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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this paper, we propose a framework of building knowledgeable robot controlin the scope of smart human-robot interaction, by empowering a basicuncalibrated visual servoing controller with contextual knowledge through thejoint usage of event knowledge graphs (EKGs) and large-scale pretrainedvision-language models (VLMs). The framework is expanded in twofold: first, weinterpret low-level image geometry as high-level concepts, allowing us toprompt VLMs and to select geometric features of points and lines for motorcontrol skills; then, we create an event knowledge graph (EKG) to conceptualizea robot manipulation task of interest, where the main body of the EKG ischaracterized by an executable behavior tree, and the leaves by semanticconcepts relevant to the manipulation context. We demonstrate, in anuncalibrated environment with real robot trials, that our method lowers thereliance of human annotation during task interfacing, allows the robot toperform activities of daily living more easily by treating low-levelgeometric-based motor control skills as high-level concepts, and is beneficialin building cognitive thinking for smart robot applications.

Bridging Low-level Geometry to High-level Concepts in Visual Servoing of  Robot Manipulation Task Using Event Knowledge Graphs and Vision-Language  Models