Skip to main content

Leveraging neural networks and the Koopman operator for controlled dynamical systems and linear model predictive control

Resource type
Thesis type
(Thesis) M.Sc.
Date created
2023-11-20
Authors/Contributors
Abstract
In this thesis, we present a novel network architecture using an encoder-decoder neural network, inspired by Lusch et al. [15], to directly obtain the eigenfunctions of the Koopman operator, which globally linearize the dynamics of nonlinear systems. By extending this approach to account for control inputs, we enable the application of well-established control synthesis techniques for obtaining optimal policies, while ensuring that control constraints remain convex for globally optimal solutions. This method overcomes the limitations of traditional Koopman operator approximations and provides improved prediction and control performance. We demonstrate the efficacy of our approach on a range of simulated controlled dynamical systems and show its potential for real-world applications in fields like robotics, and process control.
Document
Extent
45 pages.
Identifier
etd22885
Copyright statement
Copyright is held by the author(s).
Permissions
This thesis may be printed or downloaded for non-commercial research and scholarly purposes.
Supervisor or Senior Supervisor
Thesis advisor: Chen, Mo
Language
English
Member of collection
Download file Size
etd22885.pdf 1.37 MB

Views & downloads - as of June 2023

Views: 0
Downloads: 0