Abstract

We present an approach for creating conceptual representations of human-made indoor environments using mobile
robots. The concepts refer to spatial and functional properties of typical indoor environments. Following findings
in cognitive psychology, our model is composed of layers representing maps at different levels of abstraction. The
complete system is integrated in a mobile robot endowed with laser and vision sensors for place and object recognition.
The system also incorporates a linguistic framework that actively supports the map acquisition process, and which
is used for situated dialogue. Finally, we discuss the capabilities of the integrated system.