Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network

TL;DR

This paper introduces GR-ConvNet, a neural network model that rapidly generates accurate antipodal grasps for unknown objects, enabling real-time robotic grasping with high success rates.

Contribution

The paper presents a novel generative residual convolutional neural network that achieves state-of-the-art accuracy and real-time performance in robotic grasping tasks.

Findings

Achieved 97.7% accuracy on Cornell dataset.

Demonstrated 95.4% grasp success rate on household objects.

Operates at approximately 20ms per inference.

Abstract

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.