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

Physics-based manipulation in clutter involves complex interaction betweenmultiple objects. In this paper, we consider the problem of learning, frominteraction in a physics simulator, manipulation skills to solve thismulti-step sequential decision making problem in the real world. Our approachhas two key properties: (i) the ability to generalize and transfer manipulationskills (over the type, shape, and number of objects in the scene) using anabstract image-based representation that enables a neural network to learnuseful features; and (ii) the ability to perform look-ahead planning in theimage space using a physics simulator, which is essential for such multi-stepproblems. We show, in sets of simulated and real-world experiments (videoavailable on https://youtu.be/EmkUQfyvwkY), that by learning to evaluateactions in an abstract image-based representation of the real world, the robotcan generalize and adapt to the object shapes in challenging real-worldenvironments.

Learning Physics-Based Manipulation in Clutter: Combining Image-Based Generalization and Look-Ahead Planning