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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Despite the impressive progress achieved in robotic grasping, robots are notskilled in sophisticated tasks (e.g. search and grasp a specified target inclutter). Such tasks involve not only grasping but the comprehensive perceptionof the world (e.g. the object relationships). Recently, encouraging resultsdemonstrate that it is possible to understand high-level concepts by learning.However, such algorithms are usually data-intensive, and the lack of dataseverely limits their performance. In this paper, we present a new datasetnamed REGRAD for the learning of relationships among objects and grasps. Wecollect the annotations of object poses, segmentations, grasps, andrelationships for the target-driven relational grasping tasks. Our dataset iscollected in both forms of 2D images and 3D point clouds. Moreover, since allthe data are generated automatically, it is free to import new objects for datageneration. We also released a real-world validation dataset to evaluate thesim-to-real performance of models trained on REGRAD. Finally, we conducted aseries of experiments, showing that the models trained on REGRAD couldgeneralize well to the realistic scenarios, in terms of both relationship andgrasp detection. Our dataset and code could be found at:https://github.com/poisonwine/REGRAD

REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter