LBA-CBF: Rapidly Adaptive Safety Filters via Parallel Dynamics Inference

2026-10-06

AI Summary

This study addresses the failure of Control Barrier Function (CBF) safety certificates caused by abrupt dynamic changes, proposing a fast adaptive safety control framework based on parallel dynamics reasoning. The method ranks candidate models using retrospective window errors combined with robust filtering, handling nonlinear unknown parameters without switching mechanisms or continuous parameter estimation while supporting an adaptive range from best-fit to full-library coverage. By integrating high-order CBFs with finite model library evaluation, simulations achieve a 100% success rate matching the oracle upper bound. Real-world experiments demonstrate that the system effectively adapts to wind disturbances and sudden payload variations, enabling real-time operation across approximately 250,000 candidate models.

Abstract

Control barrier functions (CBFs) certify commands through an assumed dynamics model, so an abrupt, unmeasured regime change can undermine the certificate exactly when safety matters most. We present Look-Back Adaptive Control Barrier Functions (LBA-CBF), which rank a finite bank of candidate dynamics by recent prediction error over a short look-back window and enforce the high-order CBF condition against every model within a tolerance of the best, spanning best-fit adaptation to full-bank robust filtering. The dynamics may depend nonlinearly on the unknown parameters, and no switching model or continuously parameterized estimator is required. We prove that any feasible filtered input satisfies the true CBF condition whenever a safety-representative candidate is retained. In quadrotor simulation with abrupt wind reversals and an unknown payload, LBA-CBF is safe and reaches the goal from all random initial conditions, matching an oracle, while adaptive and robust baselines achieve 0-88% success. Banks of up to 250,000 models run inside the control loop, and Crazyflie 2.1 and F1TENTH experiments demonstrate adaptation to wind, payload release, and varying tire-road friction. Code, videos, and project details are available at: https://lla-control.github.io

Problem

• Control Barrier Functions
• Safety Filters
• Dynamics Inference
• Adaptive Control
• Regime Change

Innovation

• Control Barrier Functions
• Parallel Dynamics Inference
• Safety Filters
• Rapid Adaptation
• Model Bank Ranking