logo Idiap Research Institute        
 [BibTeX] [Marc21]
Bayesian Gaussian mixture model for robotic policy imitation
Type of publication: Journal paper
Citation: Pignat_RA-L_2019
Publication status: Published
Journal: IEEE Robotics and Automation Letters
Volume: 4
Number: 4
Year: 2019
Month: October
Pages: 4452 - 4458
ISSN: 10.1109/LRA.2019.2932610
URL: https://ieeexplore.ieee.org/do...
DOI: 10.1109/LRA.2019.2932610
Abstract: 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.
Projects Idiap
Authors Pignat, Emmanuel
Calinon, Sylvain
Added by: [UNK]
Total mark: 0
  • Pignat_RA-L_2019.pdf