International conference on construction engineering and project management (국제학술발표논문집)

  • 2024.07a
  • /
  • Pages.1019-1026
  • /
  • 2024
  • /
  • 2508-9048(eISSN)
Korea Institute of Construction Engineering and Management (한국건설관리학회)
권호 표지
DOI QR코드

DOI QR Code

Location Measurement System for Automated Operation of Construction Machinery Using Visual SLAM

  • Masaki CHINO (Frontier Research Department, Technical Research Institute, Hazama Ando Corporation) ;
  • Atsushi YAMASHITA (Department of Human and Engineered Environmental Studies Graduate School of Frontier Sciences, The University of Tokyo)
  • Published : 2024.07.29
Download PDF
⟨ Previous Next ⟩

Abstract

In the construction industry, there is a growing demand for improving productivity, and development of autonomous operation systems for construction machinery is progressing. Autonomous operation of construction machinery requires positioning information because construction must be carried out at planned locations. In this paper, we focused on Visual Simultaneous Localization and Mapping (Visual SLAM) as a method for obtaining location information for construction machinery and proposed an automated operation system using Visual SLAM. For automated driving, the indirect method based on ORB features is used in Visual SLAM, and processes such as mask processing for surrounding moving objects and measurement of initial positions using markers are performed. With the proposed system, it was confirmed that it is possible to perform automated operation in an experimental environment using the location information output by Visual SLAM. In addition, the experiment was conducted to verify the measurement accuracy when using Visual SLAM during construction work at actual construction sites. As a result, the measurement accuracy was less than 500 mm, which is a usable accuracy for actual construction. By using this system, it is possible to obtain the location information of construction machinery even in environments where GNSS cannot be used, and productivity at construction sites can be improved by performing automated operation.

Keywords

References

  1. The Japan Institute for Labour Policy and Training: Databook of International Labour Statistics 2023, 2023.
  2. Satoru Miura, Izuru Kuronuma, Kenniti Hamamoto: "Next Generation Construction Production System: On Automated Construction Machinery", Proceedings of the 7th Civil Engineering Conference In the Asian Region, pp. 1-11, 2016.
  3. Ying Jiang, Xiangyu He: "Overview of Applications of the Sensor Technologies for Construction Machinery", IEEE Access, Vol. 8, pp. 110324-110335, 2020.
  4. Nobuaki Kurihara, Hiromichi Miyazaki, Hiroaki Aoki, Saburo Katayama: "Demonstration of Vibrating Roller of Autonomous Control Type", Technical Report of Taisei Advanced Center of Technology, Vol. 47, pp. 1-6, 2014.
  5. Julian Nubert, Etienne Walther, Shehryar Khattak, Marco Hutter: "Learning-based Localizability Estimation for Robust LiDAR Localization", Proceedings of the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1-8, 2022.
  6. Runqiu Bao, Ren Komatsu, Renato Miyagusuku, Masaki Chino, Atsushi Yamashita, Hajime Asama: "Cost-effective and Robust Visual Based Localization with Consumer-level Cameras at Construction Sites", Proceedings of the 2019 IEEE 8th Global Conference on Consumer Electronics, pp. 1007-1009, 2019.
  7. Cosimo Patruno, Roberto Colella, Massimiliano Nitti, Vito Reno, Nicola Mosca, Ettore Stella: "A Vision-Based Odometer for Localization of Omnidirectional Indoor Robots", Sensors, Vol. 20, Issue 3, pp. 1-25, 2020.
  8. Ethan Rublee, Vincent Rabaud, Kurt Konolige, Gary Bradski: "ORB: An Efficient Alternative to SIFT or SURF", Proceedings of the 2011 International Conference on Computer Vision, pp. 2564-2571, 2011.
  9. Shinya Sumikura, Mikiya Shibuya, Ken Sakurada: "OpenVSLAM: A Versatile Visual SLAM Framework", Proceedings of the 27th ACM International Conference on Multimedia, pp. 2292-2295, 2019.
  10. Runqiu Bao, Ren Komatsu, Renato Miyagusuku, Masaki Chino, Atsushi Yamashita, Hajime Asama: "Stereo Camera Visual SLAM with Hierarchical Masking and Motion-state Classification at Outdoor Construction Sites Containing Large Dynamic Objects", Advanced Robotics, Vol. 35, No. 3-4, pp. 228-241, 2021.
  11. Vincent Lepetit, Francesc Moreno-Noguer, Pascal Fua: "EPnP: An Accurate O(n) Solution to the PnP Problem", International Journal of Computer Vision, Vol. 81, No. 2, pp. 155-166, 2009.
  12. Ministry of Land, Infrastructure, Transport and Tourism: "TS GNSS wo mochiita morido no shimekatame kannri youryou (in Japanese) (Management Procedure for Compaction of Embankments Using TS and GNSS)", 2020.