liu.seSearch for publications in DiVA
ReferencesLink to record
Permanent link

Direct link
Toward rich geometric map for SLAM: Online Detection of Planes in 2D LIDAR
2012 (English)In: Proceedings of the International Workshop on Perception for Mobile Robots Autonomy (PEMRA), 2012Conference paper (Refereed)
Abstract [en]

Rich geometric models of the environment are needed for robots to accomplish their missions. However a robot operatingin a large environment would require a compact representation.

In this article, we present a method that relies on the idea that a plane appears as a line segment in a 2D scan, andthat by tracking those lines frame after frame, it is possible to estimate the parameters of that plane. The method istherefore divided in three steps: fitting line segments on the points of the 2D scan, tracking those line segments inconsecutive scan and estimating the parameters with a graph based SLAM (Simultaneous Localisation And Mapping)algorithm.

Keyword [en]
laser scanner, SLAM, LIDAR
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:liu:diva-84465 (URN)oai:DiVA.org:liu-84465 (OAI)diva2:559417 (DiVA)
Conference
International Workshop on Perception for Mobile Robots Autonomy (PEMRA)
Available from2012-10-15 Created:2012-10-09 Last updated:2013-01-09Bibliographically approved

Open Access in DiVA

fulltext(2909 kB)165 downloads
File information
File name FULLTEXT01.pdfFile size 2909 kBChecksum SHA-512
d5dd5ed3d07cf8fe219ff8d07cc0e8cf8c4cc7af7b56869107a6c3b2bf5e103e8fa4baf32984699a52afefe66de16f132c0da384f16d5ff153b9c5ffd4fcd621
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Berger, Cyrille
By organisation
KPLAB - Knowledge Processing LabThe Institute of Technology
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 165 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available
Total: 76 hits
ReferencesLink to record
Permanent link

Direct link