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

A Study on Sensor Modeling for Virtual Testing of ADS Based on MIL Simulation

MIL 시뮬레이션 기반 ADS 기능 검증을 위한 환경 센서 모델링에 관한 연구

  • Shin, Seong-Geun (ICT Convergence R&D Center, Korea Automotive Technology Institute) ;
  • Baek, Yun-Seok (ICT Convergence R&D Center, Korea Automotive Technology Institute) ;
  • Park, Jong-Ki (ICT Convergence R&D Center, Korea Automotive Technology Institute) ;
  • Lee, Hyuck-Kee (ICT Convergence R&D Center, Korea Automotive Technology Institute)
  • 신성근 (한국자동차연구원 ICT융합연구센터) ;
  • 백윤석 (한국자동차연구원 ICT융합연구센터) ;
  • 박종기 (한국자동차연구원 ICT융합연구센터) ;
  • 이혁기 (한국자동차연구원 ICT융합연구센터)
  • Received : 2021.11.10
  • Accepted : 2021.12.23
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Virtual testing is considered a major requirement for the safety verification of autonomous driving functions. For virtual testing, both the autonomous vehicle and the driving environment should be modeled appropriately. In particular, a realistic modeling of the perception sensor system such as the one having a camera and radar is important. However, research on modeling to consistently generate realistic perception results is lacking. Therefore, this paper presents a sensor modeling method to provide realistic object detection results in a MILS (Model in the Loop Simulation) environment. First, the key parameters for modeling are defined, and the object detection characteristics of actual cameras and radar sensors are analyzed. Then, the detection characteristics of a sensor modeled in a simulation environment, based on the analysis results, are validated through a correlation coefficient analysis that considers an actual sensor.

시뮬레이션 기반 가상 검증은 자율주행 기능의 안전성 검증을 위한 주요 요구사항으로 간주되고 있다. 가상 검증 환경에서는 자율주행차량과 주행 환경은 모두 모델링되어야 하며 특히, 카메라 및 레이더 센서와 같은 환경 센서의 현실적인 모델링이 중요하다. 하지만 현실적인 인식 결과를 일관되게 제공하기 위한 모델링에 관한 연구는 부족한 실정이다. 이에 본 논문에서는 MILS(Model in the Loop Simulation) 환경에서 현실적인 오브젝트 인식 결과를 제공하기 위한 센서 모델링 방법이 다루어진다. 먼저, 모델링을 위한 주요 파라미터가 정의되며 카메라 및 레이더 센서의 오브젝트 감지 특성이 분석된다. 분석 결과로부터 모델링된 가상 센서 모델의 감지 특성은 실물 센서와의 상관계수 분석을 통해 유효성이 검증된다.

Keywords

Acknowledgement

본 연구는 국토교통부 및 국토교통과학기술진흥원의 연구비지원(21AMDP-C162182-01)으로 수행된 연구임.

References

  1. Enable-S3, European Initiative to Enable Validation for Highly Automated Safe and Secure Systems, https://www.enable-s3.eu
  2. Euro NCAP(2021), Test Protocol-AEB Car-to-Car systems and AEB/LSS VRU Systems.
  3. Goodin C., Kala R., Carrrillo A. and Liu L. Y.(2009), "Sensor modeling for the Virtual Autonomous Navigation Environment," SENSORS, 2009 IEEE, pp.1588-1592.
  4. Hirsenkorn N., Hanke T., Rauch A. and Dehlink B.(2015), "A Non-Parametric Approach for Modeling Sensor Behavior," In 16th International Radar Symposium (IRS), Dresden, pp.131-136.
  5. Holder M., Linnhoff C., Rosenberger P., Popp C. and Winner H.(2019), "Modeling and Simulation of Radar Sensor Artifacts for Virtual Testing of Autonomous Driving," In 9, Tagung Automatisiertes Fahren.
  6. Holder M., Rosenverger P., Winner H., Makkapati V. P., Maier M., Schreiver H., Magosi Z., D'hondt T., Slavik Z., Bringmann O. and Rosenstiel W.(2018), "Measurements revealing Challenges in Radar Sensor Modeling for Virtual Validation of Autonomous Driving," 2018 21st International Conference on Intelligent Transtpotation Systems(ITSC), Maui, HI, USA.
  7. Kalra N. and Paddock S. M.(2016), "Driving to Safety: How Many Miles of Driving Would It Take to Demonstrate Autonomous Vehicle Reliability?," Transportation Research Part A: Policy and Practice, vol. 94, pp.182-193. https://doi.org/10.1016/j.tra.2016.09.010
  8. Li Y., Wang Y., Deng W. and Li X.(2016), Lidar Sensor Modeling for ADAS Applications under a Virtual Driving Environment, SAE Technical Paper 2016-01-1907.
  9. Litman T.(2021), Autonomous Vehicle Implementation Predictions: Implications for Transport Planning, Victoria Transport Policy Institute.
  10. Liu Z., Deng W., Li Y., Jiang L., Li X. and Wang Y.(2016), Physical Modeling Method on Ultrasonic Sensors for Virtual Intelligent Driving, SAE Technical Paper 2016-01-1901.
  11. Muckenhuber S., Holzer H., Riibsam J. and Stettinger G.(2019), "Object-based sensor model for virtual testing of ADAS/AD functions," 2019 IEEE International Conference on Connected Vehicles and Expo(ICCVE), Graz, Austria.
  12. Pegasus, Pegasus Research Project-Securing Automated Driving Effectively, http://www.pegasus-projekt.info/en/
  13. Rosenberger P., Wendler J. T., Holder M., Linnhoff C., Berghofer M., Winner H. and Maurer M.(2019), "Towards a Generally Accepted Validation Methodology for Sensor Models-Challenges, Metrics, and First Results," In Graz Symposium Virtual Vehicle (GSVF) 2019, Graz, Austria, p.13.
  14. Shin S. G., Baek Y. S., Park J. K. and Lee H. K.(2021), "Test Scheme for Estimating Illumination Dependence of Camera Sensor for Night Pedestrian Safety," The Conference of The Korea Institute of Intelligent Transport Systems, Jeju, South Korea.
  15. Yeong D. J., Velasco-Hernandez G., Barry J. and Walsh J.(2021), "Sensor and Sensor Fusion Technology in Autonomous Vehicles: A Review," Sensors 2021, vol. 21, no. 6, p.2140.
  16. 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