Policy Library CBF: Finite-Horizon Safety at Runtime via Parallel Rollouts

TL;DR

This paper introduces PL-CBF, a runtime safety filter using parallel rollouts of fallback policies to ensure finite-horizon safety in autonomous systems, with theoretical guarantees and real-time performance.

Contribution

It proposes a novel safety filtering method that evaluates multiple fallback policies in parallel to improve safety coverage in autonomous control.

Findings

Enhanced safety coverage over single-policy filters.

Achieved millisecond-level runtime in simulations.

Validated on diverse dynamic systems including vehicles and quadrotors.

Abstract

Safety-critical autonomy in unstructured environments poses significant challenges for online safety certification under evolving constraints. We propose Policy Library Control Barrier Function~(PL-CBF), a runtime safety filter that evaluates a library of fallback policies via parallel finite-horizon rollouts, selects the least invasive safe mode, and enforces safety by solving a quadratic program that minimally modifies a nominal policy. We provide a theoretical analysis based on a finite-horizon language metric over closed-loop behaviors, characterizing policy-library coverage requirements for certifying finite-horizon safety. Simulations on a planar double-integrator (4 states), highway driving with abrupt friction changes using a realistic nonlinear vehicle model (8 states), and 3D quadrotor navigation in crowded dynamic environments (12 states) demonstrate improved safety coverage over single-policy safety filters while retaining millisecond-level runtime.