Learning Stable Koopman Embeddings

Fan, F; Yi, B; Rye, D; Shi, G; Manchester, IR

Learning Stable Koopman Embeddings

Fan, F Yi, B

Rye, D Shi, G Manchester, IR

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Conference Proceeding
Citation:: Proceedings of the American Control Conference, 2022, 2022-June, pp. 2742-2747
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	Learning_Stable_Koopman_Embeddings.pdf	Published version	271.96 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Fan, F
dc.contributor.author	Yi, B https://orcid.org/0000-0002-0517-9519
dc.contributor.author	Rye, D
dc.contributor.author	Shi, G
dc.contributor.author	Manchester, IR
dc.date	2022-06-08
dc.date.accessioned	2023-03-10T04:10:26Z
dc.date.available	2023-03-10T04:10:26Z
dc.date.issued	2022-01-01
dc.identifier.citation	Proceedings of the American Control Conference, 2022, 2022-June, pp. 2742-2747
dc.identifier.isbn	9781665451963
dc.identifier.issn	0743-1619
dc.identifier.uri	http://hdl.handle.net/10453/166960
dc.description.abstract	In this paper, we present a new data-driven method for learning stable models of nonlinear systems. Our model lifts the original state space to a higher-dimensional linear manifold using Koopman embeddings. Interestingly, we prove that every discrete-time nonlinear contracting model can be learnt in our framework. Another significant merit of the proposed approach is that it allows for unconstrained optimization over the Koopman embedding and operator jointly while enforcing stability of the model, via a direct parameterization of stable linear systems, greatly simplifying the computations involved. We validate our method on a simulated system and analyze the advantages of our parameterization compared to alternatives.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	Proceedings of the American Control Conference
dc.relation.ispartof	2022 American Control Conference (ACC)
dc.relation.isbasedon	10.23919/ACC53348.2022.9867865
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Learning Stable Koopman Embeddings
dc.type	Conference Proceeding
utslib.citation.volume	2022-June
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2023-03-10T04:10:25Z
pubs.finish-date	2022-06-10
pubs.publication-status	Published
pubs.start-date	2022-06-08
pubs.volume	2022-June

Abstract:

In this paper, we present a new data-driven method for learning stable models of nonlinear systems. Our model lifts the original state space to a higher-dimensional linear manifold using Koopman embeddings. Interestingly, we prove that every discrete-time nonlinear contracting model can be learnt in our framework. Another significant merit of the proposed approach is that it allows for unconstrained optimization over the Koopman embedding and operator jointly while enforcing stability of the model, via a direct parameterization of stable linear systems, greatly simplifying the computations involved. We validate our method on a simulated system and analyze the advantages of our parameterization compared to alternatives.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/166960