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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Upper limb and hand functionality is critical to many activities of dailyliving and the amputation of one can lead to significant functionality loss forindividuals. From this perspective, advanced prosthetic hands of the future areanticipated to benefit from improved shared control between a robotic hand andits human user, but more importantly from the improved capability to inferhuman intent from multimodal sensor data to provide the robotic hand perceptionabilities regarding the operational context. Such multimodal sensor data mayinclude various environment sensors including vision, as well as humanphysiology and behavior sensors including electromyography and inertialmeasurement units. A fusion methodology for environmental state and humanintent estimation can combine these sources of evidence in order to helpprosthetic hand motion planning and control.  In this paper, we present a dataset of this type that was gathered with theanticipation of cameras being built into prosthetic hands, and computer visionmethods will need to assess this hand-view visual evidence in order to estimatehuman intent. Specifically, paired images from human eye-view and hand-view ofvarious objects placed at different orientations have been captured at theinitial state of grasping trials, followed by paired video, EMG and IMU fromthe arm of the human during a grasp, lift, put-down, and retract style trialstructure. For each trial, based on eye-view images of the scene showing thehand and object on a table, multiple humans were asked to sort in decreasingorder of preference, five grasp types appropriate for the object in its givenconfiguration relative to the hand. The potential utility of paired eye-viewand hand-view images was illustrated by training a convolutional neural networkto process hand-view images in order to predict eye-view labels assigned byhumans.

HANDS: A Multimodal Dataset for Modeling Towards Human Grasp Intent Inference in Prosthetic Hands