Hostname: page-component-7b7567c8c-2jgqx Total loading time: 0 Render date: 2026-11-19T21:15:46.638Z Has data issue: false hasContentIssue false

Landmark detection methods for in-pipe robot traveling in urban gas pipelines

Published online by Cambridge University Press:  09 July 2014

Dong-Hyuk Lee
Affiliation:
School of Mechanical Engineering, Sungkyunkwan University, Suwon 440-746, South Korea
Hyungpil Moon
Affiliation:
School of Mechanical Engineering, Sungkyunkwan University, Suwon 440-746, South Korea
Hyouk Ryeol Choi*
Affiliation:
School of Mechanical Engineering, Sungkyunkwan University, Suwon 440-746, South Korea
*
*Corresponding author. E-mail: hrchoi@me.skku.ac.kr
Rights & Permissions [Opens in a new window]

Summary

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

Elbows and branches in pipelines produce unique image patterns, which can be used as landmarks for autonomous navigation inside the pipelines. This paper presents two landmark detection methods, known as shadow-based method and laser projection method. The first method uses the landmark's unique patterns of shadow produced by the robot's illuminator. The other method exploits special line features generated by its own line-laser beam projector. The basic algorithms for extracting the landmarks are given and special sensor mechanisms are addressed respectively. Finally, the detection performances of each method are validated in various pipeline conditions by using an in-pipe robot, called MRINSPECT-V.

Information

Type
Articles
Copyright
Copyright © Cambridge University Press 2014