zone in Beijing, In CICTP 2020, 62-72. 10.1061/9780784482933.006

Information

Publisher :Korean Society of Transportation
Publisher(Ko) :대한교통학회
Journal Title :Journal of Korean Society of Transportation
Journal Title(Ko) :대한교통학회지
Volume : 41
No :3
Pages :375-393
Received Date : 2023-04-21
Revised Date : 2023-05-08
Accepted Date : 2023-05-31
DOI :https://doi.org/10.7470/jkst.2023.41.3.375

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

All Issue