A Cognitive Architecture for Socially Adaptable Robots

Abstract

A social robot that's aware of our needs and continuously adapts its behaviour to them has the potential of creating a complex, personalized, human-like interaction of the kind we are used to have with our peers in our everyday lives. However adaptability, being a result of a process of learning and making errors, brings with itself also uncertainty, and we as humans are heavily relying on the machines we use to always be predictable and consistent. To further explore this, we propose a cognitive architecture for the humanoid robot iCub supporting adaptability and we attempt to validate its functionality and establish the potential benefits it could bring with respect to the more traditional pre-scripted interaction protocols for robots.