Grant: Engage Grants Program
University of British Columbia
$24,380.00
Automatic monocular localization of pipe inspection robots inside water and sewer pipes
EF 2010-11
Résumé
Inuktun Services Ltd. is a Canadian manufacturer of leading-edge inspection robots and remotely controlled
articulated camera systems used for visual inspection and nondestructive testing of water mains and sewer
pipes in the world. Inuktun robots are typically teleoperated that is an operator uses a live video feedback from
the robot to manipulate the robot inside the pipe. Thus, robot autonomy has never been a concern for the
company, and as a result investment in additional software and hardware required for robot localization was
not justifiable for this particular robotic application. To advance the capability of the robot and to maintain its
leading position in the industry, Inuktun has become interested in automatic robot localization first to report the
location of the pipe defects detected during inspection with a greater accuracy and second to generate a map of
buried pipes with respect to the outside world, which is typically unavailable for these municipal assets. In this
project and in full collaboration with Inuktun Services Ltd., the applicant aims at developing an appropriate
localization system for the inspection robots manufactured by Inuktun. The proposed solution is the use of the
mono-vSLAM system recently developed at the research laboratory of the applicant. The mono-vSLAM system
relies on the sequential images of a single camera and hence no additional hardware will be required for the
Inuktun robots. However, the remaining technical challenges of this project include: i) to adapt the
mono-vSLAM system for real-time operation on the embedded controller of the robot, and ii) to modify the
method to take into account variable optical properties (e.g., autofocus, zoom and radial distortion) of the
onboard camera system that unlike laboratory setups is a critical constraint in practical applications. By the
implementation of the proposed mono-vSLAM system, the Inuktun robots will be able to locate themselves and
simultaneously create a map of buried pipes.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
402855-2010
Name nom
Najjaran, Homayoun
Department département
Okanagan - Engineering, School of
Organization id
2
Institution établissement
University of British Columbia
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2010
Competition year année de concours
2010
Award amount
24380
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1554
Committee name en
Pacific Internal Decision Committee
Committee name fr
Comité de décision interne pour le Pacifique
Area of application code
515
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Instrumentation technology
Area of application fr
Technologie de l'instrumentation
Research subject code
2109
Research subject group en
Mechanical engineering
Research subject group fr
Génie mécanique
Research subject en
Mechanical systems and instrumentation
Research subject fr
Instrumentation et systèmes mécaniques
Partie
1
Nb partie
1
Application title
Automatic monocular localization of pipe inspection robots inside water and sewer pipes
Keyword
NSERC
Application summary
Inuktun Services Ltd. is a Canadian manufacturer of leading-edge inspection robots and remotely controlled
articulated camera systems used for visual inspection and nondestructive testing of water mains and sewer
pipes in the world. Inuktun robots are typically teleoperated that is an operator uses a live video feedback from
the robot to manipulate the robot inside the pipe. Thus, robot autonomy has never been a concern for the
company, and as a result investment in additional software and hardware required for robot localization was
not justifiable for this particular robotic application. To advance the capability of the robot and to maintain its
leading position in the industry, Inuktun has become interested in automatic robot localization first to report the
location of the pipe defects detected during inspection with a greater accuracy and second to generate a map of
buried pipes with respect to the outside world, which is typically unavailable for these municipal assets. In this
project and in full collaboration with Inuktun Services Ltd., the applicant aims at developing an appropriate
localization system for the inspection robots manufactured by Inuktun. The proposed solution is the use of the
mono-vSLAM system recently developed at the research laboratory of the applicant. The mono-vSLAM system
relies on the sequential images of a single camera and hence no additional hardware will be required for the
Inuktun robots. However, the remaining technical challenges of this project include: i) to adapt the
mono-vSLAM system for real-time operation on the embedded controller of the robot, and ii) to modify the
method to take into account variable optical properties (e.g., autofocus, zoom and radial distortion) of the
onboard camera system that unlike laboratory setups is a critical constraint in practical applications. By the
implementation of the proposed mono-vSLAM system, the Inuktun robots will be able to locate themselves and
simultaneously create a map of buried pipes.