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

Indoor localization systems often fuse inertial odometry with map informationvia hand-defined methods to reduce odometry drift, but such methods aresensitive to noise and struggle to generalize across odometry sources. Toaddress the robustness problem in map utilization, we propose a data-drivenprior on possible user locations in a map by combining learned spatial mapembeddings and temporal odometry embeddings. Our prior learns to encode whichmap regions are feasible locations for a user more accurately than previoushand-defined methods. This prior leads to a 49% improvement in inertial-onlylocalization accuracy when used in a particle filter. This result issignificant, as it shows that our relative positioning method can match theperformance of absolute positioning using bluetooth beacons. To show thegeneralizability of our method, we also show similar improvements using wheelencoder odometry.

Learnable Spatio-Temporal Map Embeddings for Deep Inertial Localization