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

Localization and Mapping is an essential component to enable AutonomousVehicles navigation, and requires an accuracy exceeding that of commercialGPS-based systems. Current odometry and mapping algorithms are able to providethis accurate information. However, the lack of robustness of these algorithmsagainst dynamic obstacles and environmental changes, even for short timeperiods, forces the generation of new maps on every session without takingadvantage of previously obtained ones. In this paper we propose the use of adeep learning architecture to segment movable objects from 3D LiDAR pointclouds in order to obtain longer-lasting 3D maps. This will in turn allow forbetter, faster and more accurate re-localization and trajectoy estimation onsubsequent days. We show the effectiveness of our approach in a very dynamicand cluttered scenario, a supermarket parking lot. For that, we record severalsequences on different days and compare localization errors with and withoutour movable objects segmentation method. Results show that we are able toaccurately re-locate over a filtered map, consistently reducing trajectoryerrors between an average of 35.1% with respect to a non-filtered map versionand of 47.9% with respect to a standalone map created on the current session.

Improving Map Re-localization with Deep 'Movable' Objects Segmentation on 3D LiDAR Point Clouds