An Introduction to a Cognitive Decision Unit Applied to Autonomous Robots

A novel approach to equip robots with human-like capabilities is to use meta-psychology – the theoretic foundation of psychoanalysis. We used meta-psychology as archetype for a decision making framework to control a robot. This has been achieved recently in theory and in software simulation. However, when moving to a real robotic platform, additional things have to be considered. In this article we show how to fill the gap between sensing, environmental interaction, and decision making by grounding these topics with an agent's internal needs using the concepts of meta-psychology. The use of the common humanoid robot platform NAO compelled us to deal with complex situations and disturbed sensor readings. An implemented visual marker detecting system helps to detect objects in the surrounding environment, representing energy sources. We show how it is possible to use the psychoanalytically inspired framework A.R.S. to control a real world application, the robot NAO.