PointNet++ Grasping: Learning An End-to-end Spatial Grasp Generation Algorithm from Sparse Point Clouds

TL;DR

This paper introduces an end-to-end deep learning approach using PointNet++ for direct grasp prediction from sparse point clouds, eliminating the need for sampling and search, and achieving high success rates in robotic grasping tasks.

Contribution

It presents a novel end-to-end grasp detection method that directly predicts grasp poses from sparse point clouds without sampling, and introduces a fast multi-object grasp dataset generation algorithm.

Findings

Achieves 71.43% success rate in grasping tasks.

Predicts grasps in 102ms on a GeForce 840M GPU.

Outperforms current state-of-the-art methods.

Abstract

Grasping for novel objects is important for robot manipulation in unstructured environments. Most of current works require a grasp sampling process to obtain grasp candidates, combined with local feature extractor using deep learning. This pipeline is time-costly, expecially when grasp points are sparse such as at the edge of a bowl. In this paper, we propose an end-to-end approach to directly predict the poses, categories and scores (qualities) of all the grasps. It takes the whole sparse point clouds as the input and requires no sampling or search process. Moreover, to generate training data of multi-object scene, we propose a fast multi-object grasp detection algorithm based on Ferrari Canny metrics. A single-object dataset (79 objects from YCB object set, 23.7k grasps) and a multi-object dataset (20k point clouds with annotations and masks) are generated. A PointNet++ based network combined with multi-mask loss is introduced to deal with different training points. The whole weight size of our network is only about 11.6M, which takes about 102ms for a whole prediction process using a GeForce 840M GPU. Our experiment shows our work get 71.43% success rate and 91.60% completion rate, which performs better than current state-of-art works.