George scenario

George is a curious robot we developed in the CogX project. Our objective was 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.

Our work focuses on the integration of visual perception and processing of linguistic information by forming beliefs about the state of the world; these beliefs are then used in the learning process for updating the current representations. The system behaviour is driven by a motivation framework which facilitates different kinds of learning in a dialogue with a human teacher, including self-motivated learning, triggered by autonomous knowledge gap detection. George is based on a distributed asynchronous architecture depicted in the figure below.

The video below shows the system in action. It explains the main principles implemented in George. It describes the operation of the robot from a system perspective with the emphasis on different learning mechanisms and shows fragments of the corresponding mixed-initiative dialogue.