Seven questions along the perception-to-release chain reveal where the evidence trail from your perception stack's failure modes to the safety goal is missing, without requiring ground truth.

The check walks through seven probes along the chain of an ML-based perception stack: measurement basis without ground truth, triggering conditions, monitor quality, cross-modal consistency, persistence as a validation signal, traceability, and the organizational seam between the perception and safety teams. Each answer carries an evidence weight, and the chain turns red wherever the proof is missing. The result names your largest open point and the next defensible step.
The check does not judge the safety or conformity of a system and does not replace a safety case. It surfaces open evidence points. Tool, library, and compiler qualification per ISO 26262-8 is deliberately out of scope and is flagged as a separate evidence strand. Inputs are abstract multiple choice only. No free-text field invites confidential function details.

Flat object lists drop what they have not seen before. This demo abstracts each detection up a semantic taxonomy to the most specific level it can safely justify, and cross-checks it with an independent segmentation path.

A perception stack that classifies each frame on its own is a snapshot machine with no memory. This project fuses several sensors over time into one persistent 3D driving context, where probabilistic and deterministic paths cross-check each other and static scene is separated from moving objects.

Map your organisation's AI readiness against a model-based maturity matrix. Mark what you have, set where you want to go, and get a dependency-ordered roadmap plus a personalised report.