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

Achieving human-like dexterous manipulation remains a crucial area ofresearch in robotics. Current research focuses on improving the success rate ofpick-and-place tasks. Compared with pick-and-place, throw-catching behavior hasthe potential to increase picking speed without transporting objects to theirdestination. However, dynamic dexterous manipulation poses a major challengefor stable control due to a large number of dynamic contacts. In this paper, wepropose a Stability-Constrained Reinforcement Learning (SCRL) algorithm tolearn to catch diverse objects with dexterous hands. The SCRL algorithmoutperforms baselines by a large margin, and the learned policies show strongzero-shot transfer performance on unseen objects. Remarkably, even though theobject in a hand facing sideward is extremely unstable due to the lack ofsupport from the palm, our method can still achieve a high level of success inthe most challenging task. Video demonstrations of learned behaviors and thecode can be found on the supplementary website.

DexCatch: Learning to Catch Arbitrary Objects with Dexterous Hands