Planning with Spatial and Temporal Abstraction from Point Clouds for Deformable Object Manipulation
Planning with Spatial and Temporal Abstraction from Point Clouds for Deformable Object Manipulation
复制标题
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Xingyu Lin;Carl Qi;Yunchu Zhang;Zhiao Huang;Katerina Fragkiadaki;Yunzhu Li;Chuang Gan;David Held
中科院分区：
文献类型：
--
作者：
Xingyu Lin;Carl Qi;Yunchu Zhang;Zhiao Huang;Katerina Fragkiadaki;Yunzhu Li;Chuang Gan;David Held
：要有效地规划长期可变形对象操作，需要在空间和时间两个层面上进行适当的抽象。以前的方法通常要么专注于短期任务，要么强烈假设完整的状态信息是可用的。但是，可变形对象的完整状态通常不可用。在本文中，我们提出了基于空间和时间抽象的规划(PAPA)，它结合了空间抽象(关于对象及其相互关系的推理)和时间抽象(基于技能的推理而不是低层动作)。该框架将高维三维点云映射为一组潜在向量，并用潜在集表示来规划技能序列。我们的方法可以解决现实世界中具有挑战性的、新颖的顺序可变形对象操纵任务，这些任务需要结合多种工具使用技能，如用刀切割、用推进器推和用滚筒铺面团。更多的材料可以在我们的项目网站上找到。1
: Effective planning of long-horizon deformable object manipulation requires suitable abstractions at both the spatial and temporal levels. Previous methods typically either focus on short-horizon tasks or make the strong assumption that full-state information is available. However, full states of deformable objects are often unavailable. In this paper, we propose PlAnning with Spatial and Temporal Abstraction (PASTA), which incorporates both spatial abstraction (reasoning about objects and their relations to each other) and temporal abstraction (reasoning over skills instead of low-level actions). Our framework maps high-dimension 3D point clouds into a set of latent vectors and plans skill sequences with the latent set representation. Our method can solve challenging, novel sequential deformable object manipulation tasks in the real world, which require combining multiple tool-use skills such as cutting with a knife, pushing with a pusher, and spreading dough with a roller. Additional materials can be found on our project website. 1