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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Inertial-sensor-based attitude estimation is a crucial technology in variousapplications, from human motion tracking to autonomous aerial and groundvehicles. Application scenarios differ in characteristics of the performedmotion, presence of disturbances, and environmental conditions. Sincestate-of-the-art attitude estimators do not generalize well over thesecharacteristics, their parameters must be tuned for the individual motioncharacteristics and circumstances. We propose RIANN, a ready-to-use, neuralnetwork-based, parameter-free, real-time-capable inertial attitude estimator,which generalizes well across different motion dynamics, environments, andsampling rates, without the need for application-specific adaptations. Wegather six publicly available datasets of which we exploit two datasets for themethod development and the training, and we use four datasets for evaluation ofthe trained estimator in three different test scenarios with varying practicalrelevance. Results show that RIANN outperforms state-of-the-art attitudeestimation filters in the sense that it generalizes much better across avariety of motions and conditions in different applications, with differentsensor hardware and different sampling frequencies. This is true even if thefilters are tuned on each individual test dataset, whereas RIANN was trained oncompletely separate data and has never seen any of these test datasets. RIANNcan be applied directly without adaptations or training and is thereforeexpected to enable plug-and-play solutions in numerous applications, especiallywhen accuracy is crucial but no ground-truth data is available for tuning orwhen motion and disturbance characteristics are uncertain. We made RIANNpublicly available.

RIANN -- A Robust Neural Network Outperforms Attitude Estimation Filters