Learning from demonstration with model-based Gaussian process

Jaquier, Noémie; Ginsbourger, David; Calinon, Sylvain (2020). Learning from demonstration with model-based Gaussian process. In: Kaelbling, Leslie Pack; Kragic, Danica; Sugiura, Komei (eds.) Conference on Robot Learning. Proceedings of Machine Learning Research: Vol. 100 (pp. 247-257). PMLR

[img] Text
jaquier20b.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (2MB) | Request a copy

In learning from demonstrations, it is often desirable to adapt the behavior of the robot as a function of the variability retrieved from human demonstrations and the (un)certainty encoded in different parts of the task. In this paper, we propose a novel multi-output Gaussian process (MOGP) based on Gaussian mixture regression (GMR). The proposed approach encapsulates the variability retrieved from the demonstrations in the covariance of the MOGP. Leveraging the generative nature of GP models, our approach can efficiently modulate trajectories towards new start-, via- or end-points defined by the task. Our framework allows the robot to precisely track via-points while being compliant in regions of high variability. We illustrate the proposed approach in simulated examples and validate it in a real-robot experiment.

Item Type:

Conference or Workshop Item (Paper)


08 Faculty of Science > Department of Mathematics and Statistics > Institute of Mathematical Statistics and Actuarial Science

UniBE Contributor:

Ginsbourger, David


300 Social sciences, sociology & anthropology > 360 Social problems & social services
500 Science > 510 Mathematics
000 Computer science, knowledge & systems


Proceedings of Machine Learning Research






David Ginsbourger

Date Deposited:

09 Sep 2020 12:23

Last Modified:

05 Dec 2022 15:40





Actions (login required)

Edit item Edit item
Provide Feedback