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 use of anthropomorphic robotic hands for assisting individuals insituations where human hands may be unavailable or unsuitable has gainedsignificant importance. In this paper, we propose a novel task calledhuman-assisting dexterous grasping that aims to train a policy for controllinga robotic hand's fingers to assist users in grasping objects. Unlikeconventional dexterous grasping, this task presents a more complex challenge asthe policy needs to adapt to diverse user intentions, in addition to theobject's geometry. We address this challenge by proposing an approachconsisting of two sub-modules: a hand-object-conditional grasping primitivecalled Grasping Gradient Field~(GraspGF), and a history-conditional residualpolicy. GraspGF learns `how' to grasp by estimating the gradient from a successgrasping example set, while the residual policy determines `when' and at whatspeed the grasping action should be executed based on the trajectory history.Experimental results demonstrate the superiority of our proposed methodcompared to baselines, highlighting the user-awareness and practicality inreal-world applications. The codes and demonstrations can be viewed at"https://sites.google.com/view/graspgf".

GraspGF: Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping