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

Grasping objects with limited or no prior knowledge about them is a highlyrelevant skill in assistive robotics. Still, in this general setting, it hasremained an open problem, especially when it comes to only partialobservability and versatile grasping with multi-fingered hands. We present anovel, fast, and high fidelity deep learning pipeline consisting of a shapecompletion module that is based on a single depth image, and followed by agrasp predictor that is based on the predicted object shape. The shapecompletion network is based on VQDIF and predicts spatial occupancy values atarbitrary query points. As grasp predictor, we use our two-stage architecturethat first generates hand poses using an autoregressive model and thenregresses finger joint configurations per pose. Critical factors turn out to besufficient data realism and augmentation, as well as special attention todifficult cases during training. Experiments on a physical robot platformdemonstrate successful grasping of a wide range of household objects based on adepth image from a single viewpoint. The whole pipeline is fast, taking onlyabout 1 s for completing the object's shape (0.7 s) and generating 1000 grasps(0.3 s).

Combining Shape Completion and Grasp Prediction for Fast and Versatile Grasping with a Multi-Fingered Hand