Billard, A.Epars, Y.Calinon, S.Cheng, G.Schaal, S.2005-11-162005-11-162005-11-16200410.1016/j.robot.2004.03.002https://infoscience.epfl.ch/handle/20.500.14299/220068WOS:0002223335000025277This paper develops a general policy for learning relevant features of an imitation task. We restrict our study to imitation of manipulative tasks or of gestures. The imitation process is modeled as a hierarchical optimization system, which minimizes the discrepancy between two multi- dimensional datasets. To classify across manipulation strategies, we apply a probabilistic analysis to data in Cartesian and joint spaces. We determine a general metric that optimizes the policy of task reproduction, following strategy determination. The model successfully discovers strategies in six different imitative tasks and controls task reproduction by a full body humanoid robot.Programming by DemonstrationImitation LearningHumanoid RobotsArtificial Neural NetworksHidden Markov ModelsBayesian LearningLearning by imitation - Roboticstext::journal::journal article::research article