Recognition of inside pipeline geometry by using PSD sensors for autonomous navigation
Yun Seok Choi, Ho Moon Kim, Jung Seok Suh, Hyeong Min Mun, Seung Ung Yang, Chan Min Park, Hyouk Ryeol Choi
- Year
- 2014
- Citations
- 14
Abstract
To deploy an untethered robot inside pipelines without any external assistance, it is prerequisite to recognize the pipeline elements such as straight pipeline, elbow, T-branch, and miter. This paper presents a method of recognizing pipeline elements using PSD(Position Sensitive Device) sensors. It is easy to implement, but help us collect accurate information necessary for navigating inside pipelines without heavy computation. The method is composed of three parts, which is the method for distinguishing T-branch and miter, searching the direction in T-branch and elbow, and determining the types of pipeline element, respectively. The design for the PSD sensor suite is presented and the algorithm for recognition procedures are addressed. The sensor suite is implemented in an in-pipe robot, called MRINSPECT VI, and its performances are validated.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Fractional Differential Equations
Igor Podlubný
2025
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991