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

In this work, we present a reconfigurable data glove design to capturedifferent modes of human hand-object interactions, which are critical intraining embodied artificial intelligence (AI) agents for fine manipulationtasks. To achieve various downstream tasks with distinct features, ourreconfigurable data glove operates in three modes sharing a unified backbonedesign that reconstructs hand gestures in real time. In the tactile-sensingmode, the glove system aggregates manipulation force via customized forcesensors made from a soft and thin piezoresistive material; this designminimizes interference during complex hand movements. The virtual reality (VR)mode enables real-time interaction in a physically plausible fashion: Acaging-based approach is devised to determine stable grasps by detectingcollision events. Leveraging a state-of-the-art finite element method (FEM),the simulation mode collects data on fine-grained 4D manipulation eventscomprising hand and object motions in 3D space and how the object's physicalproperties (e.g., stress and energy) change in accordance with manipulationover time. Notably, the glove system presented here is the first to usehigh-fidelity simulation to investigate the unobservable physical and causalfactors behind manipulation actions. In a series of experiments, wecharacterize our data glove in terms of individual sensors and the overallsystem. More specifically, we evaluate the system's three modes by (i)recording hand gestures and associated forces, (ii) improving manipulationfluency in VR, and (iii) producing realistic simulation effects of various tooluses, respectively. Based on these three modes, our reconfigurable data glovecollects and reconstructs fine-grained human grasp data in both physical andvirtual environments, thereby opening up new avenues for the learning ofmanipulation skills for embodied AI agents.

A Reconfigurable Data Glove for Reconstructing Physical and Virtual Grasps