We investigate the path planning problem for autonomous 3D modeling of a large outdoor structure with micro-aerial vehicle. For this problem, there are two categories of the next-best-view algorithm: volumetric and surface-based approaches. The volumetric approach finds a position that camera can view as much of unknown volume as possible, so it is extensively employed in exploration task. The surface-based approach computes a viewpoint by analyzing the trend and quality of the reconstructed surface, and focuses on the model completion. In this paper, we propose a new view planning algorithm that combines both surface and volumetric approaches. The algorithm first determines a goal configuration in volumetric approach, and then plans an optimal path that provides full coverage of neighboring frontier surfaces. Therefore, we can accurately and efficiently complete the 3D modeling of large structure.
KAIST, 드론 활용 대형 구조물 3D 스캔 기술 개발 [LINK]
Related publications
1. S Song, S Jo, Online Inspection Path Planning for Autonomous 3D Modeling using a Micro-Aerial Vehicle, 2017 IEEE International Conference on Robotics and Automation (ICRA).
[LINK][PDF].
