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

Articulated objects like cabinets and doors are widespread in daily life.However, directly manipulating 3D articulated objects is challenging becausethey have diverse geometrical shapes, semantic categories, and kineticconstraints. Prior works mostly focused on recognizing and manipulatingarticulated objects with specific joint types. They can either estimate thejoint parameters or distinguish suitable grasp poses to facilitate trajectoryplanning. Although these approaches have succeeded in certain types ofarticulated objects, they lack generalizability to unseen objects, whichsignificantly impedes their application in broader scenarios. In this paper, wepropose a novel framework of Generalizable Articulation Modeling andManipulating for Articulated Objects (GAMMA), which learns both articulationmodeling and grasp pose affordance from diverse articulated objects withdifferent categories. In addition, GAMMA adopts adaptive manipulation toiteratively reduce the modeling errors and enhance manipulation performance. Wetrain GAMMA with the PartNet-Mobility dataset and evaluate with comprehensiveexperiments in SAPIEN simulation and real-world Franka robot. Results show thatGAMMA significantly outperforms SOTA articulation modeling and manipulationalgorithms in unseen and cross-category articulated objects. We willopen-source all codes and datasets in both simulation and real robots forreproduction in the final version. Images and videos are published on theproject website at: http://sites.google.com/view/gamma-articulation

GAMMA: Generalizable Articulation Modeling and Manipulation for Articulated Objects