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

We study the problem of learning a robot policy to follow natural languageinstructions that can be easily extended to reason about new objects. Weintroduce a few-shot language-conditioned object grounding method trained fromaugmented reality data that uses exemplars to identify objects and align themto their mentions in instructions. We present a learned map representation thatencodes object locations and their instructed use, and construct it from ourfew-shot grounding output. We integrate this mapping approach into aninstruction-following policy, thereby allowing it to reason about previouslyunseen objects at test-time by simply adding exemplars. We evaluate on the taskof learning to map raw observations and instructions to continuous control of aphysical quadcopter. Our approach significantly outperforms the prior state ofthe art in the presence of new objects, even when the prior approach observesall objects during training.

Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following