Constrained Generative Sampling of 6-DoF Grasps

TL;DR

This paper introduces VCGS, a generative network for constrained 6-DoF grasp sampling, enabling task-specific grasps on objects, supported by a large synthetic dataset, and demonstrates improved success rates over existing methods.

Contribution

The work presents VCGS, a novel constrained grasp sampling network, and curates the CONG dataset for training and evaluation, advancing task-specific robotic grasping capabilities.

Findings

VCGS achieves 10-15% higher grasp success rate than baseline.

VCGS is 2-3 times more sample efficient.

The CONG dataset contains over 14 million training samples.

Abstract

Most state-of-the-art data-driven grasp sampling methods propose stable and collision-free grasps uniformly on the target object. For bin-picking, executing any of those reachable grasps is sufficient. However, for completing specific tasks, such as squeezing out liquid from a bottle, we want the grasp to be on a specific part of the object's body while avoiding other locations, such as the cap. This work presents a generative grasp sampling network, VCGS, capable of constrained 6 Degrees of Freedom (DoF) grasp sampling. In addition, we also curate a new dataset designed to train and evaluate methods for constrained grasping. The new dataset, called CONG, consists of over 14 million training samples of synthetically rendered point clouds and grasps at random target areas on 2889 objects. VCGS is benchmarked against GraspNet, a state-of-the-art unconstrained grasp sampler, in simulation and on a real robot. The results demonstrate that VCGS achieves a 10-15% higher grasp success rate than the baseline while being 2-3 times as sample efficient. Supplementary material is available on our project website.