A3VLM: Actionable Articulation-Aware Vision Language Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911915357241344 |
|---|---|
| author | Huang, Siyuan Chang, Haonan Liu, Yuhan Zhu, Yimeng Dong, Hao Gao, Peng Boularias, Abdeslam Li, Hongsheng |
| author_facet | Huang, Siyuan Chang, Haonan Liu, Yuhan Zhu, Yimeng Dong, Hao Gao, Peng Boularias, Abdeslam Li, Hongsheng |
| contents | Vision Language Models (VLMs) have received significant attention in recent years in the robotics community. VLMs are shown to be able to perform complex visual reasoning and scene understanding tasks, which makes them regarded as a potential universal solution for general robotics problems such as manipulation and navigation. However, previous VLMs for robotics such as RT-1, RT-2, and ManipLLM have focused on directly learning robot-centric actions. Such approaches require collecting a significant amount of robot interaction data, which is extremely costly in the real world. Thus, we propose A3VLM, an object-centric, actionable, articulation-aware vision language model. A3VLM focuses on the articulation structure and action affordances of objects. Its representation is robot-agnostic and can be translated into robot actions using simple action primitives. Extensive experiments in both simulation benchmarks and real-world settings demonstrate the effectiveness and stability of A3VLM. We release our code and other materials at https://github.com/changhaonan/A3VLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_07549 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A3VLM: Actionable Articulation-Aware Vision Language Model Huang, Siyuan Chang, Haonan Liu, Yuhan Zhu, Yimeng Dong, Hao Gao, Peng Boularias, Abdeslam Li, Hongsheng Robotics Vision Language Models (VLMs) have received significant attention in recent years in the robotics community. VLMs are shown to be able to perform complex visual reasoning and scene understanding tasks, which makes them regarded as a potential universal solution for general robotics problems such as manipulation and navigation. However, previous VLMs for robotics such as RT-1, RT-2, and ManipLLM have focused on directly learning robot-centric actions. Such approaches require collecting a significant amount of robot interaction data, which is extremely costly in the real world. Thus, we propose A3VLM, an object-centric, actionable, articulation-aware vision language model. A3VLM focuses on the articulation structure and action affordances of objects. Its representation is robot-agnostic and can be translated into robot actions using simple action primitives. Extensive experiments in both simulation benchmarks and real-world settings demonstrate the effectiveness and stability of A3VLM. We release our code and other materials at https://github.com/changhaonan/A3VLM. |
| title | A3VLM: Actionable Articulation-Aware Vision Language Model |
| topic | Robotics |
| url | https://arxiv.org/abs/2406.07549 |