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

Using multiple robots for exploring and mapping environments can provideimproved robustness and performance, but it can be difficult to implement. Inparticular, limited communication bandwidth is a considerable constraint when arobot needs to determine if it has visited a location that was previouslyexplored by another robot, as it requires for robots to share descriptions ofplaces they have visited. One way to compress this description is to useconstellations, groups of 3D points that correspond to the estimate of a set ofrelative object positions. Constellations maintain the same pattern fromdifferent viewpoints and can be robust to illumination changes or dynamicelements. We present a method to extract from these constellations compactspatial and semantic descriptors of the objects in a scene. We use thisrepresentation in a 2-step decentralized loop closure verification: first, wedistribute the compact semantic descriptors to determine which other robotsmight have seen scenes with similar objects; then we query matching robots withthe full constellation to validate the match using geometric information. Theproposed method requires less memory, is more interpretable than global imagedescriptors, and could be useful for other tasks and interactions with theenvironment. We validate our system's performance on a TUM RGB-D SLAM sequenceand show its benefits in terms of bandwidth requirements.

CAPRICORN: Communication Aware Place Recognition using Interpretable Constellations of Objects in Robot Networks