Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network
This addresses robotic grasping for unknown objects in household settings, representing a strong specific gain rather than a broad breakthrough.
The paper tackles the problem of generating antipodal robotic grasps for unknown objects from images, achieving state-of-the-art accuracy of 97.7% on the Cornell dataset and 95.4% grasp success rate on household objects with a robotic arm.
In this paper, we present a modular robotic system to tackle the problem of generating and performing antipodal robotic grasps for unknown objects from n-channel image of the scene. We propose a novel Generative Residual Convolutional Neural Network (GR-ConvNet) model that can generate robust antipodal grasps from n-channel input at real-time speeds (~20ms). We evaluate the proposed model architecture on standard datasets and a diverse set of household objects. We achieved state-of-the-art accuracy of 97.7% and 94.6% on Cornell and Jacquard grasping datasets respectively. We also demonstrate a grasp success rate of 95.4% and 93% on household and adversarial objects respectively using a 7 DoF robotic arm.