Learning Controllers from Data via Approximate Nonlinearity Cancellation
Systems and Control
2022-01-26 v1 Systems and Control
Abstract
We introduce a method to deal with the data-driven control design of nonlinear systems. We derive conditions to design controllers via (approximate) nonlinearity cancellation. These conditions take the compact form of data-dependent semi-definite programs. The method returns controllers that can be certified to stabilize the system even when data are perturbed and disturbances affect the dynamics of the system during the execution of the control task, in which case an estimate of the robustly positively invariant set is provided.
Cite
@article{arxiv.2201.10232,
title = {Learning Controllers from Data via Approximate Nonlinearity Cancellation},
author = {Claudio De Persis and Monica Rotulo and Pietro Tesi},
journal= {arXiv preprint arXiv:2201.10232},
year = {2022}
}
Comments
Submitted to IEEE Transactions on Automatic Control