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 vision-based grasp detection method is an important research direction inthe field of robotics. However, due to the rectangle metric of the graspdetection rectangle's limitation, a false-positive grasp occurs, resulting inthe failure of the real-world robot grasp task. In this paper, we propose anovel generative convolutional neural network model to improve the accuracy androbustness of robot grasp detection in real-world scenes. First, aGaussian-based guided training method is used to encode the quality of thegrasp point and grasp angle in the grasp pose, highlighting the highest-qualitygrasp point position and grasp angle and reducing the generation offalse-positive grasps. Simultaneously, deformable convolution is used to obtainthe shape features of the object in order to guide the subsequent network tothe position. Furthermore, a global-local feature fusion method is introducedin order to efficiently obtain finer features during the feature reconstructionstage, allowing the network to focus on the features of the grasped objects. Onthe Cornell Grasping Datasets and Jacquard Datasets, our method achievesexcellent performance of 99.0$\%$ and 95.9$\%$, respectively. Finally, theproposed method is put to the test in a real-world robot grasping scenario.

A Novel Generative Convolutional Neural Network for Robot Grasp Detection on Gaussian Guidance