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

Key points

• 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.1
• We prove that any feasible filtered input satisfies the true CBF condition whenever a safety-representative candidate is retained.1
• 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.1
• 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.1

Sources (1)

• [1]LBA-CBF: Rapidly Adaptive Safety Filters via Parallel Dynamics Inference
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 05:51 PM

  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.

  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.

Extractive summary: sentences quoted from the sources.