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/

Zendy Plus

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

Zendy Tools

Zendy Open

Accurate estimation of the relative pose between an object and a robot handis critical for many manipulation tasks. However, most of the existingobject-in-hand pose datasets use two-finger grippers and also assume that theobject remains fixed in the hand without any relative movements, which is notrepresentative of real-world scenarios. To address this issue, a 6Dobject-in-hand pose dataset is proposed using a teleoperation method with ananthropomorphic Shadow Dexterous hand. Our dataset comprises RGB-D images,proprioception and tactile data, covering diverse grasping poses, fingercontact states, and object occlusions. To overcome the significant handocclusion and limited tactile sensor contact in real-world scenarios, wepropose PoseFusion, a hybrid multi-modal fusion approach that integrates theinformation from visual and tactile perception channels. PoseFusion generatesthree candidate object poses from three estimators (tactile only, visual only,and visuo-tactile fusion), which are then filtered by a SelectLSTM network toselect the optimal pose, avoiding inferior fusion poses resulting from modalitycollapse. Extensive experiments demonstrate the robustness and advantages ofour framework. All data and codes are available on the project website:https://elevenjiang1.github.io/ObjectInHand-Dataset/

PoseFusion: Robust Object-in-Hand Pose Estimation with SelectLSTM