Development of Visual Simultaneous Localization and Mapping (VSLAM) for a Pipe Inspection Robot

Krys, Dennis; Najjaran, Homayoun

doi:10.1109/cira.2007.382850

Cited by 31 publications

(20 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simultaneous localisation and mapping (SLAM) techniques [6] have been applied to robots in water pipes, using cameras and inertial measurement units (IMUs) [7], [8]. However, the use of cameras is limited by the lack of visual features, and IMUs are subject to drift, meaning that there is still much scope for improvement.…”

Section: Introductionmentioning

confidence: 99%

Robot mapping and localisation in metal water pipes using hydrophone induced vibration and map alignment by dynamic time warping

Schirru

Zahraee

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

ReuseUnless indicated otherwise, fulltext items are protected by copyright with all rights reserved. The copyright exception in section 29 of the Copyright, Designs and Patents Act 1988 allows the making of a single copy solely for the purpose of non-commercial research or private study within the limits of fair dealing. The publisher or other rights-holder may allow further reproduction and re-use of this version -refer to the White Rose Research Online record for this item. Where records identify the publisher as the copyright holder, users can verify any specific terms of use on the publisher's website. TakedownIf you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing eprints@whiterose.ac.uk including the URL of the record and the reason for the withdrawal request.Robot mapping and localisation in metal water pipes using hydrophone induced vibration and map alignment by dynamic time warping* Abstract-Water is a highly valuable resource so asset management of associated infrastructure is of critical importance. Water distribution pipe networks are usually buried, and so are difficult to access. Robots are therefore appealing for performing inspection and detecting damage to target repairs. However, robot mapping and localisation of buried water pipes has not been widely investigated to date, and is challenging because pipes tend to be relatively featureless. In this paper we propose a mapping and localisation algorithm for metal water pipes with two key novelties: the development of a new type of map based on hydrophone induced vibration signals of metal pipes, and a mapping algorithm based on spatial warping and averaging of dead reckoning signals used to calibrate the map (using dynamic time warping). Localisation is performed using both terrain-based extended Kalman filtering and also particle filtering. We successfully demonstrate and evaluate the approach on a combination of experimental and simulation data, showing improved localisation compared to dead reckoning.

show abstract

Section: Introductionmentioning

confidence: 99%

Robot mapping and localisation in metal water pipes using hydrophone induced vibration and map alignment by dynamic time warping

Schirru

Zahraee

et al. 2017

2017 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…Mapping and localisation has been developed for water pipes using SLAM techniques with cameras and inertial measurement units (IMUs) [5], [6]. A limitation of these methods is that there are few visual features available in the pipe.…”

Section: Introductionmentioning

confidence: 99%

PipeSLAM: Simultaneous localisation and mapping in feature sparse water pipes using the Rao-Blackwellised particle filter

Schirru

Zahraee

et al. 2017

2017 IEEE International Conference on Advanced Intelligent Mechatronics (AIM)

View full text Add to dashboard Cite

Abstract-Water, a valuable resource, is usually distributed through urban environments by buried pipes. These pipes are difficult to access for inspection, maintenance and repair. This makes in-pipe robots an appealing technology for inspecting water pipes and localising damage prior to repair from above ground. Accurate localisation of damage is of critical importance because of the costs associated with excavating roads, disrupting traffic and disrupting the water supply. The problem is that pipes tend to be relatively featureless making robot localisation a challenging problem. In this paper we propose a novel simultaneous localisation and mapping (SLAM) algorithm for metal water pipes. The approach we take is to excite pipe vibration with a hydrophone (sound induced vibration), which leads to a map of pipe vibration amplitude over space. We then develop a SLAM algorithm that makes use of this new type of map, where the estimation method is based on the RaoBlackwellised particle filter (RBPF), termed PipeSLAM. The approach is also suited to SLAM in plastic water pipes using a similar type of map derived from ultrasonic sensing. We successfully demonstrate the feasibility of the approach using a combination of experimental and simulation data.

show abstract

“…Since the length and angle of the track can vary, the program will determine the track length and calibrate the simulator automatically before every simulation. Details of the structure and design of the simulator can be found in [5]. Simultaneously, the motion control software records the position data measured by the embedded position sensors of the servomotors as well as the localization and visualization sensors.…”

Section: Simulation Apparatusmentioning

confidence: 99%

INS assisted vision-based localization in unstructured environments

Krys

Najjaran

2008

2008 IEEE International Conference on Systems, Man and Cybernetics

Self Cite

View full text Add to dashboard Cite

This paper presents a sensor fusio incorporates a monocular vision system, laser ra inertial navigation sensor (INS) for localization and manipulators. The proposed method is part applications in which there is a featured wall or to the robots. Examples include unmanned (UGV), unmanned aerial vehicles (UAV), and robots. In essence, the proposed method fuses and dead reckoning where the sequential im camera are stitched together with the help navigation system (INS). In the proposed mod load of image mosaicing is reduced significantly time accumulation of error of the INS is localization method was developed as a standa tested using a hardware-in-the-loop simulator paper. This module will eventually be used navigation of a pipe inspection robot capa nondestructive testing (NDT) sensors and instruments into large water mains.

show abstract

Development of Visual Simultaneous Localization and Mapping (VSLAM) for a Pipe Inspection Robot

Cited by 31 publications

References 8 publications

Robot mapping and localisation in metal water pipes using hydrophone induced vibration and map alignment by dynamic time warping

Robot mapping and localisation in metal water pipes using hydrophone induced vibration and map alignment by dynamic time warping

PipeSLAM: Simultaneous localisation and mapping in feature sparse water pipes using the Rao-Blackwellised particle filter

INS assisted vision-based localization in unstructured environments

Contact Info

Product

Resources

About