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. Reproducible regression suite — pass-rate baseline available on request.

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

Worst-case certified |u| envelope across the AEB operational design domain as a function of closing velocity. The orange curve is the analytical certified bound at each closing-velocity slice, computed over the full (d, v_ego) ODD. Blue dots are 5,055 closing-case input boxes from the Zonotropic AEB regression suite, every one of which sits at or under the curve by construction.

Solid orange: the certified worst-case |u| envelope across the AEB operational design domain, computed analytically at each closing-velocity slice over the full (d, v_ego) input space. Dashed line: the physical safe envelope. Blue dots: 5,055 closing-case input boxes (v_rel > 0) from the Zonotropic AEB regression suite — a subset of the 10,000-case evidence-pack run, all of which passed certification. Every regression scenario sits at or under the analytical envelope by construction.

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 % 10,000-case Zonotropic AEB evidence-pack run
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