EASEL will explore and develop a theoretical understanding of human-robot symbiotic interaction (HRSI) where symbiosis is defined as the capacity of the robot and the person to mutually influence each other, and alter each other’s behaviour over different time-scales (for instance, within encounters and across encounters). Symbiosis requires that the robot can read, and be responsive to, the behaviour and emotional state of the person, and adapt its own behaviour to take into account the user social context and extract knowledge from long sequences of behavioural interaction and changing its action responses accordingly. EASEL takes tutoring as validation domain. Current ICT applications for teaching and tutoring lack in their abilities for adaptation and only deal with limited problem spaces. EASEL will develop a new set of Robotic Based Tutoring Solutions (RBTS) and will deliver an innovative Synthetic Tutor Assistant (STA) incorporating key features of human tutors and other proven approaches capable to instruct a human user and learn from their interactions during large time scales. EASEL will develop new cross-disciplinary theoretical models for intelligent learning systems and test them into learning contexts including interaction with children, in the classroom and in museums. Scientifically we will develop new theories to address formally how a social context can be acquired and how new action possibilities could be learned. We base this social context formalization on the concept of social affordances, the new action possibilities arising from a bidirectional history of interactions that determine social and contextual priors. For this purpose EASEL will develop new spatial and temporal perceptual capabilities, to be able to process speech tokens, gestures, facial expressions and physiological data, integrated over long time scales in long term memory structures. EASEL will certainly advance the theories of human cognition.