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

Localisation with Frequency-Modulated Continuous-Wave (FMCW) radar has gainedincreasing interest due to its inherent resistance to challenging environments.However, complex artefacts of the radar measurement process require appropriateuncertainty estimation to ensure the safe and reliable application of thispromising sensor modality. In this work, we propose a multi-session mapmanagement system which constructs the best maps for further localisation basedon learned variance properties in an embedding space. Using the same varianceproperties, we also propose a new way to introspectively reject localisationqueries that are likely to be incorrect. For this, we apply robust noise-awaremetric learning, which both leverages the short-timescale variability of radardata along a driven path (for data augmentation) and predicts the downstreamuncertainty in metric-space-based place recognition. We prove the effectivenessof our method over extensive cross-validated tests of the Oxford Radar RobotCarand MulRan dataset. In this, we outperform the current state-of-the-art inradar place recognition and other uncertainty-aware methods when using onlysingle nearest-neighbour queries. We also show consistent performance increaseswhen rejecting queries based on uncertainty over a difficult test environment,which we did not observe for a competing uncertainty-aware place recognitionsystem.

Off the Radar: Uncertainty-Aware Radar Place Recognition with Introspective Querying and Map Maintenance