Latent force models encode the interaction between multiple related dynamical systems in the form of a kernel or covariance function. Each variable to be modeled is represented as the output of a differential equation and each differential equation is driven by a weighted sum of latent functions with uncertainty given by a Gaussian process prior. In this paper we consider employing the latent force model framework for the problem of determining robot motor primitives. To deal with discontinuities in the dynamical systems or the latent driving force we intro- duce an extension of the basic latent force model, that switches between different latent functions and potentially different dynamical systems. This creates a versatile representation for robot movements that can capture discrete changes and non-linearities in the dynamics. We give illustrative examples on both synthetic data and for striking movements recorded using a Barrett WAM robot as haptic in- put device. Our inspiration is robot motor primitives, but we expect our model to have wide application for dynamical systems including models for human motion capture data and systems biology.

@InProceedings{alvarez-switched10,
title = {Switched Latent Force Models for Movement Segmentation},
author = {Mauricio A. Álvarez and Jan Peters and Bernhard Schölkopf and Neil D. Lawrence},
booktitle = {Advances in Neural Information Processing Systems},
pages = {55},
year = {2010},
editor = {John Lafferty and Christopher K. I. Williams and John Shawe-Taylor and Rich S. Zemel and Aron Culotta},
volume = {23},
address = {Cambridge, MA},
month = {00},
publisher = {MIT Press},
edit = {https://github.com/lawrennd//publications/edit/gh-pages/_posts/2010-01-01-alvarez-switched10.md},
url = {http://inverseprobability.com/publications/alvarez-switched10.html},
pdf = {http://books.nips.cc/papers/files/nips23/NIPS2010_1222.pdf},
abstract = {Latent force models encode the interaction between multiple related dynamical systems in the form of a kernel or covariance function. Each variable to be modeled is represented as the output of a differential equation and each differential equation is driven by a weighted sum of latent functions with uncertainty given by a Gaussian process prior. In this paper we consider employing the latent force model framework for the problem of determining robot motor primitives. To deal with discontinuities in the dynamical systems or the latent driving force we intro- duce an extension of the basic latent force model, that switches between different latent functions and potentially different dynamical systems. This creates a versatile representation for robot movements that can capture discrete changes and non-linearities in the dynamics. We give illustrative examples on both synthetic data and for striking movements recorded using a Barrett WAM robot as haptic in- put device. Our inspiration is robot motor primitives, but we expect our model to have wide application for dynamical systems including models for human motion capture data and systems biology.},
crossref = {Lafferty:nips10},
key = {Alvarez:switched10},
OPTgroup = {}
}

%T Switched Latent Force Models for Movement Segmentation
%A Mauricio A. Álvarez and Jan Peters and Bernhard Schölkopf and Neil D. Lawrence
%B
%C Advances in Neural Information Processing Systems
%D
%E John Lafferty and Christopher K. I. Williams and John Shawe-Taylor and Rich S. Zemel and Aron Culotta
%F alvarez-switched10
%I MIT Press
%P 55--63
%R
%U http://inverseprobability.com/publications/alvarez-switched10.html
%V 23
%X Latent force models encode the interaction between multiple related dynamical systems in the form of a kernel or covariance function. Each variable to be modeled is represented as the output of a differential equation and each differential equation is driven by a weighted sum of latent functions with uncertainty given by a Gaussian process prior. In this paper we consider employing the latent force model framework for the problem of determining robot motor primitives. To deal with discontinuities in the dynamical systems or the latent driving force we intro- duce an extension of the basic latent force model, that switches between different latent functions and potentially different dynamical systems. This creates a versatile representation for robot movements that can capture discrete changes and non-linearities in the dynamics. We give illustrative examples on both synthetic data and for striking movements recorded using a Barrett WAM robot as haptic in- put device. Our inspiration is robot motor primitives, but we expect our model to have wide application for dynamical systems including models for human motion capture data and systems biology.

TY - CPAPER
TI - Switched Latent Force Models for Movement Segmentation
AU - Mauricio A. Álvarez
AU - Jan Peters
AU - Bernhard Schölkopf
AU - Neil D. Lawrence
BT - Advances in Neural Information Processing Systems
PY - 2010/01/01
DA - 2010/01/01
ED - John Lafferty
ED - Christopher K. I. Williams
ED - John Shawe-Taylor
ED - Rich S. Zemel
ED - Aron Culotta
ID - alvarez-switched10
PB - MIT Press
SP - 55
EP - 63
L1 - http://books.nips.cc/papers/files/nips23/NIPS2010_1222.pdf
UR - http://inverseprobability.com/publications/alvarez-switched10.html
AB - Latent force models encode the interaction between multiple related dynamical systems in the form of a kernel or covariance function. Each variable to be modeled is represented as the output of a differential equation and each differential equation is driven by a weighted sum of latent functions with uncertainty given by a Gaussian process prior. In this paper we consider employing the latent force model framework for the problem of determining robot motor primitives. To deal with discontinuities in the dynamical systems or the latent driving force we intro- duce an extension of the basic latent force model, that switches between different latent functions and potentially different dynamical systems. This creates a versatile representation for robot movements that can capture discrete changes and non-linearities in the dynamics. We give illustrative examples on both synthetic data and for striking movements recorded using a Barrett WAM robot as haptic in- put device. Our inspiration is robot motor primitives, but we expect our model to have wide application for dynamical systems including models for human motion capture data and systems biology.
ER -

Álvarez, M.A., Peters, J., Schölkopf, B. & Lawrence, N.D.. (2010). Switched Latent Force Models for Movement Segmentation. Advances in Neural Information Processing Systems 23:55-63