Please use this identifier to cite or link to this item: http://dx.doi.org/10.18419/opus-9722
|Title:||Learning an approximate model predictive controller with guarantees|
|metadata.ubs.bemerkung.extern:||Parts of this thesis have been submitted for publication at the IEEE Control Systems Letters. The title of the submitted paper is "Learning an Approximate Model Predictive Controller with Guarantees". The authors of the paper are Michael Hertneck, Johannes Köhler, Sebastian Trimpe and Frank Allgöwer.|
|Abstract:||In this thesis, a supervised learning framework to approximate a model predictive controller (MPC) with guarantees on stability and constraint satisfaction is proposed. The approximate controller has a reduced computational complexity in comparison to standard MPC which makes it possible to implement the resulting controller for systems with a high sampling rate on a cheap hardware. The framework can be used for a wide class of nonlinear systems. In order to obtain closed-loop guarantees for the approximate MPC, a robust MPC (RMPC) with robustness to bounded input disturbances is used which guarantees stability and constraint satisfaction if the input is approximated with a bound on the approximation error. The RMPC can be sampled offline and hence, any standard supervised learning technique can be used to approximate the MPC from samples. Neural networks (NN) are discussed in this thesis as one suitable approximation method. To guarantee a bound on the approximation error, statistical learning bounds are used. A method based on Hoeffding’s Inequality is proposed to validate that the approximate MPC satisfies these bounds with high confidence. This validation method is suited for any approximation method. The result is a closed-loop statistical guarantee on stability and constraint satisfaction for the approximated MPC. Within this thesis, an algorithm to obtain automatically an approximate controller is proposed. The proposed learning-based MPC framework is illustrated on a nonlinear benchmark problem for which we learn a neural network controller that guarantees stability and constraint satisfaction. The combination of robust control and statistical validation can also be used for other learning based control methods to obtain guarantees on stability and constraint satisfaction.|
|Appears in Collections:||07 Fakultät Konstruktions-, Produktions- und Fahrzeugtechnik|
Files in This Item:
|Learning an Approximate Model Predictive Controller with Guarantees.pdf||3,38 MB||Adobe PDF||View/Open|
Items in OPUS are protected by copyright, with all rights reserved, unless otherwise indicated.