Dynamically Consistent Probabilistic Model for Robot Motion Learning

Diego Pardo, Leonel Rozo, Guillem Alenya and Carme Torras

This work presents a probabilistic model for learning robot tasks from human demonstrations using kinesthetic teaching. The difference with respect to similar previous works is that a complete representation of the state of the robot is used to obtain a consistent representation of the dynamics of the task. The learning framework is based on hidden Markov models and Gaussian mixture regression, used for coding and reproducing the skills. Benefits of the proposed approach are shown in the execution of a simple self-crossing trajectory by a 7-DoF manipulator.