Probabilistic performance validation of deep learning-based robust NMPC controllers

TL;DR

This paper introduces a probabilistic validation method for deep learning-based robust nonlinear model predictive controllers, enabling reliable performance assessment under uncertainty for fast systems and embedded hardware.

Contribution

It proposes a novel probabilistic validation technique using finite families and constraint backoff to evaluate deep learning controllers' performance under uncertainty.

Findings

Validation method successfully applied to uncertain nonlinear system simulations.

Approach provides statistically valid performance guarantees.

Enables deployment of deep learning controllers in real-time, resource-constrained environments.

Abstract

Solving nonlinear model predictive control problems in real time is still an important challenge despite of recent advances in computing hardware, optimization algorithms and tailored implementations. This challenge is even greater when uncertainty is present due to disturbances, unknown parameters or measurement and estimation errors. To enable the application of advanced control schemes to fast systems and on low-cost embedded hardware, we propose to approximate a robust nonlinear model controller using deep learning and to verify its quality using probabilistic validation techniques. We propose a probabilistic validation technique based on finite families, combined with the idea of generalized maximum and constraint backoff to enable statistically valid conclusions related to general performance indicators. The potential of the proposed approach is demonstrated with simulation results of an uncertain nonlinear system.