Dynamic Open-Vocabulary 3D Scene Graphs for Long-Term Language-Guided Mobile Manipulation
IEEE Robotics and Automation Letters · 2025-05 · 10 (5) · 4252-4259
DOI: 10.1109/lra.2025.3547643 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Robotics and Automation Letters, 2025-05. Verfasst von Zhijie Yan und 7 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Ministry of Industry and Information Technology of the People's Republic of China, Key Laboratory of Intelligent Manufacturing for High-end Aerospace Products.
Abstract (Originalsprache)
Enabling mobile robots to perform long-term tasks in dynamic real-world environments is a formidable challenge, especially when the environment changes frequently due to human-robot interactions or the robot's own actions. Traditional methods typically assume static scenes, which limits their applicability in the continuously changing real world. To overcome these limitations, we present DovSG, a novel mobile manipulation framework that leverages dynamic open-vocabulary 3D scene graphs and a language-guided task planning module for long-term task execution. DovSG takes RGB-D sequences as input and utilizes vision-language models (VLMs) for object detection to obtain high-level object semantic features. Based on the segmented objects, a structured 3D scene graph is generated for low-level spatial relationships. Furthermore, an efficient mechanism for locally updating the scene graph, allows the robot to adjust parts of the graph dynamically during interactions without the need for full scene reconstruction. This mechanism is particularly valuable in dynamic environments, enabling the robot to continually adapt to scene changes and effectively support the execution of long-term tasks. We validated our system in real-world environments with varying degrees of manual modifications, demonstrating its effectiveness and superior performance in long-term tasks.
Förderung
- National Natural Science Foundation of China
- Ministry of Industry and Information Technology of the People's Republic of China
- Key Laboratory of Intelligent Manufacturing for High-end Aerospace Products
- Beijing Key Laboratory of Digital Design and Manufacturing
Zitieren
APA
Yan, Z., Li, S., Wang, Z., Wu, L., Wang, H., Zhu, J., Chen, L., & Liu, J. (2025). Dynamic Open-Vocabulary 3D Scene Graphs for Long-Term Language-Guided Mobile Manipulation. IEEE Robotics and Automation Letters, 10(5), 4252-4259. https://doi.org/10.1109/lra.2025.3547643
Vancouver
Yan Z, Li S, Wang Z, Wu L, Wang H, Zhu J, et al. Dynamic Open-Vocabulary 3D Scene Graphs for Long-Term Language-Guided Mobile Manipulation. IEEE Robotics and Automation Letters. 2025;10(5):4252-4259. doi:10.1109/lra.2025.3547643
BibTeX
@article{Yan2025,
author = {Yan, Zhijie and Li, Shufei and Wang, Zuoxu and Wu, Lixiu and Wang, Han and Zhu, Jun and Chen, Lijiang and Liu, Jihong},
title = {Dynamic Open-Vocabulary 3D Scene Graphs for Long-Term Language-Guided Mobile Manipulation},
journal = {IEEE Robotics and Automation Letters},
year = {2025},
volume = {10},
number = {5},
pages = {4252--4259},
doi = {10.1109/lra.2025.3547643}
}
EUVIMED