DOI QR코드

DOI QR Code

RSU 통신 및 딥러닝 기반 최적화 차량 라우팅 시스템 설계

A design of Optimized Vehicle Routing System(OVRS) based on RSU communication and deep learning

  • Son, Su-Rak (Department of Software Engineering, Catholic kwandong University) ;
  • Lee, Byung-Kwan (Department of Software Engineering, Catholic kwandong University) ;
  • Sim, Son-Kweon (Department of Geography Education, Catholic kwandong University) ;
  • Jeong, Yi-Na (Department of Software Engineering, Catholic kwandong University)
  • 투고 : 2020.02.23
  • 심사 : 2020.04.09
  • 발행 : 2020.04.30

초록

현재 자율주행 차량 시장은 3레벨 자율주행 차량의 상용화를 넘어 4레벨 자율주행 차량을 연구, 개발하고 있다. 4레벨 자율주행 차량에서 가장 주목되는 부분은 차량의 안정성이다. 3레벨과 다르게 4레벨의 자율주행 차량은 긴급상황을 차량이 직접 대처해야 하기 때문이다. 본 논문에서는 긴급상황에서의 즉각적인 반응보다는 차량의 목적지가 정해진 순간 사고 가능성이 가장 낮은 경로를 결정하는 Optimized Vehicle Routing System (OVRS)을 제안한다. OVRS는 RSU 통신으로 수집한 도로와 주변 차량 정보를 분석하여 도로의 위험성을 예측하여 주행 중인 차량이 더 안전하고 빠른 길로 주행할 수 있도록 경로를 설정한다. OVRS는 네트워크 라우팅 방식처럼 도로에 있는 RSU를 통하여 도로 상황에 따른 경로 안내를 실행하기 때문에 차량의 안정성을 더욱 높일 수 있다. 실험 결과, OVRS모듈 중 하나인 ASICM의 RPNN은 CNN보다 약 17%, LSTM보다 약 40% 더 좋은 연산 시간을 보였다. 그러나 해당 연구가 PC를 이용한 가상환경에서 실행되었기 때문에, VPDM의 사고 가능성을 실제로 검증하지 못했다. 따라서 향후 사고 데이터 수집으로 인한 VPDM의 정확도 높은 실험과 실제 차량 및 RSU에서 실제 도로를 대상으로 한 실험이 진행되어야 한다.

Currently, The autonomous vehicle market is researching and developing four-level autonomous vehicles beyond the commercialization of three-level autonomous vehicles. Because unlike the level 3, the level 4 autonomous vehicle has to deal with an emergency directly, the most important aspect of a four-level autonomous vehicle is its stability. In this paper, we propose an Optimized Vehicle Routing System (OVRS) that determines the route with the lowest probability of an accident at the destination of the vehicle rather than an immediate response in an emergency. The OVRS analyzes road and surrounding vehicle information collected by The RSU communication to predict road hazards, and sets the route for the safer and faster road. The OVRS can improve the stability of the vehicle by executing the route guidance according to the road situation through the RSU on the road like the network routing method. As a result, the RPNN of the ASICM, one of the OVRS modules, was about 17% better than the CNN and 40% better than the LSTM. However, because the study was conducted in a virtual environment using a PC, the possibility of accident of the VPDM was not actually verified. Therefore, in the future, experiments with high accuracy on VPDM due to the collection of accident data and actual roads should be conducted in real vehicles and RSUs.

키워드

참고문헌

  1. YiNa Jeong, SuRak Son, ByungKwan Lee, "he Lightweight Autonomous Vehicle Self-Diagnosis (LAVS) Using Machine Learning Based on Sensors and Multi-Protocol IoT Gateway", Sensor, Vol. 19, No. 11, June, 2019.
  2. Byeongjoon Noh, Wonjun No, ,Jaehong Lee, David Lee, "Vision-Based Potential Pedestrian Risk Analysis on Unsignalized Crosswalk Using Data Mining Techniques", Applied Sciences, Vol. 10, No. 3, February, 2020.
  3. Dario Vangi, Carlo Cialdai, Michelangelo-Santo Gulino, Kjell Gunnar Robbersmyr, "Vehicle Accident Databases: Correctness Checks for Accident Kinematic Data", Designs, Vol. 2, No. 1, January, 2018. https://doi.org/10.3390/designs2010009
  4. Jhihoon Joo, Odongo Steven Eyobu, Ji Hun Kim, Hong-Jong Jeong, Dong Seog Han, "Analysis of Radio Propagation Characteristics for V2V Scenarios in WAVE Standard Based Vehicular Communication System", The Journal of Korean Institute of Communications and Information Sciences. Vol. 42 No. 6, pp. 1175-1184, 2017 https://doi.org/10.7840/kics.2017.42.6.1175
  5. Bongsue Suh, "Performance Analysis of RSUs in Probability-Based Data Delivery Strategy for Energy-Constrained V2I Systems". The Journal of Korean Institute of Information Technology, Vol. 16 No.11, pp. 69-76, 2018
  6. Seok-Gyu Park, Heui-Hak Ahn, Yi-Na Jeuong, "Preventing Communication Disruption in the Urban Environment Using RRPS (RSU Request Priority Scheduling)", Journal of Korea Institute of Information, Electronics, and Communication Technology, Vol.9 No.6, pp. 584-590, 2016 https://doi.org/10.17661/jkiiect.2016.9.6.584
  7. Jungmin Kwon, Hyunggon Park, "Data Driven Reliable Dissemination Strategy Based Systematic Network Coding in V2I Networks", The Journal of Korean Institute of Communications and Information Sciences, Vol.45 No.2, pp. 327-336, 2020 https://doi.org/10.7840/kics.2020.45.2.327
  8. Bongsue Suh, "Variable Transmission Distance-Based Data Delivery Strategy to Support Near-Optimal Delivery Delay for V2I Systems", The Journal of Korean Institute of Information Technology, Vol.17 No.12, pp. 93-100, 2019 https://doi.org/10.14801/jkiit.2019.17.12.93
  9. Eum Han, Ilsoo Yun, Sang Soo Lee, Kitae Jang, ․Byungkyu Park, "Development of Real-time Traffic Signal Control Strategy for Coordinated Signalized Intersections under V2I Communication Environment", The Journal of The Korea Institute of Intelligent Transportation Systems, Vol.17, No.3, pp. 59-71, 2018 https://doi.org/10.12815/kits.2018.17.3.59
  10. Kyoung Soo Bok, Seung Wan Hong, Jae Hog Cha, Jong Tae Lim, Jaesoo Yoo, "Cooperative RSU Scheduling for Efficient Data Dissemination in VANET Environments", JOURNAL OF THE KOREA CONTENTS ASSOCIATION, Vol.13 No.10, pp. 27-36, 2013 https://doi.org/10.5392/JKCA.2013.13.10.027