10.1109/LRA.2021.3060414
https://zenodo.org/records/5596174
oai:zenodo.org:5596174
Kulak, Thibaut
Thibaut
Kulak
Idiap Research Institute, Martigny, Switzerland
Girgin, Hakan
Hakan
Girgin
Idiap Research Institute, Martigny, Switzerland
Odobez, Jean-Marc
Jean-Marc
Odobez
Idiap Research Institute, Martigny, Switzerland
Calinon, Sylvain
Sylvain
Calinon
Idiap Research Institute, Martigny, Switzerland
Active Learning of Bayesian Probabilistic Movement Primitives
Zenodo
2021
2021-03-18
https://zenodo.org/communities/collaborate_project
https://zenodo.org/communities/eu
Creative Commons Attribution 4.0 International
Learning from Demonstration permits non-expert users to easily and intuitively reprogram robots. Among approaches embracing this paradigm, probabilistic movement primitives (ProMPs) are a well-established and widely used method to learn trajectory distributions. However, providing or requesting useful demonstrations is not easy, as quantifying what constitutes a good demonstration in terms of generalization capabilities is not trivial. In this letter, we propose an active learning method for contextual ProMPs for addressing this problem. More specifically, we learn the trajectory distributions using a Bayesian Gaussian mixture model (BGMM) and then leverage the notion of epistemic uncertainties to iteratively choose new context query points for demonstrations. We show that this approach reduces the required number of human demonstrations. We demonstrate the effectiveness of the approach on a pouring task, both in simulation and on a real 7-DoF Franka Emika robot.
European Commission
10.13039/501100000780
820767
Co-production CeLL performing Human-Robot Collaborative AssEmbly