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 on 3D data is a challenging task for unmanned vehicles,especially in long-term dynamic urban scenarios. Due to the generality andlong-term stability, the pole-like objects are very suitable as landmarks forunmanned vehicle localization in time-varing scenarios. In this paper, along-term LiDAR-only localization algorithm based on semantic cluster map isproposed. At first, the Convolutional Neural Network(CNN) is used to infer thesemantics of LiDAR point clouds. Combined with the point cloud segmentation,the long-term static objects pole/trunk in the scene are extracted andregistered into a semantic cluster map. When the unmanned vehicle re-enters theenvironment again, the relocalization is completed by matching the clusters ofthe local map with the clusters of the global map. Furthermore, the continuousmatching between the local and global maps stably outputs the global pose at2Hz to correct the drift of the 3D LiDAR odometry. The proposed approachrealizes localization in the long-term scenarios without maintaining thehigh-precision point cloud map. The experimental results on our campus datasetdemonstrate that the proposed approach performs better in localization accuracycompared with the current state-of-the-art methods. The source of this paper isavailable at: http://www.github.com/HITSZ-NRSL/long-term-localization.

Pole-like Objects Mapping and Long-Term Robot Localization in Dynamic Urban Scenarios