liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Simultaneous Localization And Mapping Using a Kinect In a Sparse Feature Indoor Environment
Linköping University, Department of Electrical Engineering, Automatic Control.
Linköping University, Department of Electrical Engineering, Automatic Control.
2012 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Simultan lokalisering och kartering med hjälp av en Kinect i en inomhusmiljö med få landmärken (Swedish)
Abstract [en]

Localization and mapping are two of the most central tasks when it comes to autonomous robots. It has often been performed using expensive, accurate sensors but the fast development of consumer electronics has made similar sensors available at a more affordable price.

In this master thesis a TurtleBot, robot and a Microsoft Kinect, camera are used to perform Simultaneous Localization And Mapping, SLAM. The thesis presents modifications to an already existing open source SLAM algorithm. The original algorithm, based on visual odometry, is extended so that it can also make use of measurements from wheel odometry and asingle axis gyro. Measurements are fused using an Extended Kalman Filter, EKF, operating in a multirate fashion. Both the SLAM algorithm and the EKF are implemented in C++ using the framework Robot Operating System, ROS.

The implementation is evaluated on two different data sets. One set is recorded in an ordinary office room which constitutes an environment with many landmarks. The other set is recorded in a conference room where one of the walls is flat and white. This gives a partially sparse featured environment.

The result by providing additional sensor information is a more robust algorithm. Periods without credible visual information does not make the algorithm lose its track and the algorithm can thus be used in a larger variety of environments including such where the possibility to extract landmarks is low. The result also shows that the visual odometry can cancel out drift introduced by wheel odometry and gyro sensors.

Place, publisher, year, edition, pages
2012. , 86 p.
Keyword [en]
SLAM, RGBDSLAM, Kinect, TurtleBot, Sparse Feature Environment, Extended Kalman Filter, Robot Operating System
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:liu:diva-81553ISRN: LiTH-ISY-EX--12/4587--SEOAI: oai:DiVA.org:liu-81553DiVA: diva2:553351
Uppsok
Technology
Supervisors
Examiners
Available from: 2012-09-19 Created: 2012-09-18 Last updated: 2012-09-19Bibliographically approved

Open Access in DiVA

fulltext(15225 kB)14612 downloads
File information
File name FULLTEXT01.pdfFile size 15225 kBChecksum SHA-512
089791152742075fa6e58c911f3810f884a344b7e05e543e4ea604823c19480293a34bcef0cdfe01c131477caf65dc1eb6f7cc3d8fe68bd98ddbc2c2daef7bf2
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Hjelmare, FredrikRangsjö, Jonas
By organisation
Automatic Control
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
Total: 14613 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

urn-nbn

Altmetric score

urn-nbn
Total: 662 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf