ARTICLE Pignat_RA-L_2019/IDIAP Bayesian Gaussian mixture model for robotic policy imitation Pignat, Emmanuel Calinon, Sylvain EXTERNAL https://publications.idiap.ch/attachments/papers/2019/Pignat_RA-L_2019.pdf PUBLIC IEEE Robotics and Automation Letters 4 4 4452 - 4458 10.1109/LRA.2019.2932610 2019 https://ieeexplore.ieee.org/document/8784286 URL 10.1109/LRA.2019.2932610 doi A common approach to learn robotic skills is to imitate a demonstrated policy. Due to the compounding of small errors and perturbations, this approach may let the robot leave the states in which the demonstrations were provided. This requires the consideration of additional strategies to guarantee that the robot will behave appropriately when facing unknown states. We propose to use a Bayesian method to quantify the action uncertainty at each state. The proposed Bayesian method is simple to set up, computationally efficient, and can adapt to a wide range of problems. Our approach exploits the estimated uncertainty to fuse the imitation policy with additional policies. It is validated on a Panda robot with the imitation of three manipulation tasks in the continuous domain using different control input/state pairs.