Task-Oriented Grasping with Point Cloud Representation of Objects

TL;DR

This paper introduces a neural network-based method for task-oriented grasp synthesis from partial point cloud data, enabling effective grasp planning without manual labels or simulation, suitable for manipulation tasks involving screw motions.

Contribution

The work presents a novel approach that predicts grasp quality from bounding boxes derived from partial point clouds, avoiding manual labeling and simulation, and integrates with screw motion planning.

Findings

Effective grasp region prediction from partial point clouds

No manual labeling or simulation required

Successful in simulation and real-world experiments

Abstract

In this paper, we study the problem of task-oriented grasp synthesis from partial point cloud data using an eye-in-hand camera configuration. In task-oriented grasp synthesis, a grasp has to be selected so that the object is not lost during manipulation, and it is also ensured that adequate force/moment can be applied to perform the task. We formalize the notion of a gross manipulation task as a constant screw motion (or a sequence of constant screw motions) to be applied to the object after grasping. Using this notion of task, and a corresponding grasp quality metric developed in our prior work, we use a neural network to approximate a function for predicting the grasp quality metric on a cuboid shape. We show that by using a bounding box obtained from the partial point cloud of an object, and the grasp quality metric mentioned above, we can generate a good grasping region on the bounding box that can be used to compute an antipodal grasp on the actual object. Our algorithm does not use any manually labeled data or grasping simulator, thus making it very efficient to implement and integrate with screw linear interpolation-based motion planners. We present simulation as well as experimental results that show the effectiveness of our approach.