Grant: Discovery Grants Program - Individual
University of British Columbia
$51,500.00
Robots, maps, and tasks
EF 2009-10
Résumé
Currently we have mobile robots that can map their environs both indoors and outdoors, and then reliably recover their metric position while moving around in their space by solving the well-known simultaneous localization and mapping problem (SLAM). But robots cannot yet tell us where they are, nor easily take our directions.
Bridging the gap between dense accurate geometric information and the semantics of the space we share with robots is the critical next step in building usable robotic assistants.
I will investigate how to supply a world description to the robot, learned from examples or adopted from ontologies that characterize prototypical spaces. The relations between places and robots support our interactions with them and enable robots to work with us. Moreover, I will ground descriptions in robust visual features that identify particular locations, to which place identifiers are associated.
Assistive technology, in particular stereo-guided wheelchairs, is an application where stereo sensing-based mapping technology can sense obstacles and nearby walking patients. Moreover, vision can provide situation awareness, by giving information about contexts and activities, beyond simple geometric occupancy maps.
Recently our mobile robotics group teamed with David Lowe's group in recognition to create "Curious George", a mobile robot for the semantic Robot Vision challenge at AAAI 2007. The robot learns to find objects in a room from Web images. Our next generation robots will use maps to guide viewpoint selection and use context to find objects, and assist people in everyday tasks.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
41627-2008
Name nom
Little, James
Department département
Computer Science
Organization id
2
Institution établissement
University of British Columbia
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2009
Competition year année de concours
2008
Award amount
51500
Program id
RGPIN
Program nane 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
2603
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Computer vision
Research subject fr
Vision artificielle
Partie
2
Nb partie
5
Application title
Robots, maps, and tasks
Keyword
NA
Application summary
Currently we have mobile robots that can map their environs both indoors and outdoors, and then reliably recover their metric position while moving around in their space by solving the well-known simultaneous localization and mapping problem (SLAM). But robots cannot yet tell us where they are, nor easily take our directions.
Bridging the gap between dense accurate geometric information and the semantics of the space we share with robots is the critical next step in building usable robotic assistants.
I will investigate how to supply a world description to the robot, learned from examples or adopted from ontologies that characterize prototypical spaces. The relations between places and robots support our interactions with them and enable robots to work with us. Moreover, I will ground descriptions in robust visual features that identify particular locations, to which place identifiers are associated.
Assistive technology, in particular stereo-guided wheelchairs, is an application where stereo sensing-based mapping technology can sense obstacles and nearby walking patients. Moreover, vision can provide situation awareness, by giving information about contexts and activities, beyond simple geometric occupancy maps.
Recently our mobile robotics group teamed with David Lowe's group in recognition to create "Curious George", a mobile robot for the semantic Robot Vision challenge at AAAI 2007. The robot learns to find objects in a room from Web images. Our next generation robots will use maps to guide viewpoint selection and use context to find objects, and assist people in everyday tasks.