A system for interactive learning in dialogue with a tutor

Danijel Skocaj, Matej Kristan, Alen Vrecko, Marko Mahnic, Miroslav Janicek, Geert-Jan Kruijff, Michael Zillich, Kai Zhou, Marc Hanheide, Nick Hawes, Thomas Keller

In: 5th International Conference on Cognitive Systems, Collection of posters. International Conference on Cognitive Systems (CogSys-2012) February 22-23 Wien Austria 2/2012.


Interactive continuous learning is an important characteristic of a cognitive agent that is supposed to operate and evolve in an everchanging environment. We present representations and mechanisms that are necessary for continuous learning of visual concepts in dialoguewith a tutor. We present an approach for modelling beliefs and we show how these beliefs are created by processing visual and linguistic information. Based on the detected knowledge gaps represented in the beliefs, the motivation and planning mechanism implements four types of interaction for learning. These principles have been implemented in an integrated system.


Weitere Links

skocajCogSys12.pdf (pdf, 246 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence