Grant: Discovery Grants Program - Individual
McGill University
$61,000.00
Autonomous systems for unstructured environments
EF 2012-13
Résumé
This proposal deals with
acquiring and maintaining a description of a large-scale
unknown dynamic environment using a collection of
spatially distributed mobile and immobile sensors. This is to be examined specifically in the context of underwater and amphibious robotics.
Important research objectives, successively more abstract, are: multiple robot collaborative task execution, modeling and summarization of large navigation histories (particularly for
human consumption and analysis),
robust vision-based robot navigation and exploration over large unstructured environments,
approaches to re-generating apparently complete descriptions of an
environment from partial models,
the development of a
a coherent theoretical framework for both metric and non-metric
exploration and spatial representation.
As a key concrete example and application, the questions I
propose to examine are how an amphibious vehicle can build descriptions
of its environment, navigate over and record the flora and fauna on a coral reef, plan its
activities (including recovery from surprising events), and interact with humans and other computational
agents in its immediate vicinity. This is an application domain with genuine significance
and real challenges. Moreover, it necessitates scientific innovation in order to handle the
rich and variable context. Until refcently, it could be argued that neither our scientific not
our engineering skills we up to this challange.
With the maturation of robotics as a field, large changes are
taking place in our understanding of the key principles of the field, and in how they can be applied.
This suggests that there is an exceptional potential to contribute to, and influence, the development
of this discipline as it crystallizes.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
105395-2008
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
2012
Competition year année de concours
2008
Award amount
61000
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
331
Committee name en
Computing and Information Sciences - B
Committee name fr
Informatique - B
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
5
Nb partie
5
Application title
Autonomous systems for unstructured environments
Keyword
NSERC
Application summary
This proposal deals with
acquiring and maintaining a description of a large-scale
unknown dynamic environment using a collection of
spatially distributed mobile and immobile sensors. This is to be examined specifically in the context of underwater and amphibious robotics.
Important research objectives, successively more abstract, are: multiple robot collaborative task execution, modeling and summarization of large navigation histories (particularly for
human consumption and analysis),
robust vision-based robot navigation and exploration over large unstructured environments,
approaches to re-generating apparently complete descriptions of an
environment from partial models,
the development of a
a coherent theoretical framework for both metric and non-metric
exploration and spatial representation.
As a key concrete example and application, the questions I
propose to examine are how an amphibious vehicle can build descriptions
of its environment, navigate over and record the flora and fauna on a coral reef, plan its
activities (including recovery from surprising events), and interact with humans and other computational
agents in its immediate vicinity. This is an application domain with genuine significance
and real challenges. Moreover, it necessitates scientific innovation in order to handle the
rich and variable context. Until refcently, it could be argued that neither our scientific not
our engineering skills we up to this challange.
With the maturation of robotics as a field, large changes are
taking place in our understanding of the key principles of the field, and in how they can be applied.
This suggests that there is an exceptional potential to contribute to, and influence, the development
of this discipline as it crystallizes.