Journal of the Korea Institute of Military Science and Technology (한국군사과학기술학회지)

The Korea Institute of Military Science and Technology (한국군사과학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Real-virtual Point Cloud Augmentation Method for Test and Evaluation of Autonomous Weapon Systems

자율무기체계 시험평가를 위한 실제-가상 연계 포인트 클라우드 증강 기법

  • Saedong Yeo (Defense Test & Evaluation Research Institute, Agency for Defense Development) ;
  • Gyuhwan Hwang (Defense Test & Evaluation Research Institute, Agency for Defense Development) ;
  • Hyunsung Tae (Defense Test & Evaluation Research Institute, Agency for Defense Development)
  • 여세동 (국방과학연구소 국방시험연구원) ;
  • 황규환 (국방과학연구소 국방시험연구원) ;
  • 태현성 (국방과학연구소 국방시험연구원)
  • Received : 2024.01.02
  • Accepted : 2024.03.15
  • Published : 2024.06.05
Download PDF
⟨ Previous Next ⟩

Abstract

Autonomous weapon systems act according to artificial intelligence-based judgement based on recognition through various sensors. Test and evaluation for various scenarios is required depending on the characteristics that artificial intelligence-based judgement is made. As a part of this approach, this paper proposed a LiDAR point cloud augmentation method for mixed-reality based test and evaluation. The augmentation process is achieved by mixing real and virtual LiDAR signals based on the virtual LiDAR synchronized with the pose of the autonomous weapon system. For realistic augmentation of test and evaluation purposes, appropriate intensity values were inserted when generating a point cloud of a virtual object and its validity was verified. In addition, when mixing the generated point cloud of the virtual object with the real point cloud, the proposed method enhances realism by considering the occlusion phenomenon caused by the insertion of the virtual object.

Keywords

References

  1. DoD Directive 3000.09, Autonomy in Weapon Systems, U.S. Depart-ment of Defense, Jan. 2023.
  2. S. Feng, Y. Feng, C. Yu, and Y. Zhang, "Testing scenario library generation for connected and automated vehicles, Part I: Methodology," IEEE Trans. Intell. Transp. Syst., Vol. 22, No. 3, pp. 1573-1582, Mar. 2021.
  3. S. Feng, Y. Feng, H. Sun, S. Bao, and Y Zhang, "Testing scenario library generation for connected and automated vehicles, Part II: Case Studies," IEEE Trans. Intell. Transp. Syst., Vol. 22, No. 9, pp. 5635-5647, Sep. 2021.
  4. S. Riedmaier, T. Ponn, D. Ludwig, B. Schick, and F. Diermeyer, "Survey on scenario-based safety assessment of autonomous vehicles," IEEE Access, Vol. 8, pp. 87459-87477, 2020.
  5. T. Duser, H. Abdellatif, C. Gutenkunst, and C. Gnandt, "Approaches for the homologation of automated driving," ATZelectronics worldwide, No. 14, pp. 48-53, 2019.
  6. VARGA, Balazs, et al., "Mixed-reality automotive testing with sensoris," Periodica Polytechnica Transportation Engineering, 48.4: pp. 357-362, 2020.
  7. M. F. Drechsler, J. Peintner, F. Reway, G. Seifert, A. Riener and W. Huber, "MiRE, A Mixed Reality Environment for Testing of Automated Driving Functions," in IEEE Transactions on Vehicular Technology, Vol. 71, No. 4, pp. 3443-3456, April 2022, doi: 10.1109/TVT.2022.3160353.
  8. ARGUI, Imane; GUERIAU, Maxime; AINOUZ-ZEMOUCHE, Samia, "Towards a Mixed-Reality framework for autonomous driving," In: ROS 2022-13th Workshop on Planning, Perception and Navigation for Intelligent Vehicles, 2022.
  9. CHE, Xiaobo; LI, Chao; ZHANG, Zihui, "A test method for self-driving vehicle based on mixed reality," In: 2021 IEEE International Conference on Smart Internet of Things(SmartIoT), IEEE, pp. 401-405, 2021.
  10. WANG, Shenlong; FORSYTH, David, "Safely Test Autonomous Vehicles with Augmented Reality," I-ACT-21-07, 2022.
  11. SZALAI, Matyas, et al., "Mixed reality test environment for autonomous cars using Unity 3D and SUMO," In: 2020 IEEE 18th World Symposium on Applied Machine Intelligence and Informatics (SAMI), IEEE, pp. 73-78, 2020.
  12. HAHNER, Martin, et al., "Quantifying data augmentation for lidar based 3d object detection," arXiv preprint arXiv:2004.01643, 2020.
  13. FANG, Jin, et al., "Augmented LiDAR simulator for autonomous driving," IEEE Robotics and Automation Letters, 5.2: 1931-1938, 2020.
  14. CHOI, Jaeseok; SONG, Yeji; KWAK, Nojun, "Part-aware data augmentation for 3d object detection in point cloud," In 2021 IEEE. In: RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3391-3397, 2021.
  15. FANG, Jin, et al., "Lidar-aug: A general rendering-based augmentation framework for 3d object detection," In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4710-4720, 2021.
  16. VACEK, Patrik, et al., "Learning to predict lidar intensities," IEEE Transactions on Intelligent Transportation Systems, 23.4: 3556-3564, 2021.
  17. ANTONELLI, Gianluca; CHIAVERINI, Stefano, "Linear estimation of the physical odometric parameters for differential-drive mobile robots," Autonomous Robots, 23: 59-68, 2007.
  18. HEWITT, Robert A.; MARSHALL, Joshua A., "Towards intensity-augmented SLAM with LiDAR and ToF sensors," In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 1956-1961, 2015.
  19. J. Lambert et al., Performance Analysis of 10 Models of 3D LiDARs for Automated Driving," in IEEE Access, Vol. 8, pp. 131699-131722, 2020.
  20. Massey, F. J., "The Kolmogorov-Smirnov Test for Goodness of Fit," Journal of the American Statistical Association, Vol. 46, No. 253, pp. 68-78, 1951.
  21. Miller, L. H., "Table of Percentage Points of Kolmogorov Statistics," Journal of the American Statistical Association, Vol. 51, No. 2736, pp. 111-121, 195.
  22. Marsaglia, G., W. Tsang, and J. Wang, "Evaluating Kolmogorov's Distribution," Journal of Statistical Software, Vol. 8, Issue 18, 2003.