Neural Operators for Predictor Feedback Control of Nonlinear Delay Systems
This addresses a computational limitation in delay-compensating control for nonlinear systems, offering a practical improvement for applications like robotics, though it is incremental as it builds on existing predictor feedback designs.
The paper tackles the computational bottleneck of implementing predictor feedback for nonlinear delay systems by learning the predictor mapping with a neural operator, achieving semiglobal practical stability and demonstrating significant speedups in controlling a 5-link robotic manipulator compared to classic schemes.
Predictor feedback designs are critical for delay-compensating controllers in nonlinear systems. However, these designs are limited in practical applications as predictors cannot be directly implemented, but require numerical approximation schemes, which become computationally prohibitive when system dynamics are expensive to compute. To address this challenge, we recast the predictor design as an operator learning problem, and learn the predictor mapping via a neural operator. We prove the existence of an arbitrarily accurate neural operator approximation of the predictor operator. Under the approximated predictor, we achieve semiglobal practical stability of the closed-loop nonlinear delay system. The estimate is semiglobal in a unique sense - one can enlarge the set of initial states as desired, though this increases the difficulty of training a neural operator, which appears practically in the stability estimate. Furthermore, our analysis holds for any black-box predictor satisfying the universal approximation error bound. We demonstrate the approach by controlling a 5-link robotic manipulator with different neural operator models, achieving significant speedups compared to classic predictor feedback schemes while maintaining closed-loop stability.