Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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
Cloud-based Mobile Robot Localization
KTH, School of Computer Science and Communication (CSC).
2014 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Molnbaserad mobil robotlokalisering (Swedish)
Abstract [sv]

Molnbaserad mobil robotlokalisering Cloud robotics Är en modern inställning till robotik baserad på datormoln, lagringsmoln och andra internettjänster som robotar kan använda för att överkomma fundamentala begränsningar i inbygd beräkning och lagringsskalbarhet. Det här nya delområdet inom robotik drivs av den snabba utvecklingen av trådlös kommunikation och lättillgänglig molnbaserad infrastruktur som tillhandahålls av stora företag som till exempel Google, Amazon och Microsoft. Målet med det här projektet är att designa och implementera en molnbaserad prototyp för mobil robotlokalisering inomhus med RGB-D kameror. Lokalisering är ett fundamentalt problem inom robotik och har undersökts i den här rapporten. Rapporten behandlar även särdragsextraktion av 3D-bilder för robotlokalisering. Som ett resultat av det här projektet presenteras ett nytt system av molnbaserad robotlokalisering. Systemet använder öppen programvara som ROS och GraphLab. Slutligen, experiment redovisar fördelar och nackdelar med vårt tillvägagångssätt.

Abstract [en]

Cloud robotics is a modern approach to robotics based on cloud computing, cloud storage and other Internet services that robots can benefit from to overcome fundamental limitations in on-board computation and memory scalability. This new subfield of robotics is driven by the rapid progress of wireless communications and easy-toaccess cloud infrastructure provided by large industries such as Google, Amazon, and Microsoft. The goal of this project consists of the design and implementation of a prototype for indoor mobile robot localization with RGB-D cameras leveraging the cloud. Localization is a fundamental problem in autonomous robotics surveyed in this report. In addition, extraction of features for localization from depth images is also addressed. As a result of this project, a new system for cloud-based robot localization is presented. The system makes use of modern opensource software such as ROS and GraphLab. Finally, experiments are presented to analyse the improvements and limitations achieved by our approach.

Place, publisher, year, edition, pages
2014.
National Category
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-153649OAI: oai:DiVA.org:kth-153649DiVA: diva2:753043
Examiners
Available from: 2014-11-24 Created: 2014-10-06 Last updated: 2014-11-24Bibliographically approved

Open Access in DiVA

fulltext(1759 kB)570 downloads
File information
File name FULLTEXT01.pdfFile size 1759 kBChecksum SHA-512
b14e8f0e9c83a4d619c2fc6caac20032ec605258b1273923429837ad70ce20ed7ead4099b215f29868de3ba05d11c2431387b39e3b915a556b4610a58ac6709c
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 570 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: 276 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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