The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Reinforcement Learning-Based Adaptive Traffic Signal Control considering Vehicles and Pedestrians in Intersection

차량과 보행자를 고려한 강화학습 기반 적응형 교차로 신호제어 연구

  • Received : 2023.12.28
  • Accepted : 2024.02.17
  • Published : 2024.02.29
Download PDF
⟨ Previous Next ⟩

Abstract

Traffic congestion has caused issues in various forms such as the environment and economy. Recently, an intelligent transport system (ITS) using artificial intelligence (AI) has been focused so as to alleviate the traffic congestion problem. In this paper, we propose a reinforcement learning-based traffic signal control algorithm that can smooth the flow of traffic while reducing discomfort levels of drivers and pedestrians. By applying the proposed algorithm, it was confirmed that the discomfort levels of drivers and pedestrians can be significantly reduced compared to the existing fixed signal control system, and that the performance gap increases as the number of roads at the intersection increases.

원활한 교통의 흐름은 현대 사회에서 매우 중요한 요소이며, 교통체증은 환경 및 경제 등 다양한 형태로 문제를 초래했다. 이러한 문제를 해결하기 위해 최근 인공지능을 활용한 지능형교통체계(Intelligent Transport System)가 주목받고 있다. 본 논문에서는 강화학습 기법을 활용하여 교차로 각 방향의 차량과 보행자를 동시에 고려하여 교통의 흐름을 원활하게 하면서 동시에 불만족도를 낮출 수 있는 알고리즘을 제안한다. 제안하는 알고리즘을 적용한 교차로 신호체계 시뮬레이션 결과, 기존의 고정형 신호체계에 비해 차량·보행자의 불만족도를 상당히 낮출 수 있으며, 교차로의 교차하는 도로의 수가 많을수록 성능의 차이가 증가함을 확인하였다.

Keywords

Acknowledgement

이 성과는 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임 (No. 2022R1G1A1011513)

References

  1. T. Lomax, D. Shrank, S. Turner, L. Geng, Y. L i, and N. Koncz, "Real-timing the 2010 urban mobility report," Texas A&M Transportation Ins titute, no. UTCM 10-65-55, 2011. 
  2. J. Jin and J. Jin, "A Study on the Effect of Traffic Congestion on Particulate Matter Concentration in Seoul : Big Data Approach," J. of the Korea Planning Association, vol. 56, no. 1, 2021, pp. 121-136.  https://doi.org/10.17208/jkpa.2021.02.56.1.121
  3. H. Han and I. Yun, "Prediction of the Electric Vehicles Supply and Electricity Demand Using Growth Models,"J. of the Korea Institute of Intelligent Transportation Systems, vol. 22, no. 4, 2023, pp. 132-144.  https://doi.org/10.12815/kits.2023.22.4.132
  4. Ministry of Land, Infrastructure and Transport, "Guidelines for roundabout,"Report, 2014. 
  5. A. Gohar and G. Nencioni, "The role of 5G technologies in a smart city: the case for intelligent transportation system," Sustainability, vol. 13, no. 9, 2021, pp. 5188. 
  6. M. Sharafsaleh, J. VanderWerf, A. Misener, and E. Shladover, "Implementing vehicle-infrastructure integration: real-world challenges," Transportation Research Record, vol. 2086, no. 1, 2008, pp. 124-132.  https://doi.org/10.3141/2086-15
  7. M. Kuwahara, "Intelligent transport system-overview and Japanese systems," Prometheus, vol. 86, 1998, pp. 94-103. 
  8. S. An, B. Lee, and D. Shin, "A survey of intelligent transportation systems," In proceedings of International Conference on Computational Intelligence, Communication System an Networks, Bali, Indonesia, 2011. 
  9. Y. Lee and J. Lee, "A study on link travel time estimating methodology for traffic information service," J. of the Korean Society of Transportation, vol. 20, no. 3, 2002, pp. 55-67. 
  10. J. Kim and S. Kim, "Reinforcement learning-based illuminance control method for building lighting system," J. of the Institute of Korean Electrical and Electronics Engineers, vol. 26, no. 1, 2022, pp. 56-61. 
  11. D. Kim, Y. Choi, B. Roh, and J. Choi "Reinforce learning based cooperative sensing for cognitive radio networks," J. of the Korea Institute of Electronic Communication Science, vol. 13, no. 5, 2018, pp. 1043-1050. 
  12. O. Khin and S. Lee, "Performance analysis of deep reinforcement learning for crop yield prediction,"J. of the Korea Institute of Electronic Communication Science, vol. 18, no. 1, 2023, pp. 99-106. 
  13. S. Lee, "A routing algorithm based on deep reinforcement learning in SDN,"J. of the Korea Institute of Electronic Communication Science, vol. 16, no. 6, 2021, pp. 1153-1160.