6-DOF GraspNet: Variational Grasp Generation for Object Manipulation
This work addresses the challenge of reliable grasp generation for robots, enabling manipulation of objects with varied appearances, scales, and weights, and is incremental as it builds on existing grasp generation methods with a hybrid approach.
The paper tackles the problem of generating grasp poses for robot object manipulation by using a variational autoencoder to sample grasps and a refinement network to assess them, achieving an 88% success rate on diverse objects in both simulation and real-world experiments.
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