Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.04533 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911971265216512 |
|---|---|
| author | Kapelyukh, Ivan Ren, Yifei Alzugaray, Ignacio Johns, Edward |
| author_facet | Kapelyukh, Ivan Ren, Yifei Alzugaray, Ignacio Johns, Edward |
| contents | We introduce Dream2Real, a robotics framework which integrates vision-language models (VLMs) trained on 2D data into a 3D object rearrangement pipeline. This is achieved by the robot autonomously constructing a 3D representation of the scene, where objects can be rearranged virtually and an image of the resulting arrangement rendered. These renders are evaluated by a VLM, so that the arrangement which best satisfies the user instruction is selected and recreated in the real world with pick-and-place. This enables language-conditioned rearrangement to be performed zero-shot, without needing to collect a training dataset of example arrangements. Results on a series of real-world tasks show that this framework is robust to distractors, controllable by language, capable of understanding complex multi-object relations, and readily applicable to both tabletop and 6-DoF rearrangement tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_04533 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Models Kapelyukh, Ivan Ren, Yifei Alzugaray, Ignacio Johns, Edward Robotics Computer Vision and Pattern Recognition Machine Learning We introduce Dream2Real, a robotics framework which integrates vision-language models (VLMs) trained on 2D data into a 3D object rearrangement pipeline. This is achieved by the robot autonomously constructing a 3D representation of the scene, where objects can be rearranged virtually and an image of the resulting arrangement rendered. These renders are evaluated by a VLM, so that the arrangement which best satisfies the user instruction is selected and recreated in the real world with pick-and-place. This enables language-conditioned rearrangement to be performed zero-shot, without needing to collect a training dataset of example arrangements. Results on a series of real-world tasks show that this framework is robust to distractors, controllable by language, capable of understanding complex multi-object relations, and readily applicable to both tabletop and 6-DoF rearrangement tasks. |
| title | Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Models |
| topic | Robotics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2312.04533 |