| id |
caadria2025_739 |
| authors |
Liu, Hanning, Wang, Shitong, Xie, Xingjie and Yuan, Philip F. |
| year |
2025 |
| title |
AR-Assisted Workflow in Free-Form 3D-Printed Panel Assembly: A fusion of virtual and physical elements |
| source |
Dagmar Reinhardt, Christiane M. Herr, Anastasia Globa, Jielin Chen, Taro ?Narahara, Nicolas Rogeau (eds.), ARCHITECTURAL INFORMATICS - Proceedings of the 30th CAADRIA Conference, Tokyo, 22-29 March 2025, Volume 2, pp. 387–396 |
| summary |
Methods of integrating Augmented Reality (AR) technology into the fabrication and assembly process have been extensively studied in the field of Digital Fabrication. However, existing research primarily focuses on standard construction materials, such as bricks and steel rods, and on small-scale experiments conducted in laboratories, which do not closely reflect real-world construction scenarios. This research aims to demonstrate the feasibility of implementing a large-scale outdoor assembly process of free-form 3D-printed plastic panels. In this paper, we develop a comprehensive AR-assisted workflow to ensure a high-accuracy assembly and adapt to outdoor conditions. The workflow consists of three key steps: panel quality check, outdoor pose tracking, and assembly accuracy feedback. First, a depth camera is used for 3D scanning of the panels, comparing the scanned model with the design to ensure the deviation meets the required specifications. Next, we facilitate the image alignment of virtual and physical camera with outdoor pose tracking device. Finally, a segmentation algorithm provides real-time visual feedback to the builder to ensure assembly accuracy. The results of this research demonstrate the effectiveness of integrating virtual and physical elements in an AR-assisted assembly workflow, paving ways for future advancements of AR technology in architecture, engineering, and construction industry. |
| keywords |
Augmented Reality, Pose Tracking, Outdoor Assembly, 3D-Printed Panel, High Accuracy |
| series |
CAADRIA |
| full text |
 file.pdf (3,058,913 bytes) |
| references |
Content-type: text/plain
|
| last changed |
2025/03/21 12:07 |
|
