Grant: Engage Grants Program
McGill University
$24,314.00
Tracking pose in six degrees of freedom - application to welding simulation
FY 2012-13
Summary
123 Certification is a Montreal company specializing in the development of advanced simulator technology for
the training and certification of welders. Their approach uses augmented virtual reality to place a human
welder within a simulated environment, translating the motion of a hand-held facsimile of a welding torch into
inputs to the simulator program. Visual and aural feedback in response to the actions of the welder provide an
experience that sufficiently matches reality to the point that it can supplant use of physical equipment to a large
degree in training and certification. Key to simulator fidelity is the precision to which the pose of the appliance
(welding torch facsimile) manipulated by the operator can be determined. 123 Certification has recently
demonstrated the viability of using a low-cost, 6 degree-of-freedom magnetic motion sensor (Sixense Inc.) for
this purpose. However, due to their susceptibility to ambient noise and magnetic interference, these kinds of
sensors make it difficult to perform the fine discrimination necessary (e.g., detecting hand tremors) for high
dexterity simulations.
The Artificial Perception Laboratory (APL) at the McGill Centre for Intelligent Machines has been working on
the problem of sensing for robotics for over 20 years, and has developed considerable expertise in exactly these
kinds of problems. In the current context, APL's laboratory facilities will be used to measure sensor response
characteristics from which models and algorithms can be derived to improve sensor performance. APL will
work directly with 123 Certification in the development of tracking algorithms that leverage the time series
nature of the data and expectations about sensor trajectory to yield improved estimates of dynamic sensor pose.
The goal of this initial collaboration is to determine the limits of the candidate sensor technologies and assess
the extent to which state of the art tracking techniques can recover accurate pose within given computational
limits. Success here will provide 123 Certification with a significant advantage over its competitors.
Program
Engage Grants Program
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
445169-2012
Name nom
Ferrie, Frank
Department département
Electrical and Computer Engineering
Organization id
61
Institution établissement
McGill University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2012
Award amount
24314
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
1552
Committee name en
Quebec Internal Decision Committee
Committee name fr
Comité de décision interne pour le Québec
Area of application code
500
Area of application group en
Manufacturing processes and products
Area of application group fr
Procédés et produits industriels
Area of application en
Manufacturing processes and products
Area of application fr
Procédés et produits industriels
Research subject code
2603
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Computer vision
Research subject fr
Vision artificielle
Partie
1
Nb partie
1
Application title
Tracking pose in six degrees of freedom - application to welding simulation
Keyword
NSERC
Application summary
123 Certification is a Montreal company specializing in the development of advanced simulator technology for
the training and certification of welders. Their approach uses augmented virtual reality to place a human
welder within a simulated environment, translating the motion of a hand-held facsimile of a welding torch into
inputs to the simulator program. Visual and aural feedback in response to the actions of the welder provide an
experience that sufficiently matches reality to the point that it can supplant use of physical equipment to a large
degree in training and certification. Key to simulator fidelity is the precision to which the pose of the appliance
(welding torch facsimile) manipulated by the operator can be determined. 123 Certification has recently
demonstrated the viability of using a low-cost, 6 degree-of-freedom magnetic motion sensor (Sixense Inc.) for
this purpose. However, due to their susceptibility to ambient noise and magnetic interference, these kinds of
sensors make it difficult to perform the fine discrimination necessary (e.g., detecting hand tremors) for high
dexterity simulations.
The Artificial Perception Laboratory (APL) at the McGill Centre for Intelligent Machines has been working on
the problem of sensing for robotics for over 20 years, and has developed considerable expertise in exactly these
kinds of problems. In the current context, APL's laboratory facilities will be used to measure sensor response
characteristics from which models and algorithms can be derived to improve sensor performance. APL will
work directly with 123 Certification in the development of tracking algorithms that leverage the time series
nature of the data and expectations about sensor trajectory to yield improved estimates of dynamic sensor pose.
The goal of this initial collaboration is to determine the limits of the candidate sensor technologies and assess
the extent to which state of the art tracking techniques can recover accurate pose within given computational
limits. Success here will provide 123 Certification with a significant advantage over its competitors.