Grant: Engage Grants Program
University of Manitoba
$25,000.00
Research and development of ""RobotApps"": a framework for robotic application development through modular components
EF 2011-12
Résumé
Programming robots for real-world applications is difficult even for trained programmers, making it a
challenge to build applications and use robots in education. The goal of this research is to create a new product
line for the company called ""robotApps"", which will consist of a framework for developing sophisticated
robotic applications out of component modules. Part of this development will be a sophisticated multi-robot
application, which will supply many of the modules that will ultimately become a part of this framework. The
first robotApp will be based on the investigation and development of multi-robot team formation in complex
environments using simultaneous localization and mapping (SLAM) where only certain robots are capable of
exploring certain areas (due to size or ability to navigate terrain). We propose an experimental domain where
no teams exist initially, and robots must create teams dynamically. We plan to use robots with heterogeneous
abilities and physiologies. Some robots will be able to navigate difficult terrain and stairs using a track-based
drive system, while others will be small snake-like robots able to navigate small openings. Additionally, some
robots will have the ability to carry smaller robots. Sensors will also be heterogeneous, some robots will use
laser scanners, while others will use sonar or vision. The majority of development will take place in simulation
where the algorithms and control programs will be refined. A final phase will evaluate the algorithms running
on real robots, which will also be used to evaluate the robustness of the simulator itself. Experiments will be
run in complex environments such as multi-floor buildings in disaster scenarios. The simulated environments
will be constructed in such a way as to ensure that teams will have to recruit robots of varying types to ensure
that the team can navigate and map all areas of the environment. Teams will communicate when in close range
(Bluetooth/line of sight). Robots will not be aware of other robots until they encounter them, and similarly
teams will initially not be aware of other teams. Teams will therefore have to send out members if they wish to
find and communicate with others.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Manitoba, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
413478-2011
Name nom
Anderson, John
Department département
Computer Science
Organization id
19
Institution établissement
University of Manitoba
Province en
Manitoba
Province fr
Manitoba
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2011
Award amount
25000
Program id
EGP
Program nane 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
1555
Committee name en
Prairie Internal Decision Committee
Committee name fr
Comité de décision interne pour les Prairies
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
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
Research and development of ""RobotApps"": a framework for robotic application development through modular components
Keyword
NSERC
Application summary
Programming robots for real-world applications is difficult even for trained programmers, making it a
challenge to build applications and use robots in education. The goal of this research is to create a new product
line for the company called ""robotApps"", which will consist of a framework for developing sophisticated
robotic applications out of component modules. Part of this development will be a sophisticated multi-robot
application, which will supply many of the modules that will ultimately become a part of this framework. The
first robotApp will be based on the investigation and development of multi-robot team formation in complex
environments using simultaneous localization and mapping (SLAM) where only certain robots are capable of
exploring certain areas (due to size or ability to navigate terrain). We propose an experimental domain where
no teams exist initially, and robots must create teams dynamically. We plan to use robots with heterogeneous
abilities and physiologies. Some robots will be able to navigate difficult terrain and stairs using a track-based
drive system, while others will be small snake-like robots able to navigate small openings. Additionally, some
robots will have the ability to carry smaller robots. Sensors will also be heterogeneous, some robots will use
laser scanners, while others will use sonar or vision. The majority of development will take place in simulation
where the algorithms and control programs will be refined. A final phase will evaluate the algorithms running
on real robots, which will also be used to evaluate the robustness of the simulator itself. Experiments will be
run in complex environments such as multi-floor buildings in disaster scenarios. The simulated environments
will be constructed in such a way as to ensure that teams will have to recruit robots of varying types to ensure
that the team can navigate and map all areas of the environment. Teams will communicate when in close range
(Bluetooth/line of sight). Robots will not be aware of other robots until they encounter them, and similarly
teams will initially not be aware of other teams. Teams will therefore have to send out members if they wish to
find and communicate with others.