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

Global localisation from visual data is a challenging problem applicable tomany robotics domains. Prior works have shown that neural networks can betrained to map images of an environment to absolute camera pose within thatenvironment, learning an implicit neural mapping in the process. In this workwe evaluate the applicability of such an approach to real-world roboticsscenarios, demonstrating that by constraining the problem to 2-dimensions andsignificantly increasing the quantity of training data, a compact model capableof real-time inference on embedded platforms can be used to achievelocalisation accuracy of several centimetres. We deploy our trained modelonboard a UGV platform, demonstrating its effectiveness in a waypointnavigation task, wherein it is able to localise with a mean accuracy of 9cm ata rate of 6fps running on the UGV onboard CPU, 35fps on an embedded GPU, or220fps on a desktop GPU. Along with this work we will release a novellocalisation dataset comprising simulated and real environments, each withtraining samples numbering in the tens of thousands.

On the Application of Efficient Neural Mapping to Real-Time Indoor Localisation for Unmanned Ground Vehicles