Advanced

Building rich and grounded robot world models from sensors and knowledge resources: A conceptual spaces approach

Gärdenfors, Peter LU and Williams, M.-A. (2003) AMiRE'03: 2nd International Symposium on Autonomous Minirobots for Research and Edutainment In Proceedings of AMIRE 2003 p.123-132
Abstract
Robots interacting with other agents in rich information landscapes and complex dynamic physical environments require sophisticated and robust concept and knowledge management capabilities if they are to solve problems, communicate, learn and exhibit intelligent behaviours. In this paper we describe how conceptual spaces provide a powerful substrate upon which to build effective concept and knowledge management capabilities that integrate information from multiple sensory and symbolic sources. We use SONY AIBO robots and the robot soccer domain to illustrate our framework and approach. The conceptual spaces framework allows robots to build rich and grounded world models from a wide variety of internal and external knowledge resources, e.g.... (More)
Robots interacting with other agents in rich information landscapes and complex dynamic physical environments require sophisticated and robust concept and knowledge management capabilities if they are to solve problems, communicate, learn and exhibit intelligent behaviours. In this paper we describe how conceptual spaces provide a powerful substrate upon which to build effective concept and knowledge management capabilities that integrate information from multiple sensory and symbolic sources. We use SONY AIBO robots and the robot soccer domain to illustrate our framework and approach. The conceptual spaces framework allows robots to build rich and grounded world models from a wide variety of internal and external knowledge resources, e.g. sensors, ontologies, databases, knowledge bases, the semantic Web, Web services, and other agents. Conceptual spaces provide an important and effective bridge between the perceptual level and the symbolic level by grounding sensory information to objects (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
robot soccer domain, knowledge management, knowledge resources, SONY AIBO robots
in
Proceedings of AMIRE 2003
pages
123 - 132
publisher
Queensland University of Technology
conference name
AMiRE'03: 2nd International Symposium on Autonomous Minirobots for Research and Edutainment
ISBN
1-7410-7012-0
language
English
LU publication?
yes
id
d44f6197-fcbd-44b0-86a5-7b99f1ebefe9 (old id 533157)
date added to LUP
2007-09-18 08:33:46
date last changed
2016-04-16 07:51:55
@misc{d44f6197-fcbd-44b0-86a5-7b99f1ebefe9,
  abstract     = {Robots interacting with other agents in rich information landscapes and complex dynamic physical environments require sophisticated and robust concept and knowledge management capabilities if they are to solve problems, communicate, learn and exhibit intelligent behaviours. In this paper we describe how conceptual spaces provide a powerful substrate upon which to build effective concept and knowledge management capabilities that integrate information from multiple sensory and symbolic sources. We use SONY AIBO robots and the robot soccer domain to illustrate our framework and approach. The conceptual spaces framework allows robots to build rich and grounded world models from a wide variety of internal and external knowledge resources, e.g. sensors, ontologies, databases, knowledge bases, the semantic Web, Web services, and other agents. Conceptual spaces provide an important and effective bridge between the perceptual level and the symbolic level by grounding sensory information to objects},
  author       = {Gärdenfors, Peter and Williams, M.-A.},
  isbn         = {1-7410-7012-0},
  keyword      = {robot soccer domain,knowledge management,knowledge resources,SONY AIBO robots},
  language     = {eng},
  pages        = {123--132},
  publisher    = {ARRAY(0x9bf64f0)},
  series       = {Proceedings of AMIRE 2003},
  title        = {Building rich and grounded robot world models from sensors and knowledge resources: A conceptual spaces approach},
  year         = {2003},
}