Data-Driven Stable Neural Feedback Loop Design

TL;DR

This paper introduces a data-driven method for designing neural network controllers with guaranteed stability for linear plants, integrating stability constraints into training via SDPs and demonstrating effectiveness through numerical examples.

Contribution

It presents a novel data-driven framework that incorporates stability guarantees into neural network controller design for unknown linear plant dynamics.

Findings

The method guarantees stability of neural feedback loops.

Numerical examples show improved performance over model-based approaches.

The approach effectively integrates stability constraints into neural network training.

Abstract

This paper proposes a data-driven approach to design a feedforward Neural Network (NN) controller with a stability guarantee for plants with unknown dynamics. We first introduce data-driven representations of stability conditions for Neural Feedback Loops (NFLs) with linear plants, which can be formulated into a semidefinite program (SDP). Subsequently, this SDP constraint is integrated into the NN training process to ensure stability of the feedback loop. The whole NN controller design problem can be solved by an iterative algorithm. Finally, we illustrate the effectiveness of the proposed method compared to model-based methods via numerical examples.