Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2503.15091 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913745583734784 |
|---|---|
| author | Cheng, Yao Han, Zhe Jiang, Fengyang Wang, Huaizhen Zhou, Fengyu Yin, Qingshan Wei, Lei |
| author_facet | Cheng, Yao Han, Zhe Jiang, Fengyang Wang, Huaizhen Zhou, Fengyu Yin, Qingshan Wei, Lei |
| contents | This paper addresses the high demand in advanced intelligent robot navigation for a more holistic understanding of spatial environments, by introducing a novel system that harnesses the capabilities of Large Language Models (LLMs) to construct hierarchical 3D Scene Graphs (3DSGs) for indoor scenarios. The proposed framework constructs 3DSGs consisting of a fundamental layer with rich metric-semantic information, an object layer featuring precise point-cloud representation of object nodes as well as visual descriptors, and higher layers of room, floor, and building nodes. Thanks to the innovative application of LLMs, not only object nodes but also nodes of higher layers, e.g., room nodes, are annotated in an intelligent and accurate manner. A polling mechanism for room classification using LLMs is proposed to enhance the accuracy and reliability of the room node annotation. Thorough numerical experiments demonstrate the system's ability to integrate semantic descriptions with geometric data, creating an accurate and comprehensive representation of the environment instrumental for context-aware navigation and task planning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15091 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Intelligent Spatial Perception by Building Hierarchical 3D Scene Graphs for Indoor Scenarios with the Help of LLMs Cheng, Yao Han, Zhe Jiang, Fengyang Wang, Huaizhen Zhou, Fengyu Yin, Qingshan Wei, Lei Robotics Computer Vision and Pattern Recognition This paper addresses the high demand in advanced intelligent robot navigation for a more holistic understanding of spatial environments, by introducing a novel system that harnesses the capabilities of Large Language Models (LLMs) to construct hierarchical 3D Scene Graphs (3DSGs) for indoor scenarios. The proposed framework constructs 3DSGs consisting of a fundamental layer with rich metric-semantic information, an object layer featuring precise point-cloud representation of object nodes as well as visual descriptors, and higher layers of room, floor, and building nodes. Thanks to the innovative application of LLMs, not only object nodes but also nodes of higher layers, e.g., room nodes, are annotated in an intelligent and accurate manner. A polling mechanism for room classification using LLMs is proposed to enhance the accuracy and reliability of the room node annotation. Thorough numerical experiments demonstrate the system's ability to integrate semantic descriptions with geometric data, creating an accurate and comprehensive representation of the environment instrumental for context-aware navigation and task planning. |
| title | Intelligent Spatial Perception by Building Hierarchical 3D Scene Graphs for Indoor Scenarios with the Help of LLMs |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.15091 |