Stability Margins of Neural Network Controllers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Junnarkar, Neelay, Arcak, Murat, Seiler, Peter
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913174433824768
author Junnarkar, Neelay
Arcak, Murat
Seiler, Peter
author_facet Junnarkar, Neelay
Arcak, Murat
Seiler, Peter
contents We present a method to train neural network controllers with guaranteed stability margins. The method is applicable to linear time-invariant plants interconnected with uncertainties and nonlinearities that are described by integral quadratic constraints. The type of stability margin we consider is the disk margin. Our training method alternates between a training step to maximize reward and a stability margin-enforcing step. In the stability margin enforcing-step, we solve a semidefinite program to project the controller into the set of controllers for which we can certify the desired disk margin.
format Preprint
id arxiv_https___arxiv_org_abs_2409_09184
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stability Margins of Neural Network Controllers
Junnarkar, Neelay
Arcak, Murat
Seiler, Peter
Systems and Control
We present a method to train neural network controllers with guaranteed stability margins. The method is applicable to linear time-invariant plants interconnected with uncertainties and nonlinearities that are described by integral quadratic constraints. The type of stability margin we consider is the disk margin. Our training method alternates between a training step to maximize reward and a stability margin-enforcing step. In the stability margin enforcing-step, we solve a semidefinite program to project the controller into the set of controllers for which we can certify the desired disk margin.
title Stability Margins of Neural Network Controllers
topic Systems and Control
url https://arxiv.org/abs/2409.09184