Dora the Explorer is a mobile robot with a sense of curiosity and a drive to explore its world. Given an incomplete tour of an indoor environment, Dora is driven by internal motivations to probe the gaps in her spatial knowledge. She actively explores regions of space which she hasn’t previously visited but which she expects will lead her to further unexplored space. She will also attempt to determine the categories of rooms through active visual search for functionally important objects, and through ontology-driven inference on the results of this search.
Our robot George learns and refines visual conceptual models of colours and two basic shapes, either by attending to information deliberately provided by a human tutor: e.g., Human: `This is a red box.’ or by taking initiative itself, asking the tutor for specific information about an object in the scene: e.g., George: `Is the elongated object yellow?’, or even asking questions that are not related to the current scene: e.g., George: `Can you show me something red?’. Our approach unifies these cases into an integrated approach including incremental visual learning, selection of learning goals, continual planning to select actions for optimal learning behaviour, and a dialogue subsystem. George is one system in a family of integrated systems that aim to understand where their own knowledge is incomplete and that take actions to extend their knowledge subsequently. Our objective is to demonstrate that a cognitive system can efficiently acquire conceptual models in an interactive learning process that is not overly taxing with respect to tutor supervision and is performed in an intuitive, user-friendly way.
Dora and George are both part of the EU-funded project CogX.
Michael Zillich – zillich(at)acin.tuwien.ac.at
Thomas Mörwald – moerwald(at)acin.tuwien.ac.at
Andreas Richtsfeld – ari(at)acin.tuwien.ac.at
Kai Zhou – zhou(at)acin.tuwien.ac.at
Videos can be found on the CogX-Channel