Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Research Tools and Instruments - Category 1 (<$150,000)

McGill University

$85,025.00

High-throughput multi-domain mapping

EF 2014-15

Résumé
The equipment proposed permits pose estimation and modeling of 3D structures. It includes a 3D terrestrial multi-beam range sensor (LIDAR, as found on the Google self-driving car) that can be used to localize a terrestrial vehicle and/or build 3D models of the environment, and an Ultra Short BaseLine (USBL) underwater positioning system that allows an underwater robot's position to be estimated and this allows the vehicle to build models of its environment. Supporting equipment is included to allow the use of these devices and the exploitation of the data they acquire.These tools will be used to measure 3D structure outdoors (and also indoors) for roboticsand vision research. This includes measurement of 3D point clouds modeling the environment around the sensors, well as localization of the sensors themselves, needed to put measurements into a common coordinate frame. Research based on environmental navigation needs good models for both real-time performance and for ground-truth validation. The fields are moving from the consideration of small data sets or single images to the domain of vast data sets, millions of images, and high-volume multi-sensor data feeds. The research supported by this work will address fundamental algorithms in robotics, machine learning and multi-vehicle interaction, as well as ongoing applications in biology and in the performing arts. The diverse algorithm/systems research is ongoing with HQP funded by the NSERC Canadian Field Robotics Network, the biology applications include past and future collaborations, and the artistic application is the subject of an ongoing FQRNT team grant.
Programme
Research Tools and Instruments - Category 1 (<$150,000)
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
473018-2015
Name nom
Dudek, Gregory
Department département
Computer Science, School of
Organization id
61
Institution établissement
McGill University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2015
Award amount
85025
Program id
EQPEQ
Program name en
Research Tools and Instruments - Category 1 (<$150,000)
Program name fr
Outils et instruments de recherche - catégorie 1 (<150 000$)
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2600
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Robotics
Research subject fr
Robotique
Partie
1
Nb partie
1
Application title
High-throughput multi-domain mapping
Keyword
NSERC
Application summary
The equipment proposed permits pose estimation and modeling of 3D structures. It includes a 3D terrestrial multi-beam range sensor (LIDAR, as found on the Google self-driving car) that can be used to localize a terrestrial vehicle and/or build 3D models of the environment, and an Ultra Short BaseLine (USBL) underwater positioning system that allows an underwater robot's position to be estimated and this allows the vehicle to build models of its environment. Supporting equipment is included to allow the use of these devices and the exploitation of the data they acquire.These tools will be used to measure 3D structure outdoors (and also indoors) for roboticsand vision research. This includes measurement of 3D point clouds modeling the environment around the sensors, well as localization of the sensors themselves, needed to put measurements into a common coordinate frame. Research based on environmental navigation needs good models for both real-time performance and for ground-truth validation. The fields are moving from the consideration of small data sets or single images to the domain of vast data sets, millions of images, and high-volume multi-sensor data feeds. The research supported by this work will address fundamental algorithms in robotics, machine learning and multi-vehicle interaction, as well as ongoing applications in biology and in the performing arts. The diverse algorithm/systems research is ongoing with HQP funded by the NSERC Canadian Field Robotics Network, the biology applications include past and future collaborations, and the artistic application is the subject of an ongoing FQRNT team grant.