论文标题
从点云中学习类别级的操纵任务，带有动态图CNN
Learning Category-Level Manipulation Tasks from Point Clouds with Dynamic Graph CNNs
论文作者
论文摘要
本文介绍了一种新技术，用于从原始的RGB-D视频中学习类别级别的操作，没有手动标签或注释。类别级学习旨在获得可以推广到新对象的技能，其几何形状和纹理与演示中使用的对象不同。我们通过首先将抓地力和操作视为工具使用的特殊情况来解决这个问题，其中工具对象被移至目标对象的参考框架中定义的一系列键置。使用动态图卷积神经网络预测工具和目标对象以及它们的钥匙置，该网络将整个场景的自动分割深度和颜色图像作为输入。具有真实机器人手臂的对象操纵任务的经验结果表明，所提出的网络可以有效地从真实的视觉演示中学习，以在同一类别内的新对象上执行任务，并且要优于其他方法。
This paper presents a new technique for learning category-level manipulation from raw RGB-D videos of task demonstrations, with no manual labels or annotations. Category-level learning aims to acquire skills that can be generalized to new objects, with geometries and textures that are different from the ones of the objects used in the demonstrations. We address this problem by first viewing both grasping and manipulation as special cases of tool use, where a tool object is moved to a sequence of key-poses defined in a frame of reference of a target object. Tool and target objects, along with their key-poses, are predicted using a dynamic graph convolutional neural network that takes as input an automatically segmented depth and color image of the entire scene. Empirical results on object manipulation tasks with a real robotic arm show that the proposed network can efficiently learn from real visual demonstrations to perform the tasks on novel objects within the same category, and outperforms alternative approaches.
