Reference
S. Mallick, A. Dabiri, and B. De Schutter, "Learning-based model predictive
control for piecewise affine systems with feasibility guarantees,"
Proceedings of the 2025 European Control Conference,
Thessaloniki, Greece, pp. 345-350, June 2025.
Abstract
Online model predictive control (MPC) for piecewise affine (PWA) systems
requires the online solution to an optimization problem that implicitly
optimizes over the switching sequence of PWA regions, for which the
computational burden can be prohibitive. Alternatively, the computation can be
moved offline using explicit MPC; however, the online memory requirements and
the offline computation can then become excessive. In this work we propose a
solution in between online and explicit MPC, addressing the above issues by
partially dividing the computation between online and offline. To solve the
underlying MPC problem, a policy, learned offline, specifies the sequence of
PWA regions that the dynamics must follow, thus reducing the complexity of the
remaining optimization problem that solves over only the continuous states and
control inputs. We provide a condition, verifiable during learning, that
guarantees feasibility of the learned policy's output, such that an optimal
continuous control input can always be found online. Furthermore, a method for
iteratively generating training data offline allows the feasible policy to be
learned efficiently, reducing the offline computational burden. A numerical
experiment demonstrates the effectiveness of the method compared to both online
and explicit MPC.
Publisher page
Downloads
BibTeX
@inproceedings{MalDab:25-007,
author = {Mallick, Samuel and Dabiri, Azita and De Schutter, Bart},
title = {Learning-Based Model Predictive Control for Piecewise Affine
Systems with Feasibility Guarantees},
booktitle = {Proceedings of the 2025 European Control Conference},
address = {Thessaloniki, Greece},
pages = {345--350},
month = jun,
year = {2025}
}