1. [Publications](/index.php/publications)
2. 6-DOF GraspNet: Variational Grasp Generation for Object Manipulation
 
 # 6-DOF GraspNet: Variational Grasp Generation for Object Manipulation

  ![](/sites/default/files/styles/wide/public/publications/Robot_and_objects_and_grasps.png?itok=9EdVwjya)

 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.



 ## Authors



Arsalan Mousavian (NVIDIA)

Clemens Eppner (NVIDIA)

Dieter Fox (NVIDIA)

 

 

 ## Publication Date



Sunday, October 27, 2019

 

 ## Published in



[ICCV 2019](http://iccv2019.thecvf.com/)

 

 ## Research Area



[Computer Vision](/index.php/research-area/computer-vision)

[Robotics](/index.php/research-area/robotics)

 

 

 ## External Links



[Paper](https://arxiv.org/abs/1905.10520)

[Blog Post](https://news.developer.nvidia.com/new-nvidia-research-helps-robots-improve-their-grasp/)

[Video](https://www.youtube.com/watch?v=y5EJXeEiB1o)