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

Constructing a diverse repertoire of manipulation skills in a scalablefashion remains an unsolved challenge in robotics. One way to address thischallenge is with unstructured human play, where humans operate freely in anenvironment to reach unspecified goals. Play is a simple and cheap method forcollecting diverse user demonstrations with broad state and goal coverage overan environment. Due to this diverse coverage, existing approaches for learningfrom play are more robust to online policy deviations from the offline datadistribution. However, these methods often struggle to learn under scenevariation and on challenging manipulation primitives, due in part to improperlyassociating complex behaviors to the scene changes they induce. Our insight isthat an object-centric view of play data can help link human behaviors and theresulting changes in the environment, and thus improve multi-task policylearning. In this work, we construct a latent space to model object affordances-- properties of an object that define its uses -- in the environment, and thenlearn a policy to achieve the desired affordances. By modeling and predictingthe desired affordance across variable horizon tasks, our method, PredictingLatent Affordances Through Object-Centric Play (PLATO), outperforms existingmethods on complex manipulation tasks in both 2D and 3D object manipulationsimulation and real world environments for diverse types of interactions.Videos can be found on our website: https://tinyurl.com/4u23hwfv

PLATO: Predicting Latent Affordances Through Object-Centric Play