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

Effective planning of long-horizon deformable object manipulation requiressuitable abstractions at both the spatial and temporal levels. Previous methodstypically either focus on short-horizon tasks or make strong assumptions thatfull-state information is available, which prevents their use on deformableobjects. In this paper, we propose PlAnning with Spatial-Temporal Abstraction(PASTA), which incorporates both spatial abstraction (reasoning about objectsand their relations to each other) and temporal abstraction (reasoning overskills instead of low-level actions). Our framework maps high-dimension 3Dobservations such as point clouds into a set of latent vectors and plans overskill sequences on top of the latent set representation. We show that ourmethod can effectively perform challenging sequential deformable objectmanipulation tasks in the real world, which require combining multiple tool-useskills such as cutting with a knife, pushing with a pusher, and spreading thedough with a roller.

Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation