Designing System Level Synthesis Controllers for Nonlinear Systems with Stability Guarantees
Lauren Conger, Syndey Vernon, Eric Mazumdar

TL;DR
This paper presents a novel system level synthesis approach for nonlinear systems that uses polynomial approximations and neural network optimization to ensure stability and improve control performance without relying on Lyapunov functions.
Contribution
It introduces a stability-guaranteed control design method for nonlinear systems using neural network-optimized system level synthesis without Lyapunov functions.
Findings
Improved control performance over feedback linearization.
Provides bounds for stability domain and control costs.
Numerical validation confirms effectiveness.
Abstract
We introduce a method for controlling systems with nonlinear dynamics and full actuation by approximating the dynamics with polynomials and applying a system level synthesis controller. We show how to optimize over this class of controllers using a neural network while maintaining stability guarantees, without requiring a Lyapunov function. We give bounds for the domain over which the use of the class of controllers preserves stability and gives bounds on the control costs incurred by optimized controllers. We then numerically validate our approach and show improved performance compared with feedback linearization -- suggesting that the SLS controllers are able to take advantage of nonlinearities in the dynamics while guaranteeing stability.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsModel Reduction and Neural Networks · Advanced Control Systems Optimization · Adaptive Control of Nonlinear Systems
