Set-Based Value Function Characterization and Neural Approximation of Stabilization Domains for Input-Constrained Discrete-Time Systems
This work addresses a fundamental problem in control theory for nonlinear systems with input constraints, offering a computational method to estimate stabilization domains, though it appears incremental as it builds on existing set-based and neural network approaches.
The paper tackles the challenge of estimating domains of stabilization (DOS) for input-constrained discrete-time nonlinear systems by introducing a novel framework that characterizes DOS via value functions on compact sets and uses physics-informed neural networks to learn these functions, demonstrating accurate estimation and controller synthesis in numerical examples.
Analyzing nonlinear systems with stabilizable controlled invariant sets (CISs) requires accurate estimation of their domains of stabilization (DOS) together with associated stabilizing controllers. Despite extensive research, estimating DOSs for general nonlinear systems remains challenging due to fundamental theoretical and computational limitations. In this paper, we propose a novel framework for estimating DOSs for controlled input-constrained discrete-time systems. The DOS is characterized via newly introduced value functions defined on metric spaces of compact sets. We establish the fundamental properties of these value functions and derive the associated Bellman-type (Zubov-type) functional equations. Building on this characterization, we develop a physics-informed neural network (NN) framework that learns the value functions by embedding the derived functional equations directly into the training process. The proposed methodology is demonstrated through two numerical examples, illustrating its ability to accurately estimate DOSs and synthesize stabilizing controllers from the learned value functions.