arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.06331cs.RO
收藏

用动态图CNN从点云中学习类别级操作任务

Learning Category-Level Manipulation Tasks from Point Clouds with Dynamic Graph CNNs

Rutgers University(罗格斯大学)

Junchi Liang, Abdeslam Boularias

摘要:

本文提出了一种新的技术,用于从任务演示的原始RGB-D视频中学习类别级操作,无需手动标签或注释。类别级学习旨在获得可以推广到新对象的技能,这些对象的几何形状和纹理与演示中使用的对象不同。我们解决这个问题,首先查看两个抓和操纵作为特殊情况下的工具使用,其中一个工具对象被移动到一个序列的关键构成定义在一个参考框架的目标对象。工具和目标对象,以及他们的关键姿态,预测使用动态图卷积神经网络,作为输入的自动分割的深度和彩色图像的整个场景。在一个真实的机器人手臂上进行物体操作任务的实验结果表明,该网络可以有效地从真实的视觉演示中学习,在同一类别的新物体上执行任务,并优于其他方法。

英文摘要:

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.

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。

↑