Product · Safety bound generator for ML decision modules

Exact, regulator-ready safety bounds
for machine-learning decision modules.

1.0 · Description

Type-approval of learned components in safety-critical control stacks demands bounds that hold by construction, not by sampling. Zonotropic generates closed-form activation envelopes around any ML decision module, paired with a regulator-ready evidence pack on every run. The envelope is verifiable offline and runs alongside the model in production at sub-frame latency.

1.1 · Reference application

Worked example: Tier-1-class Autonomous Emergency Braking activation module. 97-test regression suite — pass-rate baseline available on request.

Fig. 1 · Certified envelope across the AEB operational design domain

Certified |u| envelope versus closing velocity, computed from 1,505 closing scenarios in the Zonotropic AEB regression suite. Upper envelope rises from near zero at low closing velocity and saturates at the physical safe envelope as closing velocity increases.

Each blue dot is one of 1,505 closing scenarios from the Zonotropic AEB regression suite, plotted as the worst-case certified braking magnitude per input box. Solid orange traces the upper envelope per 1 m/s bin; dashed orange traces the lower. All 1,505 cases passed certification.

1.2 · Evidence pack

Every run produces a regulator-ready submission bundle. Reproducible from artifacts and traceable to source data via content hashes.

1.2.1 Certificate JSONL hashed + signed · input box, output bounds, pass/fail

1.2.2 Parity plots PNG teacher vs. certified-inference output across the ODD

1.2.3 Operation count JSON per-decision cost and energy proxy vs. baseline

1.2.4 Cover document PDF auto-generated, regulator-formatted submission cover

2.0 · Specifications

2.1 Certification pass rate 100 % 97-test Zonotropic AEB regression suite

2.2 Inference latency, typ. 0.11 ms commodity x86, single thread

2.3 Latency profile deterministic — branch-free path; no SMT or branch-and-bound search

2.4 Bound construction exact — closed-form, tight

2.5 IP status pending — US provisional, filed Apr 2026

2.6 Reference application AEB — Autonomous Emergency Braking

3.0 · Roadmap

§ Application Standard Status

3.1 Automotive AEB UNECE R152 / Euro NCAP available

3.2 Industrial cobot velocity limiting ISO 10218 / TS 15066 validated

3.3 Medical robotics FDA 510(k) planned

3.4 Aerospace decision modules DO-178C / DO-254 planned

3.5 Drone collision avoidance — exploratory