Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

Université de Sherbrooke

$50,000.00

Computational architecture for intelligence of social and autonomous mobile robots

EF 2007-08

Résumé
Now that mobile robots are used in teleoperation mode (exploring Mars) and with the continuous technological improvements in computing and mechatronics, it is necessary to put more emphasis in making them truly autonomous robots, working to assist humans and improve quality of life. An autonomous robot must deal with the unpredictability of real life settings, manifesting its own type of "intelligence" affected by its limitations in sensing, acting, processing and in making decisions, just like us. Just considering a few of its decision-making elements, obstacle avoidance, navigation, localization, mapping, planning, modeling, recognizing, tracking interaction and cooperation are good examples of algorithms that need to be integrated for the design of socially autonomous mobile robots. The solution studied in this proposal is a computational architecture based on the notion of motivated selection of behavior-producing modules. The general idea is to have different motivational sources, influenced by percepts, preset guidelines and acquired knowledge, share information about how to activate and use behavior-producing modules, i.e., the skills the robot has to operate in the real world. Distributing motivational sources allows exploiting more efficiently the various influences regarding the robot's intentions, while not having to depend on any one of them for the robot to work for robustness and adaptability purposes. Conflict management strategies amongst these motivational sources will be studied, as for self-regulation of commitments (self and to other robots or humans) and learning in such conditions. A group of unique autonomous robots with state-of-the art capabilities will be assigned to carry on duties (delivery, patrol, search) on an office floor, with no a priori knowledge about the environment. Performance will be characterized by the complexity of the working scenario, the effectiveness of the team in achieving its tasks based on its capabilities, and the level of human interventions required. Five Ph.D. and one Master's students, one postdoctoral researcher, one trainee as for teams of undergraduate students will be directly trained through this initiative.
Programme
Discovery Grants Program - Individual
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
203577-2006
Name nom
Michaud, François
Department département
Génie électrique et génie informatique
Organization id
68
Institution établissement
Université de Sherbrooke
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2007
Competition year année de concours
2006
Award amount
50000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
335
Committee name en
Electromag. & Electr. Systems (H)
Committee name fr
Électromagn. et syst. électr. (H)
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
2606
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Systems, man and cybernetics
Research subject fr
Systèmes, homme et cybernétique
Partie
2
Nb partie
5
Application title
Computational architecture for intelligence of social and autonomous mobile robots
Keyword
NA
Application summary
Now that mobile robots are used in teleoperation mode (exploring Mars) and with the continuous technological improvements in computing and mechatronics, it is necessary to put more emphasis in making them truly autonomous robots, working to assist humans and improve quality of life. An autonomous robot must deal with the unpredictability of real life settings, manifesting its own type of "intelligence" affected by its limitations in sensing, acting, processing and in making decisions, just like us. Just considering a few of its decision-making elements, obstacle avoidance, navigation, localization, mapping, planning, modeling, recognizing, tracking interaction and cooperation are good examples of algorithms that need to be integrated for the design of socially autonomous mobile robots. The solution studied in this proposal is a computational architecture based on the notion of motivated selection of behavior-producing modules. The general idea is to have different motivational sources, influenced by percepts, preset guidelines and acquired knowledge, share information about how to activate and use behavior-producing modules, i.e., the skills the robot has to operate in the real world. Distributing motivational sources allows exploiting more efficiently the various influences regarding the robot's intentions, while not having to depend on any one of them for the robot to work for robustness and adaptability purposes. Conflict management strategies amongst these motivational sources will be studied, as for self-regulation of commitments (self and to other robots or humans) and learning in such conditions. A group of unique autonomous robots with state-of-the art capabilities will be assigned to carry on duties (delivery, patrol, search) on an office floor, with no a priori knowledge about the environment. Performance will be characterized by the complexity of the working scenario, the effectiveness of the team in achieving its tasks based on its capabilities, and the level of human interventions required. Five Ph.D. and one Master's students, one postdoctoral researcher, one trainee as for teams of undergraduate students will be directly trained through this initiative.