Learning Minimum-Energy Controls from Heterogeneous Data

TL;DR

This paper develops a data-driven approach to learn minimum-energy controls for linear systems using heterogeneous datasets, providing explicit formulas, data requirements, and noise robustness analysis.

Contribution

It introduces a novel data-based representation for control trajectories and derives explicit minimum-energy control formulas for various horizons, including noise correction methods.

Findings

Derived closed-form control expressions for different horizons

Established minimum data requirements for control reconstruction

Analyzed noise effects and proposed asymptotic correction methods

Abstract

In this paper we study the problem of learning minimum-energy controls for linear systems from heterogeneous data. Specifically, we consider datasets comprising input, initial and final state measurements collected using experiments with different time horizons and arbitrary initial conditions. In this setting, we first establish a general representation of input and sampled state trajectories of the system based on the available data. Then, we leverage this data-based representation to derive closed-form data-driven expressions of minimum-energy controls for a wide range of control horizons. Further, we characterize the minimum number of data required to reconstruct the minimum-energy inputs, and discuss the numerical properties of our expressions. Finally, we investigate the effect of noise on our data-driven formulas, and, in the case of noise with known second-order statistics, we provide corrected expressions that converge asymptotically to the true optimal control inputs.