Learning for Layered Safety-Critical Control with Predictive Control Barrier Functions

TL;DR

This paper introduces predictive control barrier functions that incorporate rollouts of the full system to enhance safety guarantees in layered control of complex systems, demonstrated on a 3D hopping robot.

Contribution

It proposes a novel predictive CBF method that bridges the gap between reduced and full models, ensuring safety with minimal conservatism.

Findings

Guarantees safety in layered control systems.

Learns predictive robustness through parallel simulation.

Successfully applied on a 3D hopping robot.

Abstract

Safety filters leveraging control barrier functions (CBFs) are highly effective for enforcing safe behavior on complex systems. It is often easier to synthesize CBFs for a Reduced order Model (RoM), and track the resulting safe behavior on the Full order Model (FoM) -- yet gaps between the RoM and FoM can result in safety violations. This paper introduces \emph{predictive CBFs} to address this gap by leveraging rollouts of the FoM to define a predictive robustness term added to the RoM CBF condition. Theoretically, we prove that this guarantees safety in a layered control implementation. Practically, we learn the predictive robustness term through massive parallel simulation with domain randomization. We demonstrate in simulation that this yields safe FoM behavior with minimal conservatism, and experimentally realize predictive CBFs on a 3D hopping robot.