# 6-DOF GraspNet: Variational Grasp Generation for Object Manipulation

## TL;DR

This paper introduces 6-DOF GraspNet, a novel method that uses a variational autoencoder to generate and refine grasp poses from 3D point clouds, achieving high success rates in simulation and real-world robot experiments.

## Contribution

It presents a new variational autoencoder-based approach for grasp generation that works directly on point clouds and is trained solely in simulation, enabling effective real-world application.

## Key findings

- Achieves 88% success rate on diverse objects
- Works directly with point clouds from depth cameras
- Operates effectively without additional real-world training

## Abstract

Generating grasp poses is a crucial component for any robot object manipulation task. In this work, we formulate the problem of grasp generation as sampling a set of grasps using a variational autoencoder and assess and refine the sampled grasps using a grasp evaluator model. Both Grasp Sampler and Grasp Refinement networks take 3D point clouds observed by a depth camera as input. We evaluate our approach in simulation and real-world robot experiments. Our approach achieves 88\% success rate on various commonly used objects with diverse appearances, scales, and weights. Our model is trained purely in simulation and works in the real world without any extra steps. The video of our experiments can be found at: https://research.nvidia.com/publication/2019-10_6-DOF-GraspNet\%3A-Variational