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

Inertial sensors play a pivotal role in indoor localization, which in turnlays the foundation for pervasive personal applications. However, low-costinertial sensors, as commonly found in smartphones, are plagued by bias andnoise, which leads to unbounded growth in error when accelerations are doubleintegrated to obtain displacement. Small errors in state estimation propagateto make odometry virtually unusable in a matter of seconds. We propose to breakthe cycle of continuous integration, and instead segment inertial data intoindependent windows. The challenge becomes estimating the latent states of eachwindow, such as velocity and orientation, as these are not directly observablefrom sensor data. We demonstrate how to formulate this as an optimizationproblem, and show how deep recurrent neural networks can yield highly accuratetrajectories, outperforming state-of-the-art shallow techniques, on a widerange of tests and attachments. In particular, we demonstrate that IONet cangeneralize to estimate odometry for non-periodic motion, such as a shoppingtrolley or baby-stroller, an extremely challenging task for existingtechniques.

IONet: Learning to Cure the Curse of Drift in Inertial Odometry