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

Versatile and adaptive semantic understanding would enable autonomous systemsto comprehend and interact with their surroundings. Existing fixed-class modelslimit the adaptability of indoor mobile and assistive autonomous systems. Inthis work, we introduce LEXIS, a real-time indoor Simultaneous Localization andMapping (SLAM) system that harnesses the open-vocabulary nature of LargeLanguage Models (LLMs) to create a unified approach to scene understanding andplace recognition. The approach first builds a topological SLAM graph of theenvironment (using visual-inertial odometry) and embeds ContrastiveLanguage-Image Pretraining (CLIP) features in the graph nodes. We use thisrepresentation for flexible room classification and segmentation, serving as abasis for room-centric place recognition. This allows loop closure searches tobe directed towards semantically relevant places. Our proposed system isevaluated using both public, simulated data and real-world data, coveringoffice and home environments. It successfully categorizes rooms with varyinglayouts and dimensions and outperforms the state-of-the-art (SOTA). For placerecognition and trajectory estimation tasks we achieve equivalent performanceto the SOTA, all also utilizing the same pre-trained model. Lastly, wedemonstrate the system's potential for planning.

Language-EXtended Indoor SLAM (LEXIS): A Versatile System for Real-time Visual Scene Understanding