论文标题
以对象为中心的GRASP偏好的数据有效学习
Data-efficient learning of object-centric grasp preferences
论文作者
论文摘要
由于深度学习，抓地力在过去几年中取得了令人印象深刻的进步。但是，有许多物体无法通过仅查看RGB-D图像来选择掌握，这可能是出于物理原因（例如，具有不均匀质量分布的锤子）或任务限制（例如，不应被宠坏的食物）。在这种情况下，需要考虑专家的偏好。 在本文中，我们介绍了一个数据效率的握把管道（潜在空间GP选择器-LGP），该管道学习每个对象只有几个标签（通常为1到4），并将其推广到该对象的新视图。我们的管道基于学习带有任何最先进的GRASP发电机（例如DEX-NET）生成的数据集的Grasps潜在空间。然后，该潜在空间用作高斯过程分类器的低维输入，该分类器在发电机提出的那些中选择了首选的掌握。 结果表明，我们的方法优于gr-convnet和gg-cnn（两种基于标记的grasps的最先进的方法）在康奈尔数据集上，尤其是当仅使用少数标签时：只有80个标签足以正确地选择80％的Grasps（885 Scenes，244对象）。结果在我们的数据集（91个场景，28个对象）上相似。
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).
