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

  • 제23권5호
  • /
  • Pages.338-354
  • /
  • 2024
  • /
  • 1738-0774(pISSN)
  • /
  • 2384-1729(eISSN)
한국ITS학회 (The Korea Institute of Intelligent Transport Systems)
권호 표지
DOI QR코드

DOI QR Code

협력주행 엣지 인프라에 적합한 차량 리스크 필드 모형 구성에 관한 연구

Research on Vehicle Risk Field Model for Edge Infrastructure at Cooperative Driving

  • 고자경 (과학기술연합대학원대학교 건설환경공학과) ;
  • 양인철 (한국건설기술연구원 도로교통연구본부 )
  • Jakyung Ko (Dept. of Civil & Environmental Engineering, University of Science and Technology) ;
  • Inchul Yang (Dept. of Highway & Transportation, Korea Institute of Civil Engineering and Building Engineering)
  • 투고 : 2024.08.19
  • 심사 : 2024.10.14
  • 발행 : 2024.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

협력주행 기술의 발전에 따라 자율주행시스템은 상호 동적 상태와 주행의도 정보를 실시간으로 공유하고, 도로 상 모든 차량의 동적 상태 정보를 이용하여 다중 차량의 영향력을 종합적으로 나타내는 모형의 개발이 가능하게 되었다. 본 논문에서는 자율주행 차량의 특정 지점의 위험도 평가 및 안전한 국지적 경로 생성에 활용하기 위하여, 인프라를 중심으로 하는 협력주행 환경의 엣지 RSU에서 연산할 때, 차량의 실시간 위치, 속도, 가속도와 같은 상태 정보를 기반으로 차량 간 상호 작용하는 잠재적인 힘으로 인한 위험성을 설명할 수 있으며, 기존 모형과 비교하여 연산 성능이 우수한 리스크 필드 모형을 구성하고자 한다. 제안하는 모형은 차량의 속도, 가속도와 같은 동적 특성 변화에 따라 영향력(위험성) 범위와 크기가 달라지며, 위험성의 범위를 중첩적으로 표현 가능하고, 연산 시간이 기존 모형에 비해 감소하여 인프라 중심의 협력주행에서 엣지 RSU가 다중 차량을 실시간으로 연산하기에 적합한 특징을 갖는다.

With the development of cooperative driving technology, automated driving systems can share dynamic state and intention information in real-time. Accordingly, it has become possible to develop a model that comprehensively represents the influence of multiple vehicles by integrating the shared information to obtain the dynamic state information of all vehicles on the road in real time. This study developed a risk field model that can explain interactions between vehicles in real-time information of vehicles when calculating in an edge RSU in an infrastructure-centered cooperative driving environment to be used to assess the risk of a specific point of an autonomous vehicle and create a safe local route. The model showed that the range of risk influences increased as the velocity increased, the bias changed depending on the direction of acceleration, and caculating time decreases.

키워드

과제정보

본 연구는 국토교통부/국토교통과학기술진흥원의 지원으로 수행되었음(과제정보 : (RS-2022-00142565) 인프라 가이던스를 통한 자율차 주행 기술 개발).

참고문헌

  1. Arun, A., Haque, M. M., Washington, S. and Mannering, F.(2023), "A physics-informed road user safety field theory for traffic safety assessments applying artificial intelligence-based video analytics", Analytic Methods in Accident Research, vol. 37, doi: 10.1016/j.amar.2022.100252.
  2. Gerdes, J. C. and Rossetter, E. J.(2001), "A unified approach to driver assistance systems based on artificial potential fields", Journal of Dynamic Systems, Measurment, and Control, vol. 123, no. 3, pp.431-438.
  3. Jeon, H., Yang, I., Kim, H., Lee, J., Kim, S. and Jang, J.(2022b), "Some lessons learned from previous studies in cooperative driving automation", Journal of Digital Contents Society, vol. 23, no. 7, pp.1331-1340.
  4. Jeon, H., Yang, I., Kim, H., Lee, J., Kim, S., Jang, J. and Kim, J.(2022a), "Some lessons learned from previous studies in cooperative driving automation", Journal of Korean Society of Intelligent Transport Systems, vol. 21, no. 4, pp.62-77.
  5. Joo, Y. J., Kim, E. J., Kim, D. K. and Park, P. Y.(2023), "A generalized driving risk assessment on high-speed highways using field theory", Analytic Methods in Accident Research, vol. 40, 100303.
  6. Khatib, O.(1985), "Real-time obstacle avoidance for manipulators and mobile robots", In Proceedings 1985 IEEE International Conference on Robotics and Automation, vol. 2, pp.500-505.
  7. Kolekar, S., Petermeijer, B., Boer, E., de Winter, J. and Abbink, D.(2021), "A risk field-based metric correlates with driver's perceived risk in manual and automated driving: A test-track study", Transportation Research Part C: Emerging Technologies, vol. 133, doi: 10.1016/j.trc.2021.103428.
  8. Li, L., Gan, J., Ji, X., Qu, X. and Ran, B.(2022), "Dynamic driving risk potential field model under the connected and automated vehicles environment and its application in car-following modeling", IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 1, pp.122-141.
  9. Li, Y. and Chen, Y.(2018), "A new method based on field strength for road infrastructure risk assessment", Journal of Advanced Transportation, doi: 10.1155/2018/6379146.
  10. Ma, Y., Dong, F., Yin, B. and Lou, Y.(2023), "Real-time risk assessment model for multi-vehicle interaction of connected and autonomous vehicles in weaving area based on risk potential field", Physica A: Statistical Mechanics and its Applications, vol. 620, doi: 10.1016/j.physa.2023.128725.
  11. Ni, D.(2011), "A unified perspective on traffic flow theory, part I: the field theory", Icctp 2011: Towards Sustainable Transportation Systems, pp.4227-4243.
  12. Oh, S. M., Choi, J. H., Jang, K. T. and Yoon. J. W.(2024), "Analysis of autonomous vehicles risk cases for developing level 4+ autonomous driving test scenarios: Focusing on perceptual blind", Journal of Korean Society of Intelligent Transport Systems, vol. 23, no. 2, pp.173-188.
  13. Ploeg, C., Nyberg, T., Sanchez, J. M. G., Silvas, E. and van de Wouw, N.(2024), "Overcoming fear of the unknown: Occlusion-aware model-predictive planning for automated vehicles using risk fields", IEEE Transactions on Intelligent Transportation Systems, doi: 10.1109/TITS.2024.3382507.
  14. Reichardt, D. and Schick, J.(1994), "Collision avoidance in dynamic environments applied to autonomous vehicle guidance on the motorway", In Proceedings of the Intelligent Vehicles' 94 Symposium, pp.74-78.
  15. SAE(2021), Surface vehicle information report - Taxonomy and definitions for terms related to cooperative driving automation for on-road motor vehicles, SAE International.
  16. SAE(2022), Surface vehicle standard - V2X communications message set dictionary, SAE Internationalrface Vehicle Standard - V2X Communications Message Set Dictionary.
  17. Tan, H., Lu, G. and Liu, M.(2022), "Risk field model of driving and its application in modeling car-following behavior", IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 8, pp.11605-11620.
  18. Tan, S., Wang, Z. and Zhong, Y.(2024), "RCP RF: A comprehensive road car pedestrian risk management framework based on driving risk potential field", IET Intelligent Transport Systems, doi: 10.1049/itr2.12508.
  19. Wang, J. Q., Wu, J. and Li, Y.(2016), "Concept, principle and modeling of driving risk field based on driver-vehicle-road interaction", China Journal of Highway and Transport, vol. 29, no. 1, pp.105-114.
  20. Wang, J., Wu, J. and Li, Y.(2015), "The driving safety field based on driver-vehicle-road interactions", IEEE Transactions on Intelligent Transportation Systems, vol. 16, no. 4, pp.2203-2214.
  21. Wolf, M. T. and Burdick, J. W.(2008), "Artificial potential functions for highway driving with collision avoidance", In 2008 IEEE International Conference on Robotics and Automation, pp.3731-3736.
  22. Yang, I., Jeon, W. H. and Lee, H. M.(2017), "A study on dynamic map data provision system for automated vehicle", Journal of Korean Society of Intelligent Transport Systems, vol. 16, no. 6, pp.208-218.
  23. Yukawa, H.(1935), "On the interaction of elementary particles", Proceedings of the Physico-Mathematical Society of Japan. 3rd Series, vol. 17, pp.48-57.