Parameter Filter-based Event-triggered Learning

TL;DR

This paper introduces an event-triggered learning method that combines statistical tests with parameter filters to efficiently update models only when significant changes are detected, improving control system reliability.

Contribution

It presents a novel approach that integrates parameter filters with statistical tests to trigger model updates only when necessary, ensuring guaranteed improvement.

Findings

Effective detection of parameter changes in simulations

Reduced unnecessary model updates

Maintained control performance with fewer updates

Abstract

Model-based algorithms are deeply rooted in modern control and systems theory. However, they usually come with a critical assumption - access to an accurate model of the system. In practice, models are far from perfect. Even precisely tuned estimates of unknown parameters will deteriorate over time. Therefore, it is essential to detect the change to avoid suboptimal or even dangerous behavior of a control system. We propose to combine statistical tests with dedicated parameter filters that track unknown system parameters from state data. These filters yield point estimates of the unknown parameters and, further, an inherent notion of uncertainty. When the point estimate leaves the confidence region, we trigger active learning experiments. We update models only after enforcing a sufficiently small uncertainty in the filter. Thus, models are only updated when necessary and statistically significant while ensuring guaranteed improvement, which we call event-triggered learning. We validate the proposed method in numerical simulations of a DC motor in combination with model predictive control.