Corpus ID: 231698380

Lightweight Convolutional Neural Network with Gaussian-based Grasping Representation for Robotic Grasping Detection

  title={Lightweight Convolutional Neural Network with Gaussian-based Grasping Representation for Robotic Grasping Detection},
  author={Hu Cao and G. Chen and Zhijun Li and Jianjie Lin and A. Knoll},
The method of deep learning has achieved excellent results in improving the performance of robotic grasping detection. However, the deep learning methods used in general object detection are not suitable for robotic grasping detection. Current modern object detectors are difficult to strike a balance between high accuracy and fast inference speed. In this paper, we present an efficient and robust fully convolutional neural network model to perform robotic grasping pose estimation from n-channel… Expand


Robot grasp detection using multimodal deep convolutional neural networks
A novel robot grasp detection system that maps a pair of RGB-D images of novel objects to best grasping pose of a robotic gripper and presents a two-stage closed-loop grasping candidate estimator to accelerate the searching efficiency of grasping-candidate generation. Expand
Robotic grasp detection using deep convolutional neural networks
  • S. Kumra, Christopher Kanan
  • Computer Science, Engineering
  • 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2017
A novel robotic grasp detection system that predicts the best grasping pose of a parallel-plate robotic gripper for novel objects using the RGB-D image of the scene and then uses a shallow convolutional neural network to predict the grasp configuration for the object of interest. Expand
Multi-Object Grasping Detection With Hierarchical Feature Fusion
A novel grasp detection algorithm termed as multi-object grasping detection network, which can utilize hierarchical features to learn object detector and grasping pose estimator simultaneously simultaneously is presented. Expand
GraspNet: An Efficient Convolutional Neural Network for Real-time Grasp Detection for Low-powered Devices
It is shown that GraspNet achieves competitive grasp detection accuracy compared to the stateof-the-art computation-efficient CNN models with real-time inference speed on embedded GPU hardware (Nvidia Jetson TX1), making it suitable for low-powered devices. Expand
Real-Time, Highly Accurate Robotic Grasp Detection using Fully Convolutional Neural Networks with High-Resolution Images
This paper proposes fully convolutional neural network (FCNN) based methods for robotic grasp detection that achieved state-of-the-art detection accuracy and real-time computation time for high-resolution images on Cornell dataset. Expand
Learning robust, real-time, reactive robotic grasping
A novel approach to perform object-independent grasp synthesis from depth images via deep neural networks overcomes shortcomings in existing techniques, namely discrete sampling of grasp candidates and long computation times, and achieves better performance, particularly in clutter. Expand
Fully Convolutional Grasp Detection Network with Oriented Anchor Box
A real-time approach to predict multiple grasping poses for a parallel-plate robotic gripper using RGB images using a model with oriented anchor box mechanism and outperforms the latest state-of-the-art approach. Expand
Jacquard: A Large Scale Dataset for Robotic Grasp Detection
The results show that Jacquard enables much better generalization skills than a human labeled dataset thanks to its diversity of objects and grasping positions. Expand
Deep learning for detecting robotic grasps
This work presents a two-step cascaded system with two deep networks, where the top detections from the first are re-evaluated by the second, and shows that this method improves performance on an RGBD robotic grasping dataset, and can be used to successfully execute grasps on two different robotic platforms. Expand
Classification based Grasp Detection using Spatial Transformer Network
This work proposes a novel classification based robotic grasp detection method with multiple-stage spatial transformer networks (STN) that was able to achieve state-of-the-art performance in accuracy with real- time computation. Expand