Deterministic safety guarantees for learning-based control of monotone nonlinear systems under uncertainty

Simple item page
dc.contributor.authorAdamek, Joshua
dc.contributor.authorHeinlein, Moritz
dc.contributor.authorLüken, Lukas
dc.contributor.authorLucia, Sergio
dc.date.accessioned2025-09-15T12:31:53Z
dc.date.available2025-09-15T12:31:53Z
dc.date.issued2024-05-30
dc.description.abstractThis letter presents a novel framework to guarantee safety for learning-based control of nonlinear monotone systems under uncertainty. We propose to evaluate online whether a one-step simulation brings a nonlinear system into a robust control invariant (RCI) set. Such evaluation can be very efficiently computed even under the presence of uncertainty for learning-based approximate controllers and monotone systems, which also enable a simple computation of RCI sets. In case the one-step simulation drives the system outside of the RCI set, a fallback strategy is used, which is obtained as a byproduct of the RCI set computation. We also develop a method to calculate an N-step RCI set to reduce the conservativeness of the proposed strategy and we illustrate the results with a simulation study of a nonlinear monotone system.en
dc.identifier.urihttp://hdl.handle.net/2003/43965
dc.language.isoen
dc.relation.ispartofseriesIEEE control systems letters / IEEE Control Systems Society; 8
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectOptimal controlen
dc.subjectRobust controlen
dc.subjectMachine learningen
dc.subject.ddc660
dc.titleDeterministic safety guarantees for learning-based control of monotone nonlinear systems under uncertaintyen
dc.typeText
dc.type.publicationtypeArticle
dcterms.accessRightsopen access
eldorado.dnb.deposittrue
eldorado.doi.registerfalse
eldorado.secondarypublicationtrue
eldorado.secondarypublication.primarycitationJ. Adamek, M. Heinlein, L. Lüken, und S. Lucia, „Deterministic safety guarantees for learning-based control of monotone nonlinear systems under uncertainty“, IEEE control systems letters / IEEE Control Systems Society, Bd. 8, S. 1030–1035, 2024, doi: 10.1109/lcsys.2024.3407635.
eldorado.secondarypublication.primaryidentifierhttps://doi.org/10.1109/lcsys.2024.3407635

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Deterministic_Safety_Guarantees_for_Learning-Based_Control_of_Monotone_Nonlinear_Systems_Under_Uncertainty.pdf
Size:
799.31 KB
Format:
Adobe Portable Document Format
Description:
DNB
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.82 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Fakultät für Bio- und Chemieingenieurwesen