ReLU Barrier Functions for Nonlinear Systems with Constrained Control: A Union of Invariant Sets Approach

TL;DR

This paper introduces a novel approach using ReLU barrier functions and a union of invariant sets to certify safety in nonlinear systems with constrained inputs, improving invariant set size while maintaining computational efficiency.

Contribution

It presents a convex barrier synthesis method on PWA surrogates combined with UIS for less conservative safety certification in nonlinear systems with input saturation.

Findings

Larger certified invariant sets compared to linear-alpha designs.

Efficient convex barrier synthesis on PWA surrogates.

Successful safety certification on pendulum and cart-pole systems.

Abstract

Certifying safety for nonlinear systems with polytopic input constraints is challenging because CBF synthesis must ensure control admissibility under saturation. We propose an approximation--verification pipeline that performs convex barrier synthesis on piecewise-affine (PWA) surrogates and certifies safety for the original nonlinear system via facet-wise verification. To reduce conservatism while preserving tractability, we use a two-slope Leaky ReLU surrogate for the extended class-$\mathcal{K}$ function $\alpha(\cdot)$ and combine multiple certificates using a Union of Invariant Sets (UIS). Counterexamples are handled through local uncertainty updates. Simulations on pendulum and cart-pole systems with input saturation show larger certified invariant sets than linear-$\alpha$ designs with tractable computation time.