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

Reliable robot pose estimation is a key building block of many robot autonomypipelines, with LiDAR localization being an active research domain. In thiswork, a versatile self-supervised LiDAR odometry estimation method ispresented, in order to enable the efficient utilization of all available LiDARdata while maintaining real-time performance. The proposed approach selectivelyapplies geometric losses during training, being cognizant of the amount ofinformation that can be extracted from scan points. In addition, no labeled orground-truth data is required, hence making the presented approach suitable forpose estimation in applications where accurate ground-truth is difficult toobtain. Furthermore, the presented network architecture is applicable to a widerange of environments and sensor modalities without requiring any network orloss function adjustments. The proposed approach is thoroughly tested for bothindoor and outdoor real-world applications through a variety of experimentsusing legged, tracked and wheeled robots, demonstrating the suitability oflearning-based LiDAR odometry for complex robotic applications.

Self-supervised Learning of LiDAR Odometry for Robotic Applications