Generative design of stabilizing controllers with diffusion models: the Youla approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cercola, Matteo, Materassi, Donatello, Formentin, Simone
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914206296571904
author Cercola, Matteo
Materassi, Donatello
Formentin, Simone
author_facet Cercola, Matteo
Materassi, Donatello
Formentin, Simone
contents Designing controllers that simultaneously achieve strong performance and provable closed-loop stability remains a central challenge in control engineering. This work introduces a diffusion-based generative framework for linear controller synthesis grounded in the Youla-Kucera parameterization, enabling the construction of stabilizing controllers by design. The diffusion model learns a conditional mapping from plant dynamics and desired performance metrics to feasible Youla parameters, guaranteeing internal stability while flexibly accommodating user-specified targets. Trained on synthetically generated stable SISO plants with fixed-order Youla parameters, the proposed approach reliably synthesizes controllers that meet prescribed sensitivity and settling-time specifications on previously unseen systems. To the best of our knowledge, this work provides the first demonstration that diffusion models can generate stabilizing controllers, combining rigorous control-theoretic guarantees with the versatility of modern generative modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15725
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative design of stabilizing controllers with diffusion models: the Youla approach
Cercola, Matteo
Materassi, Donatello
Formentin, Simone
Systems and Control
Designing controllers that simultaneously achieve strong performance and provable closed-loop stability remains a central challenge in control engineering. This work introduces a diffusion-based generative framework for linear controller synthesis grounded in the Youla-Kucera parameterization, enabling the construction of stabilizing controllers by design. The diffusion model learns a conditional mapping from plant dynamics and desired performance metrics to feasible Youla parameters, guaranteeing internal stability while flexibly accommodating user-specified targets. Trained on synthetically generated stable SISO plants with fixed-order Youla parameters, the proposed approach reliably synthesizes controllers that meet prescribed sensitivity and settling-time specifications on previously unseen systems. To the best of our knowledge, this work provides the first demonstration that diffusion models can generate stabilizing controllers, combining rigorous control-theoretic guarantees with the versatility of modern generative modeling.
title Generative design of stabilizing controllers with diffusion models: the Youla approach
topic Systems and Control
url https://arxiv.org/abs/2512.15725