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

Currently, task-oriented grasp detection approaches are mostly based onpixel-level affordance detection and semantic segmentation. These pixel-levelapproaches heavily rely on the accuracy of a 2D affordance mask, and thegenerated grasp candidates are restricted to a small workspace. To mitigatethese limitations, we first construct a novel affordance-based grasp datasetand propose a 6-DoF task-oriented grasp detection framework, which takes theobserved object point cloud as input and predicts diverse 6-DoF grasp poses fordifferent tasks. Specifically, our implicit estimation network and visualaffordance network in this framework could directly predict coarse graspcandidates, and corresponding 3D affordance heatmap for each potential task,respectively. Furthermore, the grasping scores from coarse grasps are combinedwith heatmap values to generate more accurate and finer candidates. Ourproposed framework shows significant improvements compared to baselines forexisting and novel objects on our simulation dataset. Although our framework istrained based on the simulated objects and environment, the final generatedgrasp candidates can be accurately and stably executed in real robotexperiments when the object is randomly placed on a support surface.

Learning 6-DoF Task-oriented Grasp Detection via Implicit Estimation and Visual Affordance