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

Fabric manipulation is a long-standing challenge in robotics due to theenormous state space and complex dynamics. Learning approaches stand out aspromising for this domain as they allow us to learn behaviours directly fromdata. Most prior methods however rely heavily on simulation, which is stilllimited by the large sim-to-real gap of deformable objects or rely on largedatasets. A promising alternative is to learn fabric manipulation directly fromwatching humans perform the task. In this work, we explore how demonstrationsfor fabric manipulation tasks can be collected directly by humans, providing anextremely natural and fast data collection pipeline. Then, using only a handfulof such demonstrations, we show how a pick-and-place policy can be learned anddeployed on a real robot, without any robot data collection at all. Wedemonstrate our approach on a fabric folding task, showing that our policy canreliably reach folded states from crumpled initial configurations. Videos areavailable at: https://sites.google.com/view/foldingbyhand

Learning Fabric Manipulation in the Real World with Human Videos