Beyond Persistent Excitation: Online Experiment Design for Data-Driven Modeling and Control

TL;DR

This paper introduces an online experiment design method that improves data-driven modeling and control by efficiently selecting inputs based on past data, reducing sample requirements compared to traditional methods.

Contribution

The paper proposes a novel online input selection approach that ensures desirable data matrix properties with fewer samples than classical persistency of excitation methods.

Findings

Requires fewer data samples than classical methods

Ensures desirable rank properties of data matrices

Proven to be completely sample efficient

Abstract

This paper presents a new experiment design method for data-driven modeling and control. The idea is to select inputs online (using past input/output data), leading to desirable rank properties of data Hankel matrices. In comparison to the classical persistency of excitation condition, this online approach requires less data samples and is even shown to be completely sample efficient.