The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

Evaluation of Autonomous Driving Conservativeness by Urban Intersections with Real-World Data

실도로 데이터를 활용한 교차로 유형별 자율주행 보수성 평가 연구

  • Jeonghoon Jee (Dept. of Transportation and Logistics Eng., Hanyang University ERICA) ;
  • Kyeong-Pyo Kang (Center for Connected and Automated Driving Research, Korea Transport Institute) ;
  • Hoyoon Lee (Dept. of Transportation and Logistics Eng., Hanyang University ERICA) ;
  • Cheol Oh (Dept. of Transportation and Logistics Eng., Hanyang University ERICA)
  • 지정훈 (한양대학교 ERICA 교통물류공학과) ;
  • 강경표 (한국교통연구원 자율협력주행기술연구팀) ;
  • 이호윤 (한양대학교 ERICA 교통물류공학과) ;
  • 오철 (한양대학교 ERICA 교통물류공학과)
  • Received : 2024.06.24
  • Accepted : 2024.08.27
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

In mixed traffic conditions, the conservative driving behavior of autonomous vehicles (AV) would negatively affect overall traffic performance. In order to manage mobility and safety in mixed traffic conditions, it is essential to scientifically evaluate driving behavior using autonomous driving data collected from real-world. This study proposed a methodology to evaluate the driving behavior of autonomous vehicles (AV) and manual vehicles (MV) at different types of intersections using the Waymo Open Dataset. Urban street were identified through video data, and the autonomous driving conservativeness index (ADCI) was devised to compare the difference in time-to-collision (TTC) based conflict rates between AV and MV in car following situations. The results showed that unsignalized 4-way intersections had the highest ADCI value, indicating greater conservativeness in driving behavior. This indicates the necessity of analyzing the driving behavior of each road section and deriving support measures to prevent AV from negatively affecting the overall traffic performance in mixed traffic conditions. The methodology of this study is expected to serve as foundational for analyzing factors affecting AV using real-world datasets.

혼합교통류 환경에서 자율차의 보수적인 주행행태는 전체 교통흐름에 부정적인 영향을 줄 수 있다. 선제적으로 혼합교통류의 이동성과 안전성을 관리하기 위해서는 실도로에서 수집된 자율주행 데이터를 활용하여 주행행태를 과학적 평가하는 것이 필수적이다. 본 연구에서는 Waymo Open Dataset을 활용하여 단속류 교차로 유형별 자율차와 비자율차의 주행행태를 비교 평가하는 방법론을 제안하였다. 영상자료를 통해 도로구간을 구분하고, 차량 추종 상황에서 자율차와 비자율차의 Time-to Collision(TTC)를 기반으로 상충률 차이를 비교하는 자율주행 보수성 지표(Autonomous Driving Conservativeness Index, ADCI)를 고안하였다. 분석 결과 모든 TTC 임계값에서 4지 비신호 교차로가 높은 ADCI로 관찰되었다. 이는 교차로 유형 중 4지 비신호 교차로에서 자율차의 주행 보수성(Conservativeness)이 높아, 비자율차 대비 보수적이게 주행함을 의미한다. 장기간 지속될 혼합교통류 환경에서 자율차가 전체 교통흐름에 부정적인 영향을 주지 않기 위해 도로구간별 주행행태를 분석하고 지원방안을 도출할 필요함을 시사한다. 본 연구의 방법론은 실도로 데이터셋 기반 자율차에 영향을 미치는 요인들을 분석하는 기초 자료로 활용될 것으로 기대된다.

Keywords

Acknowledgement

본 연구는 국토교통부/국토교통과학기술진흥원의 지원으로 수행되었음(RS-2022-00143579, 자율주행 Lv.4/4+ 공유차(Car-Sharing) 서비스 기술 개발)

References

  1. Deluka Tibljas, A., Giuffre, T., Surdonja, S. and Trubia, S.(2018), "Introduction of Autonomous Vehicles: Roundabouts design and safety performance evaluation", Sustainability, vol. 10, no. 4, 1060.
  2. Hu, X., Zheng, Z., Chen, D. and Sun, J.(2023a), "Autonomous vehicle's impact on traffic: Empirical evidence from Waymo Open Dataset and implications from modelling", IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 6, pp.6711-6724.
  3. Hu, X., Zheng, Z., Chen, D., Zhang, X. and Sun, J.(2022), "Processing, assessing, and enhancing the Waymo autonomous vehicle open dataset for driving behavior research", Transportation Research Part C: Emerging Technologies, vol. 134, 103490.
  4. Hu, X., Zheng, Z., Zhang, X., Chen, D. and Sun, J.(2023b), "Vehicle trajectory data processed from the Waymo Open Dataset", Mendeley Data, vol. 3, doi: 10.17632/wfn2c3437n.3.
  5. Jo, Y., Jung, A. R., Oh, C., Park, J. H. and Yun, D. G.(2022), "Suitability evaluation for simulated maneuvering of autonomous vehicles", The Journal of The Korea Institute of Intelligent Transport Systems, vol. 21, no. 2, pp.183-200.
  6. Jung, A. R., Jo, Y. and Oh, C.(2023), "A methodology of identifying hazardous freeway segment based on multi-agent driving simulations for the mixed situation of autonomous and manual vehicles", Journal of Korean Society of Transportation, vol. 41, no. 4, pp.495-508, doi:10.7470/jkst.2023.41.4.495
  7. Ko, W. R, Yun, I. S., Park, S. M., Jeong, H. R. and Park, S. H.(2022), "Derivation of assessment scenario elements for automated vehicles in the expressway mainline section", The Journal of The Korea Institute of Intelligent Transport Systems, vol. 21, no. 1, pp.221-239.
  8. Kuang, Y., Qu, X. and Wang, S.(2015), "A tree-structured crash surrogate measure for freeways", Accident Analysis & Prevention, vol. 77, pp.137-148.
  9. Li, G., Li, S., Li, S. and Qu, X.(2022), "Continuous decision making for autonomous driving at intersections using deep deterministic policy gradient", IET Intelligent Transport Systems, vol. 16, no. 12, pp.1669-1681.
  10. Li, Y., Wu, D., Lee, J., Yang, M. and Shi, Y.(2020), "Analysis of the transition condition of rear-end collisions using time-to-collision index and vehicle trajectory data", Accident Analysis & Prevention, vol. 144, 105676.
  11. Mahmud, S. S., Ferreira, L., Hoque, M. S. and Tavassoli, A.(2017), "Application of proximal surrogate indicators for safety evaluation: A review of recent developments and research needs", IATSS Research, vol. 41, no. 4, pp.153-163.
  12. Meng, Q. and Qu, X.(2012), "Estimation of rear-end vehicle crash frequencies in urban road tunnels", Accident Analysis & Prevention, vol. 48, pp.254-263.
  13. Seth, D. and Cummings, M. L.(2019), "Traffic efficiency and safety impacts of autonomous vehicle aggressiveness", Simulation, vol. 19, 20.
  14. Szucs, H. and Hezer, J.(2022), "Road safety analysis of autonomous vehicles: An overview", Periodica Polytechnica Transportation Engineering, vol. 50, no. 4, pp.426-434.
  15. Vogel, K.(2003), "A comparison of headway and time to collision as safety indicators", Accident Analysis & Prevention, vol. 35, no. 3, pp.427-433.
  16. Wang, Y., Farah, H., Yu, R., Qiu, S. and van Arem, B.(2023), "Characterizing behavioral differences of autonomous vehicles and human-driven vehicles at signalized intersections based on Waymo Open Dataset", Transportation Research Record, vol. 2677, no. 11, pp.324-337.
  17. WAYMO open dataset, [online] Available: https://waymo.com/open/
  18. Wen, X., Cui, Z. and Jian, S.(2022), "Characterizing car-following behaviors of human drivers when following automated vehicles using the real-world dataset", Accident Analysis & Prevention, vol. 172, 106689.