Learning robust, real-time, reactive robotic grasping. (March 2020)

• Record Type: Journal Article
• Authors: Morrison, Douglas; Corke, Peter; Leitner, Jürgen
• Is Part Of: International journal of robotics research. Volume 39:Number 2/3(2020)
• Page Start: 183
• Page End: 201
• Publication Date: 2020-03
• Subjects: Grasping -- vision -- learning; Robots -- Periodicals; Robots, Industrial -- Periodicals; 629.89205
• DOI: 10.1177/0278364919859066
• Languages: English
• ISSNs: 0278-3649

Abstract

We present a novel approach to perform object-independent grasp synthesis from depth images via deep neural networks. Our generative grasping convolutional neural network (GG-CNN) predicts a pixel-wise grasp quality that can be deployed in closed-loop grasping scenarios. GG-CNN overcomes shortcomings in existing techniques, namely discrete sampling of grasp candidates and long computation times. The network is orders of magnitude smaller than other state-of-the-art approaches while achieving better performance, particularly in clutter. We run a suite of real-world tests, during which we achieve an 84% grasp success rate on a set of previously unseen objects with adversarial geometry and 94% on household items. The lightweight nature enables closed-loop control of up to 50 Hz, with which we observed 88% grasp success on a set of household objects that are moved during the grasp attempt. We further propose a method combining our GG-CNN with a multi-view approach, which improves overall grasp success rate in clutter by 10%. Code is provided athttps://github.com/dougsm/ggcnn