Performance improvement of iterative closest point-based outdoor SLAM by rotation invariant descriptors of salient regions

Yong Ju Lee, Jae Bok Song, Ji Hoon Choi

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)

Abstract

To navigate in an unknown environment, a robot should build a model for the environment. For outdoor environments, a three-dimensional (3-D) map is usually used as a main model. This study considers outdoor simultaneous localization and mapping (SLAM) to build a global 3-D map by matching local 3-D maps. An iterative closest point (ICP) algorithm is used to match local 3-D maps and estimate a robot pose, but an alignment error is generated by the ICP algorithm due to the false selection of corresponding points. We propose a new method to extract 3-D points that are valid for ICP matching. Rotation-invariant descriptors are introduced for robust correspondence. 3-D environmental data acquired by tilting a 2-D laser scanner are used to build local 3-D maps. Experimental results in real environments show the increased accuracy of the ICP-based matching and a reduction in matching time.

Original languageEnglish
Pages (from-to)349-360
Number of pages12
JournalJournal of Intelligent and Robotic Systems: Theory and Applications
Volume71
Issue number3-4
DOIs
Publication statusPublished - 2013 Sept

Keywords

  • 3-D maps
  • Iterative closest point (ICP)
  • Mapping
  • Outdoor navigation
  • SLAM

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Mechanical Engineering
  • Industrial and Manufacturing Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Performance improvement of iterative closest point-based outdoor SLAM by rotation invariant descriptors of salient regions'. Together they form a unique fingerprint.

Cite this