Stability Margins of Neural Network Controllers

2024/09/13 by Neelay Junnarkar, Murat Arcak, Junnarkar, Neelay +3 · 1 citation
Computer Science · #FOS: Electrical engineering #Neural Networks and Applications #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2409.09184

openalex publication_date 2024/09/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Controller Design for Bilinear Neural Feedback Loops

Related

• Stability Analysis using Quadratic Constraints for Systems with Neural Network Controllers
• Synthesizing Neural Network Controllers with Closed-Loop Dissipativity Guarantees
• Data-Driven Stable Neural Feedback Loop Design
• A Guaranteed-Stable Neural Network Approach for Optimal Control of Nonlinear Systems
• Robust Stability of Neural Network-controlled Nonlinear Systems with Parametric Variability