OVAL-Prompt: Open-Vocabulary Affordance Localization for Robot Manipulation through LLM Affordance-Grounding
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913363767853056 |
|---|---|
| author | Tong, Edmond Opipari, Anthony Lewis, Stanley Zeng, Zhen Jenkins, Odest Chadwicke |
| author_facet | Tong, Edmond Opipari, Anthony Lewis, Stanley Zeng, Zhen Jenkins, Odest Chadwicke |
| contents | In order for robots to interact with objects effectively, they must understand the form and function of each object they encounter. Essentially, robots need to understand which actions each object affords, and where those affordances can be acted on. Robots are ultimately expected to operate in unstructured human environments, where the set of objects and affordances is not known to the robot before deployment (i.e. the open-vocabulary setting). In this work, we introduce OVAL-Prompt, a prompt-based approach for open-vocabulary affordance localization in RGB-D images. By leveraging a Vision Language Model (VLM) for open-vocabulary object part segmentation and a Large Language Model (LLM) to ground each part-segment-affordance, OVAL-Prompt demonstrates generalizability to novel object instances, categories, and affordances without domain-specific finetuning. Quantitative experiments demonstrate that without any finetuning, OVAL-Prompt achieves localization accuracy that is competitive with supervised baseline models. Moreover, qualitative experiments show that OVAL-Prompt enables affordance-based robot manipulation of open-vocabulary object instances and categories. Project Page: https://ekjt.github.io/OVAL-Prompt/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_11000 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OVAL-Prompt: Open-Vocabulary Affordance Localization for Robot Manipulation through LLM Affordance-Grounding Tong, Edmond Opipari, Anthony Lewis, Stanley Zeng, Zhen Jenkins, Odest Chadwicke Robotics In order for robots to interact with objects effectively, they must understand the form and function of each object they encounter. Essentially, robots need to understand which actions each object affords, and where those affordances can be acted on. Robots are ultimately expected to operate in unstructured human environments, where the set of objects and affordances is not known to the robot before deployment (i.e. the open-vocabulary setting). In this work, we introduce OVAL-Prompt, a prompt-based approach for open-vocabulary affordance localization in RGB-D images. By leveraging a Vision Language Model (VLM) for open-vocabulary object part segmentation and a Large Language Model (LLM) to ground each part-segment-affordance, OVAL-Prompt demonstrates generalizability to novel object instances, categories, and affordances without domain-specific finetuning. Quantitative experiments demonstrate that without any finetuning, OVAL-Prompt achieves localization accuracy that is competitive with supervised baseline models. Moreover, qualitative experiments show that OVAL-Prompt enables affordance-based robot manipulation of open-vocabulary object instances and categories. Project Page: https://ekjt.github.io/OVAL-Prompt/ |
| title | OVAL-Prompt: Open-Vocabulary Affordance Localization for Robot Manipulation through LLM Affordance-Grounding |
| topic | Robotics |
| url | https://arxiv.org/abs/2404.11000 |