MPC with Gaussian Processes

Main content

Gaussian process (GP) regression has been widely used in supervised machine learning for its flexibility and inherent ability to describe uncertainty in the prediction. In the context of control, it is seeing increasing use for modeling of nonlinear dynamical systems from data, as it allows for direct assessment of the residual model uncertainty.

In practice, a nominal linear model is often available, while more complex nonlinearities can be challenging and time-intensive to model from first principles. We develop a model predictive control (MPC) approach that integrates a nominal linear system with an additive nonlinear part of the dynamics modeled as a GP. The resulting nonlinear stochastic control problem specifically takes into account the model uncertainties associated with the GP, and thus enables cautious control of the system.

Accordion. Press Tab to navigate to entries, then Enter to open or collapse content.

 

Publications & Talks

Lukas Hewing and Melanie N. Zeilinger. Predictive Control with Model Uncertainty Estimation using Gaussian Process Regression. 4th European Conference on Computational Optimization, Leuven, 2016.
[abstract] (PDF, 63 KB)

E. D. Klenske, M. N. Zeilinger, B. Schoelkopf, and P. Hennig. Gaussian process based predictive control for periodic error correction. IEEE Trans. Control Syst. Technol., 2016
[doi]|[E-Citations]

 
 
Page URL: http://www.idsc.ethz.ch/research-zeilinger/research-projects/GPMPC.html
Fri Jun 23 12:46:04 CEST 2017
© 2017 Eidgenössische Technische Hochschule Zürich