arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.04533cs.ROcs.CVcs.LG
收藏

Dream2Real:基于视觉语言模型的零样本3D物体重排

Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Models

Imperial College London(帝国理工学院);The Robot Learning Lab at Imperial College London(帝国理工学院机器人学习实验室);The Dyson Robotics Lab at Imperial College London(帝国理工学院戴森机器人实验室)

Ivan Kapelyukh, Yifei Ren, Ignacio Alzugaray, Edward Johns

AI总结:

本文提出Dream2Real框架,通过将视觉语言模型集成到3D物体重排流水线中,利用机器人自主构建场景3D表示并渲染虚拟布局,由VLM评估选出最佳方案后执行拾取与放置,实现了无需训练数据的零样本语言条件重排。

摘要:

我们引入了Dream2Real,这是一个将基于2D数据训练的视觉语言模型(VLMs)集成到3D物体重排流水线中的机器人框架。该框架通过机器人自主构建场景的3D表示来实现,在场景中可以虚拟地重排物体并渲染出结果布局的图像。这些渲染图像由VLM进行评估,从而选择最符合用户指令的布局,并通过拾取与放置在真实世界中重现。这使得语言条件下的重排能够零样本执行,无需收集示例布局的训练数据集。在一系列真实世界任务上的结果表明,该框架对干扰物具有鲁棒性,可由语言控制,能够理解复杂的多物体关系,并且适用于桌面和6自由度(6-DoF)重排任务。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑