High precision grasp pose detection in dense clutter

TL;DR

This paper enhances grasp pose detection in dense clutter by introducing new candidate representations, leveraging prior knowledge, and pretraining, achieving a 93% success rate on a Baxter robot, significantly outperforming previous methods.

Contribution

It proposes novel grasp candidate representations and demonstrates the benefits of prior knowledge and pretraining for improved detection accuracy.

Findings

Achieved 93% grasp success rate in dense clutter.

Improved detection performance by using informative representations.

Pretraining and prior knowledge significantly enhance grasp detection.

Abstract

This paper considers the problem of grasp pose detection in point clouds. We follow a general algorithmic structure that first generates a large set of 6-DOF grasp candidates and then classifies each of them as a good or a bad grasp. Our focus in this paper is on improving the second step by using depth sensor scans from large online datasets to train a convolutional neural network. We propose two new representations of grasp candidates, and we quantify the effect of using prior knowledge of two forms: instance or category knowledge of the object to be grasped, and pretraining the network on simulated depth data obtained from idealized CAD models. Our analysis shows that a more informative grasp candidate representation as well as pretraining and prior knowledge significantly improve grasp detection. We evaluate our approach on a Baxter Research Robot and demonstrate an average grasp success rate of 93% in dense clutter. This is a 20% improvement compared to our prior work.