Appearance-based loop detection from 3D laser data using the normal distributions transform

Author

Magnusson, Martin ; Andreasson, Henrik ; Nüchter, Andreas ; Lilienthal, Achim J.

Author_Institution

AASS, Orebro Univ., Orebro, Sweden

fYear

2009

fDate

12-17 May 2009

Firstpage

23

Lastpage

28

Abstract

We propose a new approach to appearance based loop detection from metric 3D maps, exploiting the NDT surface representation. Locations are described with feature histograms based on surface orientation and smoothness, and loop closure can be detected by matching feature histograms. We also present a quantitative performance evaluation using two real-world data sets, showing that the proposed method works well in different environments.

Keywords

SLAM (robots); laser ranging; normal distribution; robot vision; 3D laser data; appearance based loop detection; appearance-based loop detection; feature histogram matching; feature histograms; loop closure; metric 3D maps; normal distributions transform; quantitative performance evaluation; surface orientation; surface representation; Clouds; Covariance matrix; Eigenvalues and eigenfunctions; Face detection; Gaussian distribution; Histograms; Relaxation methods; Shape; Simultaneous localization and mapping; Tellurium;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 2009. ICRA '09. IEEE International Conference on

Conference_Location

Kobe

ISSN

1050-4729

Print_ISBN

978-1-4244-2788-8

Electronic_ISBN

1050-4729

Type

conf

DOI

10.1109/ROBOT.2009.5152712

Filename

5152712