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

In recent years, developing AI for robotics has raised much attention. Theinteraction of vision and language of robots is particularly difficult. Weconsider that giving robots an understanding of visual semantics and languagesemantics will improve inference ability. In this paper, we propose a novelmethod-VSGM (Visual Semantic Graph Memory), which uses the semantic graph toobtain better visual image features, improve the robot's visual understandingability. By providing prior knowledge of the robot and detecting the objects inthe image, it predicts the correlation between the attributes of the object andthe objects and converts them into a graph-based representation; and mappingthe object in the image to be a top-down egocentric map. Finally, the importantobject features of the current task are extracted by Graph Neural Networks. Themethod proposed in this paper is verified in the ALFRED (Action Learning FromRealistic Environments and Directives) dataset. In this dataset, the robotneeds to perform daily indoor household tasks following the required languageinstructions. After the model is added to the VSGM, the task success rate canbe improved by 6~10%.

VSGM -- Enhance robot task understanding ability through visual semantic graph