Generation and adaptation of robot skills models

Humanoid robots are required to perform a wide repertoire of task working beside humans in complex dynamic environments. Learning mechanism are important for building up this type of repertoires of robot skills, however, despite the clear advantages of this approaches it would be impractical to teach the robot skills for every needed task and for every foreseen situation. Robot skills learning approaches to develop humanoid robotic systems would have greater impact if the models of the skill can be operated upon to generate new behaviours of increasing levels of complexity. A framework that allows the adaptation of a robot previously learned motion skills to new unseen contexts is necessary. In this work we present different modalities for the adaptation and generation of new skill models based on the already learned models of skills. Experimental results are presented to validate this approach.