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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper tackles the task of goal-conditioned dynamic manipulation ofdeformable objects. This task is highly challenging due to its complex dynamics(introduced by object deformation and high-speed action) and strict taskrequirements (defined by a precise goal specification). To address thesechallenges, we present Iterative Residual Policy (IRP), a general learningframework applicable to repeatable tasks with complex dynamics. IRP learns animplicit policy via delta dynamics -- instead of modeling the entire dynamicalsystem and inferring actions from that model, IRP learns delta dynamics thatpredict the effects of delta action on the previously-observed trajectory. Whencombined with adaptive action sampling, the system can quickly optimize itsactions online to reach a specified goal. We demonstrate the effectiveness ofIRP on two tasks: whipping a rope to hit a target point and swinging a cloth toreach a target pose. Despite being trained only in simulation on a fixed robotsetup, IRP is able to efficiently generalize to noisy real-world dynamics, newobjects with unseen physical properties, and even different robot hardwareembodiments, demonstrating its excellent generalization capability relative toalternative approaches. Video is available at https://youtu.be/7h3SZ3La-oA

Iterative Residual Policy: for Goal-Conditioned Dynamic Manipulation of Deformable Objects