Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2410.02787 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912673040433152 |
|---|---|
| author | Yin, Zecheng Cheng, Chonghao Guo, and Yao Li, Zhen |
| author_facet | Yin, Zecheng Cheng, Chonghao Guo, and Yao Li, Zhen |
| contents | Navigating towards fully open language goals and exploring open scenes in an intelligent way have always raised significant challenges. Recently, Vision Language Models (VLMs) have demonstrated remarkable capabilities to reason with both language and visual data. Although many works have focused on leveraging VLMs for navigation in open scenes, they often require high computational cost, rely on object-centric approaches, or depend on environmental priors in detailed human instructions. We introduce Navigation with VLM (NavVLM), a training-free framework that harnesses open-source VLMs to enable robots to navigate effectively, even for human-friendly language goal such as abstract places, actions, or specific objects in open scenes. NavVLM leverages the VLM as its cognitive core to perceive environmental information and constantly provides exploration guidance achieving intelligent navigation with only a neat target rather than a detailed instruction with environment prior. We evaluated and validated NavVLM in both simulation and real-world experiments. In simulation, our framework achieves state-of-the-art performance in Success weighted by Path Length (SPL) on object-specifc tasks in richly detailed environments from Matterport 3D (MP3D), Habitat Matterport 3D (HM3D) and Gibson. With navigation episode reported, NavVLM demonstrates the capabilities to navigate towards any open-set languages. In real-world validation, we validated our framework's effectiveness in real-world robot at indoor scene. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02787 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Navigation with VLM framework: Towards Going to Any Language Yin, Zecheng Cheng, Chonghao Guo, and Yao Li, Zhen Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Navigating towards fully open language goals and exploring open scenes in an intelligent way have always raised significant challenges. Recently, Vision Language Models (VLMs) have demonstrated remarkable capabilities to reason with both language and visual data. Although many works have focused on leveraging VLMs for navigation in open scenes, they often require high computational cost, rely on object-centric approaches, or depend on environmental priors in detailed human instructions. We introduce Navigation with VLM (NavVLM), a training-free framework that harnesses open-source VLMs to enable robots to navigate effectively, even for human-friendly language goal such as abstract places, actions, or specific objects in open scenes. NavVLM leverages the VLM as its cognitive core to perceive environmental information and constantly provides exploration guidance achieving intelligent navigation with only a neat target rather than a detailed instruction with environment prior. We evaluated and validated NavVLM in both simulation and real-world experiments. In simulation, our framework achieves state-of-the-art performance in Success weighted by Path Length (SPL) on object-specifc tasks in richly detailed environments from Matterport 3D (MP3D), Habitat Matterport 3D (HM3D) and Gibson. With navigation episode reported, NavVLM demonstrates the capabilities to navigate towards any open-set languages. In real-world validation, we validated our framework's effectiveness in real-world robot at indoor scene. |
| title | Navigation with VLM framework: Towards Going to Any Language |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2410.02787 |