Robotics: Science and Systems XIII

Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics

Jeffrey Mahler, Jacky Liang, Sherdil Niyaz, Michael Laskey, Richard Doan, Xinyu Liu, Juan Aparicio, Ken Goldberg


To reduce data collection time for deep learning of robust robotic grasp plans, we explore training from a synthetic dataset of 6.7 million point clouds, grasps, and robust analytic grasp metrics generated from thousands of 3D models from Dex-Net 1.0 in randomized poses on a table. We use the resulting dataset, Dex-Net 2.0, to train a Grasp Quality Convolutional Neural Network (GQ-CNN) model that rapidly predicts the probability of success of grasps from depth images, where grasps are specified as the planar position, angle, and depth of a gripper relative to an RGB-D sensor. Experiments with over 1,000 trials on an ABB YuMi comparing grasp planning methods on singulated objects suggest that a GQ-CNN trained with only synthetic data from Dex-Net 2.0 can be used to plan grasps in 0.8s with a success rate of 93% on eight known objects with adversarial geometry and is 3x faster than registering point clouds to a precomputed dataset of objects and indexing grasps. The Dex-Net 2.0 grasp planner is also the highest performing method on a dataset of 10 novel rigid objects and achieves 99% precision (one false positive out of 69 grasps classified as robust) on a dataset of 40 novel household objects, some of which are articulated or deformable.



    AUTHOR    = {Jeffrey Mahler AND Jacky Liang AND Sherdil Niyaz AND Michael Laskey AND Richard Doan AND Xinyu Liu AND Juan Aparicio AND Ken Goldberg}, 
    TITLE     = {Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2017}, 
    ADDRESS   = {Cambridge, Massachusetts}, 
    MONTH     = {July}, 
    DOI       = {10.15607/RSS.2017.XIII.058}