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

Robust and lane-level positioning is essential for autonomous vehicles. As anirreplaceable sensor, LiDAR can provide continuous and high-frequency poseestimation by means of mapping, on condition that enough environment featuresare available. The error of mapping can accumulate over time. Therefore, LiDARis usually integrated with other sensors. In diverse urban scenarios, theenvironment feature availability relies heavily on the traffic (moving andstatic objects) and the degree of urbanization. Common LiDAR-based SLAMdemonstrations tend to be studied in light traffic and less urbanized area.However, its performance can be severely challenged in deep urbanized cities,such as Hong Kong, Tokyo, and New York with dense traffic and tall buildings.This paper proposes to analyze the performance of standalone NDT-based graphSLAM and its reliability estimation in diverse urban scenarios to furtherevaluate the relationship between the performance of LiDAR-based SLAM andscenario conditions. The normal distribution transform (NDT) is employed tocalculate the transformation between frames of point clouds. Then, the LiDARodometry is performed based on the calculated continuous transformation. Thestate-of-the-art graph-based optimization is used to integrate the LiDARodometry measurements to implement optimization. The 3D building models aregenerated and the definition of the degree of urbanization based on Skyplot isproposed. Experiments are implemented in different scenarios with differentdegrees of urbanization and traffic conditions. The results show that theperformance of the LiDAR-based SLAM using NDT is strongly related to thetraffic condition and degree of urbanization.

Performance Analysis of NDT-based Graph SLAM for Autonomous Vehicle in Diverse Typical Driving Scenarios of Hong Kong