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

Robust and accurate trajectory estimation of mobile agents such as people androbots is a key requirement for providing spatial awareness for emergingcapabilities such as augmented reality or autonomous interaction. Althoughcurrently dominated by optical techniques e.g., visual-inertial odometry, thesesuffer from challenges with scene illumination or featureless surfaces. As analternative, we propose milliEgo, a novel deep-learning approach to robustegomotion estimation which exploits the capabilities of low-cost mmWave radar.Although mmWave radar has a fundamental advantage over monocular cameras ofbeing metric i.e., providing absolute scale or depth, current single chipsolutions have limited and sparse imaging resolution, making existingpoint-cloud registration techniques brittle. We propose a new architecture thatis optimized for solving this challenging pose transformation problem.Secondly, to robustly fuse mmWave pose estimates with additional sensors, e.g.inertial or visual sensors we introduce a mixed attention approach to deepfusion. Through extensive experiments, we demonstrate our proposed system isable to achieve 1.3% 3D error drift and generalizes well to unseenenvironments. We also show that the neural architecture can be made highlyefficient and suitable for real-time embedded applications.

milliEgo: Single-chip mmWave Radar Aided Egomotion Estimation via Deep Sensor Fusion