Learning Minimum-Energy Controls from Heterogeneous Data
This work addresses control design for linear systems using data, which is incremental as it builds on existing data-driven control methods.
The paper tackles the problem of learning minimum-energy controls for linear systems from heterogeneous datasets with varying time horizons and initial conditions, deriving closed-form data-driven expressions for these controls and analyzing their properties, including noise effects and convergence to optimal inputs.
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.