Grant: Discovery Grants Program - Individual
McGill University
$30,000.00
Multi-agent robotic interaction
FY 2013-14
Summary
Taking advantage of huge recent advances in robotics depends on interaction between a robot, and either the other systems around it, and/or the humans employing it. We have identified this interaction as a key problem that limits future progress in the near term. As a society, have great robotics technologies on hand or almost mature. What we lack are good formal tools and foundations that let us link diverse types robots to one another to build more capable heterogeneous systems, or let humans and robots work together to allow the human to efficiently and effortlessly make use of automated assistance. This is akin to challenge faced by computer networks in the 1970s, which was solved via the deployment of the Internet, but not the diverse collection includes both humans and machines, making the challenge much more profound.This problem of developing not merely user interfaces or communication wrappers, but basic representations and interaction paradigms for collaboration between different kinds of agents, where an agent can mean either a person or a robotic vehicle. Addressing this issue has the potential to dramatically change the way robots and autonomous systems can and will be used in the next 5 to 15 years.Robots are able, or almost able, to accomplish useful tasks, but their adoption will be hampered by our ability to integrate them comfortably, efficiently, safely and easily into our existing infrastructure and modes of behavior. My proposal addresses these challenges of concise and natural inter-agent representation, data sharing, planning and sensing. As a testing scenario, much of my work will take place on amphibious or underwater vehicles where robot interaction becomes clearly highlighted. In addition, this addresses clear and open needs in the marine biology community.
Program
Discovery Grants Program - Individual
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
105395-2013
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
2013
Competition year année de concours
2013
Award amount
30000
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
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
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
Multi-agent robotic interaction
Keyword
NSERC
Application summary
Taking advantage of huge recent advances in robotics depends on interaction between a robot, and either the other systems around it, and/or the humans employing it. We have identified this interaction as a key problem that limits future progress in the near term. As a society, have great robotics technologies on hand or almost mature. What we lack are good formal tools and foundations that let us link diverse types robots to one another to build more capable heterogeneous systems, or let humans and robots work together to allow the human to efficiently and effortlessly make use of automated assistance. This is akin to challenge faced by computer networks in the 1970s, which was solved via the deployment of the Internet, but not the diverse collection includes both humans and machines, making the challenge much more profound.This problem of developing not merely user interfaces or communication wrappers, but basic representations and interaction paradigms for collaboration between different kinds of agents, where an agent can mean either a person or a robotic vehicle. Addressing this issue has the potential to dramatically change the way robots and autonomous systems can and will be used in the next 5 to 15 years.Robots are able, or almost able, to accomplish useful tasks, but their adoption will be hampered by our ability to integrate them comfortably, efficiently, safely and easily into our existing infrastructure and modes of behavior. My proposal addresses these challenges of concise and natural inter-agent representation, data sharing, planning and sensing. As a testing scenario, much of my work will take place on amphibious or underwater vehicles where robot interaction becomes clearly highlighted. In addition, this addresses clear and open needs in the marine biology community.