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

Motion prediction in unstructured environments is a difficult problem and isessential for safe and efficient human-robot space sharing and collaboration.In this work, we focus on manipulation movements in environments such as homes,workplaces or restaurants, where the overall task and environment can beleveraged to produce accurate motion prediction. For these cases we propose analgorithmic framework that accounts explicitly for the environment geometrybased on a model of affordances and a model of short-term human dynamics bothtrained on motion capture data. We propose dedicated function networks forgraspability and placebility affordances and we make use of a dedicated RNN forshort-term motion prediction. The prediction of grasp and placement probabilitydensities are used by a constraint-based trajectory optimizer to produce afull-body motion prediction over the entire horizon. We show by comparing toground truth data that we achieve similar performance for full-body motionpredictions as using oracle grasp and place locations.

Anticipating Human Intention for Full-Body Motion Prediction in Object Grasping and Placing Tasks