# Эксперимент: Measurement-Robust Neural Safety Shield (#983)

{
  "worked": false,
  "confidence": 9,
  "verdict": "Built a reproducible measurement-robust CBF action layer with box-grid uncertainty sampling and a fast 2-D projection solver. Locally, dense-box worst-case barrier residuals were approximately zero for certified radii 0, 0.05, and 0.10, while correction increased monotonically from 0.507 to 1.019 as uncertainty grew, with fitted slope 1.67. However, nominal and robust CBF both had zero collision rate even when actual error exceeded the certified radius, so the promised beyond-certification transition was not observed; the mechanism therefore does not qualify as confirmed in this toy.",
  "metrics": {
    "baseline": "Unfiltered policy: collision rate 1.00 and unsafe-step rate about 0.100 for actual errors 0.00-0.35. Nominal CBF: collision rate 0.00 and unsafe-step rate 0.000.",
    "idea": "Robust grid CBF: collision rate 0.00 and unsafe-step rate 0.000 for actual errors 0.00, 0.06, 0.12, 0.18, 0.25, and 0.35; mean action deviation at certified error 0.12 was about 0.173. Dense-box residuals for certified errors 0, 0.05, 0.10, 0.20, and 0.30 were 0.0, approximately 0.0, approximately 0.0, -0.0072, and -0.0365."
  },
  "how_to_run": "/home/maxwelhelp/main/bin/python3 robust_shield_experiment.py",
  "files": [
    "robust_shield_experiment.py",
    "results.json",
    "run_output.txt"
  ],
  "limitations": "This was a small single-integrator toy, not PPO or a double-integrator RL environment. No neural-network training, differentiable backpropagation, FLOP comparison, or GPU experiment was performed. The rollout used finite uncertainty sampling and did not force failures immediately beyond the certified radius."
}