DOI QR코드

DOI QR Code

Study on Map Building Performance Using OSM in Virtual Environment for Application to Self-Driving Vehicle

가상환경에서 OSM을 활용한 자율주행 실증 맵 성능 연구

  • 백민혁 (대구경북과학기술원, 융복합대학) ;
  • 박진우 (대구경북과학기술원, 융복합대학) ;
  • 심중석 (대구경북과학기술원, 융복합대학) ;
  • 박성정 (대구경북과학기술원, 학제학과) ;
  • 임용섭 (대구경북과학기술원, 로봇 및 기계전자공학과) ;
  • 최경호 (대구경북과학기술원, 학제학과)
  • Received : 2022.12.13
  • Accepted : 2023.06.16
  • Published : 2023.06.30

Abstract

In recent years, automated vehicles have garnered attention in the multidisciplinary research field, promising increased safety on the road and new opportunities for passengers. High-Definition (HD) maps have been in development for many years as they offer roadmaps with inch-perfect accuracy and high environmental fidelity, containing precise information about pedestrian crossings, traffic lights/signs, barriers, and more. Demonstrating autonomous driving requires verification of driving on actual roads, but this can be challenging, time-consuming, and costly. To overcome these obstacles, creating HD maps of real roads in a simulation and conducting virtual driving has become an alternative solution. However, existing HD maps using high-precision data are expensive and time-consuming to build, which limits their verification in various environments and on different roads. Thus, it is challenging to demonstrate autonomous driving on anything other than extremely limited roads and environments. In this paper, we propose a new and simple method for implementing HD maps that are more accessible for autonomous driving demonstrations. Our HD map combines the CARLA simulator and OpenStreetMap (OSM) data, which are both open-source, allowing for the creation of HD maps containing high-accuracy road information globally with minimal dependence. Our results show that our easily accessible HD map has an accuracy of 98.28% for longitudinal length on straight roads and 98.42% on curved roads. Moreover, the accuracy for the lateral direction for the road width represented 100% compared to the manual method reflected with the exact road data. The proposed method can contribute to the advancement of autonomous driving and enable its demonstration in diverse environments and on various roads.

Keywords

References

  1. Jaeseung Kim and Yoo Hyoung Gon, 2019, "A necessary element of autonomous driving; 3D HD-map", Communications of the Korean Institute of Information Scientists and Engineers, Vol. 37, No. 9, pp. 23~27.
  2. Y. Wei, F. Mahnaz, O. Bulan, Y. Mengistu, S. Mahesh and M. A. Losh, 2022, "Creating Semantic HD Maps From Aerial Imagery and Aggregated Vehicle Telemetry for Autonomous Vehicles", in IEEE Transactions on Intelligent Transportation Systems, Vol. 23, No. 9, pp. 15382~15395, doi: 10.1109/TITS.2022.3140423.
  3. Shin Dong Hoon, Park Kang Moon and Park Man Bok, 2020, "High Definition Map-Based Localization Using ADAS Environment Sensors for Application to Automated Driving Vehicles", Applied Sciences, Vol. 10, No. 14, 4924.
  4. Choi Tae Seok, Yoon Ha Su, Choi Yun Soo, Lee Won Jong and Chang Soo Young, 2020, "A Study on High Definition Road Map Construction Using Aerial Photography", Journal of Korean Society for Geospatial Information Science, Vol. 28, No. 3, pp. 69~76. https://doi.org/10.7319/kogsis.2020.28.3.069
  5. K. Kim, S. Cho and W. Chung, 2021, "HD Map Update for Autonomous Driving With Crowdsourced Data", in IEEE Robotics and Automation Letters, vol. KKK6, No. 2, pp. 1895~1901. https://doi.org/10.1109/LRA.2021.3060406
  6. Oussama Saoudi, Ishwar Singh and Hamidreza Mahyar, 2022, "Autonomous Vehicles: Open-Source Technologies, Considerations, and Development", arXiv preprint arXiv:2202.03148, pp. 3~5.
  7. OpenStreetMap Wiki, 2022.09.11, URL: https://wiki.openstreetmap.org/wiki/Commercial_OSM_Software_and_Services.
  8. Korea intelligent automobile parts promotion institute, 2022.07.13., URL: http://www.kiapi.or.kr/sub02/sub01_02.php?sid=2&page_num=&skey=&sval=&mode=.
  9. Hyundai IONIQ Electric specification, 2022.09.30, URL: https://www.hyundai.com/kr/ko/e/vehicles/ioniqelectric/spec.