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

Loop closing and relocalization are crucial techniques to establish reliableand robust long-term SLAM by addressing pose estimation drift and degeneration.This article begins by formulating loop closing and relocalization within aunified framework. Then, we propose a novel multi-head network LCR-Net totackle both tasks effectively. It exploits novel feature extraction andpose-aware attention mechanism to precisely estimate similarities and 6-DoFposes between pairs of LiDAR scans. In the end, we integrate our LCR-Net into aSLAM system and achieve robust and accurate online LiDAR SLAM in outdoordriving environments. We thoroughly evaluate our LCR-Net through three setupsderived from loop closing and relocalization, including candidate retrieval,closed-loop point cloud registration, and continuous relocalization usingmultiple datasets. The results demonstrate that LCR-Net excels in all threetasks, surpassing the state-of-the-art methods and exhibiting a remarkablegeneralization ability. Notably, our LCR-Net outperforms baseline methodswithout using a time-consuming robust pose estimator, rendering it suitable foronline SLAM applications. To our best knowledge, the integration of LCR-Netyields the first LiDAR SLAM with the capability of deep loop closing andrelocalization. The implementation of our methods will be made open-source.

Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM