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

Development of Commercial Game Engine-based Low Cost Driving Simulator for Researches on Autonomous Driving Artificial Intelligent Algorithms

자율주행 인공지능 알고리즘 연구를 위한 상용 게임 엔진 기반 초저가 드라이빙 시뮬레이터 개발

  • Im, Ji Ung (Dept. of Department of Electrical and Computer Eng., Graduate School of Inha University) ;
  • Kang, Min Su (Dept. of Department of Electrical and Computer Eng., Graduate School of Inha University) ;
  • Park, Dong Hyuk (Dept. of Department of Electrical and Computer Eng., Graduate School of Inha University) ;
  • Won, Jong hoon (Dept. of Department of Electrical Eng., Inha University)
  • 임지웅 (인하대학교 대학원 전기컴퓨터공학과) ;
  • 강민수 (인하대학교 대학원 전기컴퓨터공학과) ;
  • 박동혁 (인하대학교 대학원 전기컴퓨터공학과) ;
  • 원종훈 (인하대학교 전기공학과)
  • Received : 2021.08.02
  • Accepted : 2021.11.26
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a method to implement a low-cost driving simulator for developing autonomous driving algorithms. This is implemented by using GTA V, a physical engine-based commercial game software, containing a function to emulate output and data of various sensors for autonomous driving. For this, NF of Script Hook V is incorporated to acquire GT data by accessing internal data of the software engine, and then, various sensor data for autonomous driving are generated. We present an overall function of the developed driving simulator and perform a verification of individual functions. We explain the process of acquiring GT data via direct access to the internal memory of the game engine to build up an autonomous driving algorithm development environment. And, finally, an example applicable to artificial neural network training and performance evaluation by processing the emulated sensor output is included.

본 논문은 자율주행 알고리즘 개발을 위한 저비용 드라이빙 시뮬레이터 구축 방법을 소개한다. 이는 물리엔진을 적용한 상용게임 소프트웨어인 GTA V를 활용하여 구현되며 자율주행 시스템에 필요한 다양한 센서 출력값 및 데이터를 에뮬레이션하는 기능을 내장한다. 이를 위해 GTA V 내부 데이터를 취득할 수 있는 Script Hook V의 NF를 활용하여 GT 데이터를 취득하고, 이를 활용하여 다양한 자율주행용 센서 데이터를 생성한다. 본문에서는 설계된 드라이빙 시뮬레이터의 전반적인 기능들을 소개하며, 개별 기능에 대한 검증을 수행한다. 자율주행 알고리즘 개발 환경 구축을 위해 게임 엔진 내부 메모리 접근을 통한 GT 데이터를 취득하는 과정을 설명하고, 에뮬레이션된 센서값을 처리 및 활용하여 인공 신경망 학습 및 성능평가에 적용 가능한 예시를 제시한다.

Keywords

Acknowledgement

본 논문은 2021년도 정부(산업통상자원부)의 재원으로 한국산업기술진흥원의 지원(N0002428, 2021년 산업전문인력역량강화사업) 및 (주)한국AVL의 연구비 지원(드라이빙 시뮬레이터 성능 향상 기술: 63955-02)을 받아 수행된 연구임.

References

  1. AB Software Development, http://www.dev-c.com/, 2021.04.14.
  2. AV Simulation, https://www.avsimulation.com/, 2021.04.14.
  3. Blana E.(1996), "Driving Simulator Validation Studies: A Literature Review," Working Paper, Institute of Transport Studies, University of Leeds, UK.
  4. Bochkovskiy A., Wang C. Y. and Liao H. Y. M.(2020), Yolov4: Optimal speed and accuracy of object detection, arXiv preprint arXiv:2004.10934.
  5. Chen S., Hu J., Shi Y., Peng Y., Fang J., Zhao R. and Zhao L.(2017), "Vehicle-to-everything (V2X) services supported by LTE-based systems and 5G," IEEE Communications Standards Magazine, pp.70-76.
  6. Chucholowski F., Gnandt C., Hepperle C. and Hafner S.(2016), "Close to reality surrounding model for virtual testing of autonomous driving and ADAS," In Advanced Vehicle Control, Proceedings of the 13th International Symposium on Advanced Vehicle Control (AVEC'16), pp.85-90.
  7. FiveM, https://fivem.net/, 2021.04.14.
  8. Forsyth D. A. and Ponce J.(2003), Computer Vision: A Modern Approach, New Jersey: Prentice Hall, pp.11-18.
  9. Godley S. T., Triggs T. J. and Fildes B. N.(2002), "Driving simulator validation for speed research," Accident Analysis & Prevention, vol. 34, no. 5, pp.589-600. https://doi.org/10.1016/S0001-4575(01)00056-2
  10. Hendriks F., Tideman M., Pelders R., Bours R. and Liu X.(2010), "Development tools for active safety systems: Prescan and VeHIL," In Proceedings of 2010 IEEE International Conference on Vehicular Electronics and Safety, pp.54-58.
  11. Im J. U.(2020), Development of Commercial Game Engine-based Driving Simulator for Researches on Autonomous Driving Artificial Intelligent Algorithms, Master's Thesis, Inha University Graduate School.
  12. IPG Automotive, https://ipg-automotive.com/products-services/simulation-software/, 2021.04.14.
  13. Ji G. H. and Won J. H.(2018), "Implementation of integrated navigation algorithm based on GNSS-VTL and INS," Proceeding of Korean GNSS Society Conference, Jeju, South Korea.
  14. Joa E., Yi K. and Kim K.(2015), "A lateral driver model for vehicle-driver closed-loop simulation at the limits of handling," Vehicle System Dynamics, vol. 53, no. 9, pp.1247-1268. https://doi.org/10.1080/00423114.2015.1042485
  15. Kang M. S. and Won J. H.(2021), "Lidar and V2X-based Cooperative Localization Techniques Using EKF and PF," Proceeding of Korean GNSS Society Conference, Jeju, South Korea.
  16. Kang M. S., An S. H., Do Y. H. and Won J. H.(2020), "Implementation of a Server based Multi Client Autonomous Navigation Simulator Hardware System," 2020 IPNT Conference.
  17. Kaplan E. D. and Hegarty C. J.(1996), Understanding GPS: Principles and Applications, Boston: Artech House Publishers, pp.29-34.
  18. Martinez M., Sitawarin C., Finch K., Meincke L., Yablonski A. and Kornhauser A.(2017), Beyond grand theft auto V for training, testing and enhancing deep learning in self driving cars, arXiv preprint arXiv:1712.01397.
  19. Mechanical Simulation, https://www.carsim.com/products/carsim/index.php, 2021.04.14.
  20. Meinl F., Stolz M., Kunert M. and Blume H.(2017), "An experimental high performance radar system for highly automated driving," In 2017 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM), pp.71-74.
  21. Payload, https://en.wikipedia.org/wiki/Payload_(computing), 2021.04.29.
  22. Shah S., Dey D., Lovett C. and Kapoor A.(2018), "Airsim: High-fidelity visual and physical simulation for autonomous vehicles," In Field and service robotics, Springer, pp.621-635.
  23. Smid A.(2017), Comparison of unity and unreal engine, Czech Technical University in Prague, pp.41-61.
  24. Tass International, https://tass.plm.automation.siemens.com/prescan-overview, 2021.04.14.
  25. Vector, https://www.vector.com/int/en/company/about-vector/memberships/from-tesis-to-vector/, 2021.04.14.
  26. VectoreNav, https://www.vectornav.com/products/vn-200, 2021.04.15.
  27. WithRobot, http://withrobot.com/camera/ocam-5cro-u/, 2021.04.15.
  28. Won J. H.(2005), Studies on the Software-Based GPS Receiver and Navigation Algorithms, Doctoral Dissertation, Ajou University Graduate School.
  29. Yasuma F., Mitsunaga T., Iso D. and Nayar S. K.(2010), "Generalized assorted pixel camera: Postcapture control of resolution, dynamic range, and spectrum," IEEE Transactions on Image Processing, pp.2241-2253.
  30. Yoon S., Jung J., Hong J., Lim K., Kim J. and Kim H.(2020), "Development of Autonomous Vehicle Learning Data Generation System," The Journal of The Korea Institute of Intelligent Transport Systems, vol. 19, no. 5, pp.162-177. https://doi.org/10.12815/kits.2020.19.5.162
  31. Yue X., Wu B., Seshia S. A., Keutzer K. and Sangiovanni-Vincentelli A. L.(2018), "A lidar point cloud generator: From a virtual world to autonomous driving," In Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval, pp.458-464.
  32. Zhang X., Xu W., Dong C. and Dolan J. M.(2017), "Efficient L-shape fitting for vehicle detection using laser scanners," In 2017 IEEE Intelligent Vehicles Symposium (IV), pp.54-59.