Department of Computer Science Technische Universitaet Muenchen
Home People Teaching Research Publications Info Sitemap
IAS | Image Understanding | Med | MQM

Publications

Sorted by DateClassified by Publication TypeClassified by Research CategoryClassified by Research GroupClassified by Author Last Name

Moritz Tenorth and Michael Beetz. Towards Practical and Grounded Knowledge Representation Systems for Autonomous Household Robots. In Proceedings of the 1st International Workshop on Cognition for Technical Systems, München, Germany, 6-8 October, 2008.

Download

[PDF]1.4MB  

Abstract

Mobile household robots need much knowledge about objects, places and actions when performing more and more complex tasks. They must be able to recognize objects, know what they are and how they can be used. This knowledge can often be specified more easily in terms of action-related concepts than by giving declarative descriptions of the appearance of objects. Defining chairs as objects to sit on, for instance, is much more natural than describing how chairs in general look like. Having grounded symbolic models of its actions and related concepts allows the robot to reason about its activities and improve its problem solving performance. In order to use action-related concepts, the robot must be able to find them in its environment. We present a practical approach to robot knowledge representation that combines description logics knowledge bases with data mining and (self-) observation modules. The robot collects experiences while executing actions and uses them to learn models and aspects of action-related concepts grounded in its perception and action system. We demonstrate our approach by learning places that are involved in mobile robot manipulation actions.

BibTeX Entry

@InProceedings{tenorth08cotesys,
  author    = {Moritz Tenorth and Michael Beetz},
  title     = {Towards Practical and Grounded Knowledge Representation Systems for Autonomous Household Robots},
  booktitle = {Proceedings of the 1st International Workshop on Cognition for Technical Systems, M{\"u}nchen, Germany, 6-8 October},
  year      = {2008},
  bib2html_pubtype = {Refereed Conference Paper},
  bib2html_rescat  = {Knowledge Representation, GrAM},
  bib2html_groups  = {IAS},
  bib2html_funding  = {CoTeSys},
  abstract = {Mobile household robots need much knowledge about objects, places and actions 
              when performing more and more complex tasks. They must be able to recognize
              objects, know what they are and how they can be used. This knowledge can
              often be specified more easily in terms of action-related concepts than by
              giving declarative descriptions of the appearance of objects. Defining chairs
              as objects to sit on, for instance, is much more natural than describing
              how chairs in general look like.
              Having grounded symbolic models of its actions and related concepts allows
              the robot to reason about its activities and improve its problem solving 
              performance.
              In order to use action-related concepts, the robot must be able to find them in its
              environment. We present a practical approach to robot knowledge representation that
              combines description logics knowledge bases with data mining and (self-) observation
              modules. The robot collects experiences while executing actions and uses them to 
              learn models and aspects of action-related concepts grounded in its perception and
              action system.
              We demonstrate our approach by learning places that are involved in mobile
              robot manipulation actions.}
}

Generated by bib2html.pl (written by Patrick Riley ) on Sat Nov 29, 2008 01:35:43 UTC


Computer Science IX | Technische Universität München