Contraction metrics are crucial in control theory because they provide a
powerful framework for analyzing stability, robustezza, and convergence of
various dynamical systems. Tuttavia, identifying these metrics for complex
nonlinear systems remains an open challenge due to the lack of scalable and
effective tools. This paper explores the approach of learning verifiable
contraction metrics parametrized as neural networks (NNs) for discrete-time
nonlinear dynamical systems. While prior works on formal verification of
contraction metrics for general nonlinear systems have focused on convex
optimization methods (e.g. linear matrix inequalities, etc) under the
assumption of continuously differentiable dynamics, the growing prevalence of
NN-based controllers, often utilizing ReLU activations, introduces challenges
due to the non-smooth nature of the resulting closed-loop dynamics. To bridge
this gap, we establish a new sufficient condition for establishing formal
neural contraction metrics for general discrete-time nonlinear systems assuming
only the continuity of the dynamics. We show that from a computational
perspective, our sufficient condition can be efficiently verified using the
state-of-the-art neural network verifier $\alpha,\!\beta$-CROWN, which scales
up non-convex neural network verification via novel integration of symbolic
linear bound propagation and branch-and-bound. Built upon our analysis tool, Noi
further develop a learning method for synthesizing neural contraction metrics
from sampled data. Finalmente, our approach is validated through the successful
synthesis and verification of NN contraction metrics for various nonlinear
examples.

Questo articolo esplora i giri e le loro implicazioni.

Scarica PDF: