Multi-Robot Autonomous 3D Reconstruction Using Gaussian Splatting With Semantic Guidance
IEEE Robotics and Automation Letters · 2025-06 · 10 (6) · 5617-5624
DOI: 10.1109/lra.2025.3558703 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Robotics and Automation Letters, 2025-06. Verfasst von Jing Zeng und 7 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 24 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Zhejiang Province, National Postdoctoral Program for Innovative Talents.
Abstract (Originalsprache)
Implicit neural representations and 3D Gaussian splatting (3DGS) have shown great potential for scene reconstruction. Recent studies have expanded their applications in autonomous reconstruction through task assignment methods. However, these methods are mainly limited to a single robot, and rapid reconstruction of large-scale scenes remains a challenge. In addition, task-driven planning based on surface uncertainty is prone to being trapped in local optima. To this end, we propose the first 3DGS-based centralized multi-robot autonomous 3D reconstruction framework. To further reduce the time cost of task generation and improve reconstruction quality, we integrate open-vocabulary semantic segmentation online with surface uncertainty of 3DGS, focusing view sampling on regions with high instance uncertainty. Finally, we develop a multi-robot collaboration strategy with mode and task assignments improving reconstruction quality while ensuring planning efficiency. Our method demonstrates the highest reconstruction quality among all planning methods and superior planning efficiency compared to existing multi-robot methods. We deploy our method on multiple robots and the results show that it can effectively plan view paths and reconstruct scenes with high quality.
Förderung
- National Natural Science Foundation of China
- Key Research and Development Program of Zhejiang Province
- National Postdoctoral Program for Innovative Talents
- China Postdoctoral Science Foundation
Zitieren
APA
Zeng, J., Ye, Q., Liu, T., Xu, Y., Li, J., Xu, J., Li, L., & Chen, J. (2025). Multi-Robot Autonomous 3D Reconstruction Using Gaussian Splatting With Semantic Guidance. IEEE Robotics and Automation Letters, 10(6), 5617-5624. https://doi.org/10.1109/lra.2025.3558703
Vancouver
Zeng J, Ye Q, Liu T, Xu Y, Li J, Xu J, et al. Multi-Robot Autonomous 3D Reconstruction Using Gaussian Splatting With Semantic Guidance. IEEE Robotics and Automation Letters. 2025;10(6):5617-5624. doi:10.1109/lra.2025.3558703
BibTeX
@article{Zeng2025,
author = {Zeng, Jing and Ye, Qi and Liu, Tianle and Xu, Yang and Li, Jin and Xu, Jinming and Li, Liang and Chen, Jiming},
title = {Multi-Robot Autonomous 3D Reconstruction Using Gaussian Splatting With Semantic Guidance},
journal = {IEEE Robotics and Automation Letters},
year = {2025},
volume = {10},
number = {6},
pages = {5617--5624},
doi = {10.1109/lra.2025.3558703}
}
EUVIMED