Self Aware Robots – ROBOERGOSUM

One of the greatest challenges facing robotics research today is the design of robots able to act autonomously at a cognitive level, and to interact with people in a natural way. Major progress has been accomplished in several aspects of robotics: perception, navigation, localization, SLAM, motion and action planning, manipulation, human-robot interaction, learning. However we still lack a genuine theory of the underlying principles and methods that would enable robots to understand their environment, to be cognizant of what they do, to take appropriate and timely initiatives, to be able to reason and decide on their own - without being requested for -, to be curious, and to learn from experience in an open-ended fashion.

We contend that self and situation awareness are at the core of the answers to the abilities mentioned above, and that there is an intricate relationship between self-awareness and the ability to perform cognitive-level reasoning. Our goal in this project is to explore this assertion and study its consequences and to propose at least a few elements of a supporting theory, with experimental proofs of concepts.