Gaussian Process Latent Force Models for Learning and Stochastic Control of Physical Systems

Simo Sarkka, Mauricio A. Alvarez, Neil D. Lawrence

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish
Article number8485787
Pages (from-to)2953-2960
Number of pages8
JournalIEEE Transactions on Automatic Control
Volume64
Issue number7
DOIs
Publication statusPublished - Jul 2019

Keywords

  • Kalman filtering
  • machine learning
  • stochastic optimal control
  • stochastic systems
  • system identification

Fingerprint

Dive into the research topics of 'Gaussian Process Latent Force Models for Learning and Stochastic Control of Physical Systems'. Together they form a unique fingerprint.

Cite this