High-Definition-Map-Based LiDAR Localization Through Dynamic Time-Synchronized Normal Distribution Transform Scan Matching

Kai Wei Chiang, Surachet Srinara, Syun Tsai, Cheng Xian Lin, Meng Lun Tsai

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

In practice, the accuracy of high-definition-map-based LiDAR localization in normal distribution transform (NDT) scan matching depends on the presence of sufficient appearance information regarding the environment. This paper proposes new strategies for better handling the initialization cope with the initialization and evaluation of LiDAR localization. The first strategy involves establishing a reliable system based on the initial pose and ground truth. This study proposes the integration of an inertial navigation system and a global navigation satellite system. In the second proposed strategy, the point clouds in each partitioned scan area are processed according to the density ratio. The density ratio plays a crucial role in the analysis of NDT pose estimates, which enables a localization system to appropriately determine the uncertainty of the NDT. Preliminary results indicate that the proposed strategies not only can continually provide stable initial poses but also can be used for the reliable evaluation of NDT algorithms. Moreover, geometric information considerably influences the sensitivity on localization accuracy under the presence of sufficient appearance information regarding the environment in NDT pose estimation.

Original languageEnglish
Pages (from-to)7011-7023
Number of pages13
JournalIEEE Transactions on Vehicular Technology
Volume72
Issue number6
DOIs
Publication statusPublished - 2023 Jun 1

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Automotive Engineering

Fingerprint

Dive into the research topics of 'High-Definition-Map-Based LiDAR Localization Through Dynamic Time-Synchronized Normal Distribution Transform Scan Matching'. Together they form a unique fingerprint.

Cite this