Antipodal Robotic Grasping using Generative Residual Convolutional Neural Network (2019-09-11T00:00:00.000000Z)

TL;DR

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) is proposed.

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 the 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.

Authors

Sulabh Kumra

1 papers

Shirin Joshi

1 papers

F. Sahin

1 papers

TL;DR

Abstract

Authors

References43 items

Learning robust, real-time, reactive robotic grasping

Data-Efficient Learning for Sim-to-Real Robotic Grasping using Deep Point Cloud Prediction Networks

Object Detection Approach for Robot Grasp Detection

Learning Probabilistic Multi-Modal Actor Models for Vision-Based Robotic Grasping

On-Policy Dataset Synthesis for Learning Robot Grasping Policies Using Fully Convolutional Deep Networks

A Robotic Grasping Method using ConvNets

Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks

Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects

Semantic and geometric reasoning for robotic grasping: a probabilistic logic approach

Real-World Multiobject, Multigrasp Detection

GraspNet: An Efficient Convolutional Neural Network for Real-time Grasp Detection for Low-powered Devices

Grasping of Unknown Objects Using Deep Convolutional Neural Networks Based on Depth Images

Jacquard: A Large Scale Dataset for Robotic Grasp Detection

Fully Convolutional Grasp Detection Network with Oriented Anchor Box

Domain Randomization and Generative Models for Robotic Grasping

Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching

A hybrid deep architecture for robotic grasp detection

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

RGB-D Object Recognition and Grasp Detection Using Hierarchical Cascaded Forests

Robotic grasp detection using deep convolutional neural networks

Shape completion enabled robotic grasping

Robot grasp detection using multimodal deep convolutional neural networks

Deep learning a grasp function for grasping under gripper pose uncertainty

One-shot learning and generation of dexterous grasps for novel objects

Depth Image Inpainting: Improving Low Rank Matrix Completion With Low Gradient Regularization

Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection

Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours

Adam: A Method for Stochastic Optimization

Real-time grasp detection using convolutional neural networks

Stochastic Proximal Gradient Descent with Acceleration Techniques

Data-Driven Grasp Synthesis—A Survey

Deep learning for detecting robotic grasps

Efficient grasping from RGBD images: Learning using a new rectangle representation

Cloth grasp point detection based on multiple-view geometric cues with application to robotic towel folding

Robotic Grasping of Novel Objects using Vision

Optimal Hand-Eye Calibration

A Framework for Visual Servoing

Robotic grasping and contact: a review

Robot Grasp Synthesis Algorithms: A Survey

On the Closure Properties of Robotic Grasping

“Research computing services,”

EnsembleNet: Improving Grasp Detection using an Ensemble of Convolutional Neural Networks

Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names