@article{9758d422439f4c908a46169950bca050,
title = "Gaussian Process Latent Force Models for Learning and Stochastic Control of Physical Systems",
abstract = "This paper is concerned with learning and stochastic control in physical systems that contain unknown input signals. These unknown signals are modeled as Gaussian processes (GP) with certain parameterized covariance structures. The resulting latent force models can be seen as hybrid models that contain a first-principle physical model part and a nonparametric GP model part. We briefly review the statistical inference and learning methods for this kind of models, introduce stochastic control methodology for these models, and provide new theoretical observability and controllability results for them.",
keywords = "Kalman filtering, machine learning, stochastic optimal control, stochastic systems, system identification",
author = "Simo Sarkka and Alvarez, {Mauricio A.} and Lawrence, {Neil D.}",
note = "Funding Information: Manuscript received April 8, 2018; revised July 16, 2018 and August 13, 2018; accepted September 12, 2018. Date of publication October 8, 2018; date of current version June 26, 2019. The work of S. S{\"a}rkk{\"a} was financially supported by the Academy of Finland. The work of M. A. {\'A}lvarez was supported in part by the EPSRC under Research Project EP/N014162/1. Recommended by Associate Editor G. Pillonetto. (Corresponding author: Simo S{\"a}rkk{\"a}.) S. S{\"a}rkk{\"a} is with the Department of Electrical Engineering and Automation, Aalto University, Alto 00076, Finland (e-mail:, simo.sarkka@ aalto.fi). Publisher Copyright: {\textcopyright} 1963-2012 IEEE.",
year = "2019",
month = jul,
doi = "10.1109/TAC.2018.2874749",
language = "English",
volume = "64",
pages = "2953--2960",
journal = "IEEE Transactions on Automatic Control",
issn = "0018-9286",
publisher = "IEEE",
number = "7",
}