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

Robots assisting us in factories or homes must learn to make use of objectsas tools to perform tasks, e.g., a tray for carrying objects. We consider theproblem of learning commonsense knowledge of when a tool may be useful and howits use may be composed with other tools to accomplish a high-level taskinstructed by a human. We introduce a novel neural model, termed TANGO, forpredicting task-specific tool interactions, trained using demonstrations fromhuman teachers instructing a virtual robot. TANGO encodes the world state,comprising objects and symbolic relationships between them, using a graphneural network. The model learns to attend over the scene using knowledge ofthe goal and the action history, finally decoding the symbolic action toexecute. Crucially, we address generalization to unseen environments where someknown tools are missing, but alternative unseen tools are present. We show thatby augmenting the representation of the environment with pre-trained embeddingsderived from a knowledge-base, the model can generalize effectively to novelenvironments. Experimental results show a 60.5-78.9% absolute improvement overthe baseline in predicting successful symbolic plans in unseen settings for asimulated mobile manipulator.

TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators