oru.sePublications
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
Reactive navigation of an autonomous vehicle in underground mines:  
Örebro University, Department of Technology. (Mobile Robots Lab)
2007 (English)Licentiate thesis, monograph (Other academic)
Abstract [en]

In most underground mines, LHD (Load-Haul-Dump) vehicles are used to transportore from the stope or muck-pile to a dumping point, and are typically operated by a human who is sitting on-board the vehicle. Generally, an underground mine does not offer the best working environment for humans, and the job of an LHD operator can be characterised as Three D: Dangerous, Dirty and Dull. Tele-operated LHD vehicles are sometimes used in an attempt to remove the need of an on-board operator. However, tele-operation typically leads to reduced productivity and increased maintenance costs. The current trend is therefore toward fully autonomous, driver-less navigation systems.

In this thesis, we present our approach to develop a reactive navigation system for operating an autonomous LHD vehicle in underground mines. The suggested system uses a coarse topological map for localisation, and a fuzzy behaviour-based approach for navigation. In our work, we have extended an existing framework for autonomous robot navigation and we have designed, developed and validated novel feature detection algorithms to enable reliable tunnel following and topological localisation. These algorithms operate on data from a laser scanner, and extract features such as tunnel center line and intersections. We claim, that the developed algorithms go beyond the state of the art because of their reduced computational cost and of their robustness with respect to sensor noise. To further increase the robustness of the topological localisation, we also propose the use of RFID technology by deploying passive RFID-tags at critical locations in the mine. To complement the description of our algorithms and system, we report on an initial implementation tested on ordinary research robots, and an extensive quantitative evaluation of the feature detection algorithms. This evaluation confirms the good performance of the algorithms, and their robustness to noise in the laser data. We also describe a few qualitative tests of the complete navigation system made in indoor environments using ordinary research robots. These tests indicate that the techniques developed in this thesis, originally intended for use in an underground mine, can also be used in other domains characterized by corridor-like features.

Place, publisher, year, edition, pages
Örebro: Örebro universitet , 2007. , p. 130
Series
Studies from the Department of Technology at Örebro University, ISSN 1404-7225 ; 22
Keyword [en]
Mobile Robots
National Category
Computer Sciences Engineering and Technology Computer and Information Sciences
Research subject
Computer and Systems Science
Identifiers
URN: urn:nbn:se:oru:diva-4181OAI: oai:DiVA.org:oru-4181DiVA, id: diva2:138480
Presentation
(English)
Available from: 2007-07-05 Created: 2007-07-05 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

Authority records BETA

Larsson, Johan

Search in DiVA

By author/editor
Larsson, Johan
By organisation
Department of Technology
Computer SciencesEngineering and TechnologyComputer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 200 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