English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The method of deep learning has achieved excellent results in improving theperformance of robotic grasping detection. However, the deep learning methodsused in general object detection are not suitable for robotic graspingdetection. Current modern object detectors are difficult to strike a balancebetween high accuracy and fast inference speed. In this paper, we present anefficient and robust fully convolutional neural network model to performrobotic grasping pose estimation from an n-channel input image of the realgrasping scene. The proposed network is a lightweight generative architecturefor grasping detection in one stage. Specifically, a grasping representationbased on Gaussian kernel is introduced to encode training samples, whichembodies the principle of maximum central point grasping confidence. Meanwhile,to extract multi-scale information and enhance the feature discriminability, areceptive field block (RFB) is assembled to the bottleneck of our graspingdetection architecture. Besides, pixel attention and channel attention arecombined to automatically learn to focus on fusing context information ofvarying shapes and sizes by suppressing the noise feature and highlighting thegrasping object feature. Extensive experiments on two public grasping datasets,Cornell and Jacquard demonstrate the state-of-the-art performance of our methodin balancing accuracy and inference speed. The network is an order of magnitudesmaller than other excellent algorithms while achieving better performance withan accuracy of 98.9$\%$ and 95.6$\%$ on the Cornell and Jacquard datasets,respectively.

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