Primitive shapes for graspability maps

Grapability maps are data structures that store wrist configurations about an object that lead to successful grasp. They are suitable for both direct use in reach-to-grasp motion planning algorithms and as grasp databases for gripper design analysis and for learning grasp models.
The data includes point cloud models of shape primitives produced synthetically for representing shapes. These primitives were used for creating graspability maps and adapting the maps for complex shapes during run-time. Models include a text file of x,y,z coordinates of the point cloud data and a figure for the following primitives:
Pole: Height – 20, Radius – 2
Sphere: Radius 5
Box: Height – 8, Width – 4, Length – 18
Torus: Radius1 – 0.5, Radius2 – 4
Cone: Radius1 –3, Radius2 – 4.5, Height – 10
Gripper: A two jaw gripper with max opening – 4.7

可操作性映射是一种数据结构，其中存储了关于物体导致成功抓取的手腕配置信息。此类映射适用于直接应用于抓取运动规划算法中，亦可作为抓取数据库，用于抓取器设计分析及抓取模型的训练。数据集包含由人工合成以表征形状的形状原型的点云模型。这些原型被用于构建可操作性映射，并在运行时对复杂形状进行映射调整。模型包括点云数据的 x,y,z 坐标文本文件以及以下原型的图形：
柱形：高度 - 20，半径 - 2
球体：半径 5
立方体：高度 - 8，宽度 - 4，长度 - 18
环面：半径1 - 0.5，半径2 - 4
圆锥：半径1 - 3，半径2 - 4.5，高度 - 10
抓取器：最大开口为 4.7 的双爪抓取器。