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

We address the longstanding challenge of producing flexible, realistichumanoid character controllers that can perform diverse whole-body tasksinvolving object interactions. This challenge is central to a variety offields, from graphics and animation to robotics and motor neuroscience. Ourphysics-based environment uses realistic actuation and first-person perception-- including touch sensors and egocentric vision -- with a view to producingactive-sensing behaviors (e.g. gaze direction), transferability to real robots,and comparisons to the biology. We develop an integrated neural-network basedapproach consisting of a motor primitive module, human demonstrations, and aninstructed reinforcement learning regime with curricula and task variations. Wedemonstrate the utility of our approach for several tasks, includinggoal-conditioned box carrying and ball catching, and we characterize itsbehavioral robustness. The resulting controllers can be deployed in real-timeon a standard PC. See overview video, https://youtu.be/2rQAW-8gQQk .

Catch & Carry: Reusable Neural Controllers for Vision-Guided Whole-Body Tasks