Agudelo-España, D., Álvarez, M.A. orcid.org/0000-0002-8980-4472 and Orozco, Á.A. (2017) Definition and composition of motor primitives using latent force models and hidden Markov models. In: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2016. Iberoamerican Congress on Pattern Recognition, 08/11/2016-11/11/2016, Lima, Peru. Lecture Notes in Computer Science, 10125 . Springer Verlag , pp. 249-256. ISBN 9783319522760
Abstract
In this work a different probabilistic motor primitive parameterization is proposed using latent force models (LFMs). The sequential composition of different motor primitives is also addressed using hidden Markov models (HMMs) which allows to capture the redundancy over dynamics by using a limited set of hidden primitives. The capability of the proposed model to learn and identify motor primitive occurrences over unseen movement realizations is validated using synthetic and motion capture data.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2017 Springer. This is an author produced version of a paper subsequently published in Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2016. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | Movement representation; Motor primitives; Latent force models; Hidden Markov models; Switched models; Multi-output GPs |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 19 May 2017 10:41 |
Last Modified: | 18 Jul 2017 18:01 |
Published Version: | https://doi.org/10.1007/978-3-319-52277-7_31 |
Status: | Published |
Publisher: | Springer Verlag |
Series Name: | Lecture Notes in Computer Science |
Refereed: | Yes |
Identification Number: | 10.1007/978-3-319-52277-7_31 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:116580 |