Learning to react to abstractions: Accumulating adaptations in a humanoid embodiment

Human beings and several other living organisms are capable of acquiring a diverse repertoire of adaptive behaviours or skills, through interaction with an appropriate environment. Based on observations of human embodiment and existing cybernetic theory, an operational description of this form of `scalable´ adaptive behaviour is derivied. An articulated mechanism using the principles identified is implemented and used to control the humanoid robot iCub. The experimental physical embodiment is tested with a number of environments. Preliminary results demonstrate a limited form of emergent behavioural growth and corresponding `task´-non-specificity: the iCub is able to cumulatively learn multiple `tasks´, by chaining together sequences of primative `reactions´, to `abstractions´.