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

Objects rarely sit in isolation in everyday human environments. If we wantrobots to operate and perform tasks in our human environments, they mustunderstand how the objects they manipulate will interact with structuralelements of the environment for all but the simplest of tasks. As such, we'dlike our robots to reason about how multiple objects and environmental elementsrelate to one another and how those relations may change as the robot interactswith the world. We examine the problem of predicting inter-object andobject-environment relations between previously unseen objects and novelenvironments purely from partial-view point clouds. Our approach enables robotsto plan and execute sequences to complete multi-object manipulation tasksdefined from logical relations. This removes the burden of providing explicit,continuous object states as goals to the robot. We explore several differentneural network architectures for this task. We find the best performing modelto be a novel transformer-based neural network that both predictsobject-environment relations and learns a latent-space dynamics function. Weachieve reliable sim-to-real transfer without any fine-tuning. Our experimentsshow that our model understands how changes in observed environmental geometryrelate to semantic relations between objects. We show more videos on ourwebsite: https://sites.google.com/view/erelationaldynamics.

Latent Space Planning for Multi-Object Manipulation with Environment-Aware Relational Classifiers