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

Study of the Operation of Actuated signal control Based on Vehicle Queue Length estimated by Deep Learning

딥러닝으로 추정한 차량대기길이 기반의 감응신호 연구

  • 이용주 (아주대학교 교통연구센터) ;
  • 심민경 (아주대학교 교통공학과) ;
  • 김용만 (도로교통공단 교통과학장비처) ;
  • 이상수 (아주대학교 교통시스템공학과) ;
  • 이철기 (아주대학교 교통시스템공학과)
  • Received : 2018.07.20
  • Accepted : 2018.08.21
  • Published : 2018.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

As a part of realization of artificial intelligence signal(AI Signal), this study proposed an actuated signal algorithm based on vehicle queue length that estimates in real time by deep learning. In order to implement the algorithm, we built an API(COM Interface) to control the micro traffic simulator Vissim in the tensorflow that implements the deep learning model. In Vissim, when the link travel time and the traffic volume collected by signal cycle are transferred to the tensorflow, the vehicle queue length is estimated by the deep learning model. The signal time is calculated based on the vehicle queue length, and the simulation is performed by adjusting the signaling inside Vissim. The algorithm developed in this study is analyzed that the vehicle delay is reduced by about 5% compared to the current TOD mode. It is applied to only one intersection in the network and its effect is limited. Future study is proposed to expand the space such as corridor control or network control using this algorithm.

본 연구는 인공지능 신호 구현의 일환으로서, 딥러닝을 통해 실시간으로 추정하는 차량대기길이 기반의 감응식 신호 알고리즘을 제시하였다. 알고리즘의 구현을 위해 딥러닝 모형을 구현한 텐서플로우에 미시적 교통시뮬레이터인 Vissim을 제어하는 API, 즉 COM Interface를 구축하였다. Vissim에서 신호주기별로 수집된 링크통행시간과 통과교통량이 텐서플로우에 전달되면 학습이 완료된 딥러닝 모형을 통해 접근로별 차량대기길이가 추정된다. 접근로별 차량대기길이를 기반으로 신호시간을 산정한 후 Vissim 내부의 신호등화를 조정하여 시뮬레이션 한다. 본 연구에서 개발한 알고리즘은 현 TOD 방식에 비해 차량 지체가 약 5% 감소한 것으로 분석되었으며, 이는 네트워크 내 하나의 교차로만 대상으로 적용하여 그 효과가 제한된 것이며, 축 또는 네트워크 제어로의 공간적 확대방안을 향후연구로 제시하였다.

Keywords

References

  1. Bottou L.(1998), Online Algorithms and Stochastic Approximations, Online Learning and Neural Networks, Cambridge University Press.
  2. Doh(2017), Transportation Engineering, ChungMoonGak.
  3. Duchi et al.(2011), "Adaptive subgradient methods for online learning and stochastic optimization," The Journal of Machine Learning Research, vol. 12, pp.2121-2159.
  4. https://tensorflowkorea.gitbooks.io/tensorflow-kr/
  5. Jeong et al.(2005), "Development of The Signal Control Algorithm Using Travel Time Informations of Sectional Detection Systems," The Journal of Korean Society of Transportation, vol. 23, no. 8, pp.181-191.
  6. Kingma D. P. and Ba J. L.(2014), ADAM: A Method for Stochastic Optimization, arXiv:1412.6980.
  7. Lee et al.(2018), "Decelopment of Vehicle Queue Length Estimation Model Using Deep Learning," The Journal of the Korea Institute of Intelligent Transportation Systems, vol. 17, no. 2, pp.39-57. https://doi.org/10.12815/kits.2018.17.2.39
  8. McCulloch W. S. and Pitts W.(1943), "A logical calculus of the ideas immanent in nervous activity," Bulletin of mathematical biophysics, 5, pp.115-133. https://doi.org/10.1007/BF02478259
  9. Minsky M. and Papert S.(1969), Perceptrons : An Introduction to Computational Geometry, The MIT Press.
  10. Roger P.(2010), Traffic Engineering, PEARSON.
  11. Rosenblatt F.(1958), "The perceptron : A probabilistic model for information storage and organization in the brain," Psychological Review, vol. 65, no. 6, pp.386-408. https://doi.org/10.1037/h0042519
  12. Russell S. J. and Norvig P.(2003), Artificial Intelligence : A Modern Approach, 2nd ed., Prentice Hall.
  13. Tieleman T. et al.(2012), Lecture 6.5-RMSProp, COURSERA : Neural Networks for Machine Learning, Technical report.

Cited by

  1. Extracting Specific Information in Web Pages Using Machine Learning vol.41, pp.4, 2018, https://doi.org/10.11627/jkise.2018.41.4.189