arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.00384cs.ROcs.LG
收藏

以对象为中心的抓取偏好的数据有效学习

Data-efficient learning of object-centric grasp preferences

Université de Lorraine(洛林大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);Beijing Institute of Technology(北京理工大学)

Yoann Fleytoux, Anji Ma, Serena Ivaldi, Jean-Baptiste Mouret

摘要:

由于深度学习,抓取在过去几年中取得了令人印象深刻的进展。然而,有许多对象不可能仅通过查看RGB-D图像来选择抓取,可能是由于物理原因(例如,具有不均匀质量分布的锤子)或任务约束(例如,不应该被破坏的食物)。在这种情况下,需要考虑到专家的偏好。在本文中,我们引入了一个数据高效的抓取管道(潜在空间GP- LGPS),它可以学习抓取偏好,每个对象只有几个标签(通常为1到4个),并推广到这个对象的新视图。我们的流水线是基于利用任何最先进的抓取生成器(例如,Dex-Net)。这个潜在的空间,然后被用作高斯过程分类器的低维输入,该分类器在由生成器提出的那些抓取中选择优选的抓取。结果表明,我们的方法在Cornell数据集上的性能优于GR-ConvNet和GG-CNN(两种基于标记抓取的最先进方法),特别是当只使用少数标签时:只有80个标签足以正确选择80%的抓取(885个场景,244个对象)。在我们的数据集(91个场景,28个对象)上的结果相似。

英文摘要:

Grasping made impressive progress during the last few years thanks to deep learning. However, there are many objects for which it is not possible to choose a grasp by only looking at an RGB-D image, might it be for physical reasons (e.g., a hammer with uneven mass distribution) or task constraints (e.g., food that should not be spoiled). In such situations, the preferences of experts need to be taken into account. In this paper, we introduce a data-efficient grasping pipeline (Latent Space GP Selector -- LGPS) that learns grasp preferences with only a few labels per object (typically 1 to 4) and generalizes to new views of this object. Our pipeline is based on learning a latent space of grasps with a dataset generated with any state-of-the-art grasp generator (e.g., Dex-Net). This latent space is then used as a low-dimensional input for a Gaussian process classifier that selects the preferred grasp among those proposed by the generator. The results show that our method outperforms both GR-ConvNet and GG-CNN (two state-of-the-art methods that are also based on labeled grasps) on the Cornell dataset, especially when only a few labels are used: only 80 labels are enough to correctly choose 80% of the grasps (885 scenes, 244 objects). Results are similar on our dataset (91 scenes, 28 objects).

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。

↑