Generalized Grasping for Mechanical Grippers for Unknown Objects with Partial Point Cloud Representations

TL;DR

This paper introduces a real-time generalized grasping algorithm using point clouds and voxel grid matching, enabling mechanical grippers to grasp unknown objects with various grasp types based on partial surface data.

Contribution

The novel approach combines histogram-based shape representation and voxel cross-correlation to efficiently find grasp poses for unknown objects from partial point clouds.

Findings

Grasp poses for three types are found in near real-time.

Grasp solutions are consistent across different voxel resolutions.

Planned grasps are successfully executed with a mechanical gripper.

Abstract

We present a generalized grasping algorithm that uses point clouds (i.e. a group of points and their respective surface normals) to discover grasp pose solutions for multiple grasp types, executed by a mechanical gripper, in near real-time. The algorithm introduces two ideas: 1) a histogram of finger contact normals is used to represent a grasp 'shape' to guide a gripper orientation search in a histogram of object(s) surface normals, and 2) voxel grid representations of gripper and object(s) are cross-correlated to match finger contact points, i.e. grasp 'size', to discover a grasp pose. Constraints, such as collisions with neighbouring objects, are optionally incorporated in the cross-correlation computation. We show via simulations and experiments that 1) grasp poses for three grasp types can be found in near real-time, 2) grasp pose solutions are consistent with respect to voxel resolution changes for both partial and complete point cloud scans, and 3) a planned grasp is executed with a mechanical gripper.