Representation of practical nonsmooth control Lyapunov functions by piecewise affine functions and neural networks

Titelangaben

Grüne, Lars ; Sperl, Mario ; Chatterjee, Debasish:
Representation of practical nonsmooth control Lyapunov functions by piecewise affine functions and neural networks.
In: Systems & Control Letters. Bd. 202 (2025) . - 106103.
ISSN 1872-7956
DOI der Verlagsversion: https://doi.org/10.1016/j.sysconle.2025.106103

Volltext

	Format: PDF Name: 1-s2.0-S0167691125000854-main.pdf Version: Veröffentlichte Version Verfügbar mit der Lizenz Creative Commons BY 4.0: Namensnennung
	Download (1MB)

Abstract

In this paper we give conditions under which control Lyapunov functions exist that can be represented by either piecewise affine functions or by neural networks with a suitable number of ReLU layers. The results provide a theoretical foundation for recent computational approaches for computing control Lyapunov functions with optimization-based and machine-learning techniques.