Fully automated CAD/BIM modeling of pipe structures from plant environment 3D point cloud

Imabuchi, Takashi; Kawabata, Kuniaki

Proceedings of 2026 IEEE/SICE International Symposium on System Integration (SII2026) (Internet), p.1105 - 1109, 2026/01

Development of the performance evaluation method for small multicopter vertical mobility in a narrow environment

Yamada, Taichi; Suzuki, Soichiro; Ito, Rintaro; Ota, Yua*; Kaneko, Eiichiro*; Ogane, Katsuji*; Kawabata, Kuniaki

Advanced Robotics, 12 Pages, 2025/10

https://doi.org/10.1080/01691864.2025.2573056

We develop a test method to evaluate the vertical moving performance of an unmanned aircraft system (UAS) in a narrow environment, specifically performance for ascending through a narrow aperture. This research aims to boost the UAS industry by pushing for the expansion of UAS use into various places and situations. UAS users should know whether the UAS performance is enough to achieve their objectives and what UAS suits them. However, discussing what/how much UASs can do is complex, especially in a place or situation affecting some UAS functions. Thus, the test method provides an easy-to-understand evaluation of UAS performance for mobility to access a destination in a narrow environment, even for UAS users without technical knowledge. To develop an acceptable test method for the UAS industry, we repeatedly held demonstrations and discussions with UAS manufacturers and users to incorporate their opinions from the early stages of this research. In addition, the experiments show that the test method appropriately indicates the difference in UAS performance. This paper describes the approach of UAS performance evaluation to promote the UAS industry, the development along with UAS users' opinions, and the result of the experiments to compare the type of UAS and consideration.

Discrimination of structures in plant using deep learning models trained by 3D CAD semantics

Imabuchi, Takashi; Kawabata, Kuniaki

Artificial Life and Robotics, 30(1), p.184 - 195, 2025/02

https://doi.org/10.1007/s10015-024-00989-w

Image selection method from image sequence to improve computational efficiency of 3D reconstruction; Application of fixed threshold to remove redundant images

Hanari, Toshihide; Nakamura, Keita*; Imabuchi, Takashi; Kawabata, Kuniaki

Journal of Robotics and Mechatronics, 36(6), p.1537 - 1549, 2024/12

https://doi.org/10.20965/jrm.2024.p1537

This paper describes three-dimensional (3D) reconstruction processes introducing the image selection method for efficiently generating a 3D model from an image sequence. To obtain suitable images for efficient 3D reconstruction, we tried to apply the image selection method to remove the redundant images in the image sequence. By the proposed method, the suitable images were selected from the image sequence based on optical flow measures and a fixed threshold. As a result, the proposed method can reduce the computational cost for the 3D reconstruction processes based on the image sequence acquired by the camera. We confirmed that the computational cost of the 3D reconstruction processes can reduce while keeping the 3D reconstruction accuracy at a constant level.

Decommissioning robot manipulator for fuel debris retrieval

Nakashima, Shinsuke*; Moro, A.*; Komatsu, Ren*; Faragasso, A.*; Matsuhira, Nobuto*; Woo, H.*; Kawabata, Kuniaki; Yamashita, Atsushi*; Asama, Hajime*

Proceedings of International Topical Workshop on Fukushima Decommissioning Research 2024 (FDR2024) (Internet), 4 Pages, 2024/10

Integration of multiple dense point clouds based on estimated parameters in photogrammetry with QR code for reducing computation time

Nakamura, Keita*; Baba, Keita*; Watanobe, Yutaka*; Hanari, Toshihide; Matsumoto, Taku*; Imabuchi, Takashi; Kawabata, Kuniaki

Artificial Life and Robotics, 29(4), p.546 - 556, 2024/09

https://doi.org/10.1007/s10015-024-00966-3

Investigation of the influence of the magnitude of camera vibration on 3D reconstruction results by photogrammetry based on simulation

Nakamura, Keita*; Hanari, Toshihide; Imabuchi, Takashi; Kawabata, Kuniaki

Proceedings of 2024 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM 2024), p.7 - 8, 2024/07

Photogrammetry is a technique for 3D reconstruction of target objects from multiple images shot of the object. In the case of actual photography, the object may not be reconstructed due to the inability to shoot images suitable for photogrammetry because of vibration in the camera's angle of view of the object. Therefore, we implement this vibration by using random numbers and verify the influence of the magnitude of the vibration on the reconstruction result obtained by photogrammetry. The verification results show the relationship between the magnitude of the vibration and the success rate of 3D reconstruction.

Rail DRAGON: Long-reach Bendable Modularized Rail Structure for Constant Observation inside PCV

Yokomura, Ryota*; Goto, Masataka*; Yoshida, Takehito*; Warisawa, Shinichi*; Hanari, Toshihide; Kawabata, Kuniaki; Fukui, Rui*

IEEE Robotics and Automation Letters (Internet), 9(4), p.3275 - 3282, 2024/04

https://doi.org/10.1109/LRA.2024.3366022

To reduce errors in the remote control of robots during decommissioning, we developed a Rail DRAGON, which enables continuous observation of the work environment. The Rail DRAGON is constructed by assembling and pushing a long rail structure inside the primary containment vessel (PCV), and then repeatedly deploying several monitoring robots on the rails to enable constant observation in a high-radiation environment. In particular, we have developed the following components of Rail DRAGON: bendable rail modules, straight rail modules, a basement unit, and monitoring robots. Concretely, this research proposes and demonstrates a method to realize an ultralong articulated structure with high portability and workability. In addition, it proposes and verifies the feasibility of a method for deploying observation equipment that can be easily deployed and replaced, while considering disposal.

Discrimination of Plant Structures in 3D Point Cloud Through Back-Projection of Labels Derived from 2D Semantic Segmentation

Imabuchi, Takashi; Kawabata, Kuniaki

Journal of Robotics and Mechatronics, 36(1), p.63 - 70, 2024/02

https://doi.org/10.20965/jrm.2024.p0063

Integration of multiple partial point clouds based on estimated parameters in photogrammetry with QR codes

Baba, Keita*; Watanobe, Yutaka*; Nakamura, Keita*; Matsumoto, Taku; Hanari, Toshihide; Kawabata, Kuniaki

Proceedings of 29th International Symposium on Artificial Life and Robotics (AROB 29th 2024) (Internet), p.751 - 756, 2024/01