Forward Invariance in Neural Network Controlled Systems

09/16/2023

∙

by   Akash Harapanahalli, et al.

∙

0

∙

share

We present a framework based on interval analysis and monotone systems theory to certify and search for forward invariant sets in nonlinear systems with neural network controllers. The framework (i) constructs localized first-order inclusion functions for the closed-loop system using Jacobian bounds and existing neural network verification tools; (ii) builds a dynamical embedding system where its evaluation along a single trajectory directly corresponds with a nested family of hyper-rectangles provably converging to an attractive set of the original system; (iii) utilizes linear transformations to build families of nested paralleletopes with the same properties. The framework is automated in Python using our interval analysis toolbox , in conjunction with the symbolic arithmetic toolbox , demonstrated on an 8-dimensional leader-follower system.