We propose a certainty-equivalence scheme for adaptive control of scalar linear systems subject to additive, i.i.d. Gaussian disturbances and bounded control input constraints, without requiring prior knowledge of the bounds of the system parameters, nor the control direction. Assuming that the system is at-worst marginally stable, mean square boundedness of the closed-loop system states is proven. Lastly, numerical examples are presented to illustrate our results.
@article{arxiv.2209.07040,
title = {Learning-Based Adaptive Control for Stochastic Linear Systems with Input Constraints},
author = {Seth Siriya and Jingge Zhu and Dragan Nešić and Ye Pu},
journal= {arXiv preprint arXiv:2209.07040},
year = {2023}
}
Comments
16 pages, 2 figures, accepted at IEEE Control Systems Letters