Safety Filter Design for Neural Network Systems via Convex Optimization

TL;DR

This paper introduces a convex optimization-based safety filter for neural network systems that guarantees safety despite disturbances, using linear bounds and robust MPC, demonstrated on a nonlinear pendulum.

Contribution

It presents a novel safety filter combining neural network verification, linear bounds, and robust MPC for provably safe control of NN systems.

Findings

Successfully guarantees safety under disturbances

Effective on nonlinear pendulum system

Integrates NN verification with control synthesis

Abstract

With the increase in data availability, it has been widely demonstrated that neural networks (NN) can capture complex system dynamics precisely in a data-driven manner. However, the architectural complexity and nonlinearity of the NNs make it challenging to synthesize a provably safe controller. In this work, we propose a novel safety filter that relies on convex optimization to ensure safety for a NN system, subject to additive disturbances that are capable of capturing modeling errors. Our approach leverages tools from NN verification to over-approximate NN dynamics with a set of linear bounds, followed by an application of robust linear MPC to search for controllers that can guarantee robust constraint satisfaction. We demonstrate the efficacy of the proposed framework numerically on a nonlinear pendulum system.