ADAS Scenario Pack: 22 Regression Cases with Verified Verdicts
22 ADAS scenario YAMLs: active safety ×13, driving assist ×5, parking ×1, shared driving ×2, L3 admission ×1. One YAML is one regression case — tweak parameters to derive new scenarios. Catalog public; full pack sent on request.
§1 · WHAT IT ISOne YAML is one regression case
The scenario pack is a set of 22 ADAS scenario YAMLs, every verdict matching expectations. Each YAML declares a scenario (actors, trajectories, fault recipe, verdict thresholds) and drops straight into CI regression; tweak parameters to derive new scenarios — scenarios are code, not documents.
Catalog breakdown
| Category | Count | Typical scenarios |
|---|---|---|
| Active safety | ×13 | AEB car-to-car/pedestrian, FCW, blind-spot warning |
| Driving assist | ×5 | ACC following, LKA lane keeping, lane-change on demand |
| Parking | ×1 | APA perpendicular parking |
| Shared driving | ×2 | Hands-off detection, takeover requests |
| L3 admission | ×1 | Traffic-jam pilot (TJP-class) |
§2 · HOW TO GET ITCatalog public, full pack on request
The catalog is public; the full pack of 22 YAMLs is sent on request — hit the button below and mention “scenario pack” in your email.
§3 · DEEP DIVEThe methodology behind the scenarios
- How scenarios become CI regression: ADAS scenario regression testing →
- Where scenario boundaries come from: ODD, OpenSCENARIO 2.0, and sampling economics →
- Walking AEB through the V-model’s six levels: the TTC metric →
§4 · HONEST BOUNDARIESHonest boundaries
- All in-scenario figures are demo data, not measured on a real SUT; thresholds must be calibrated against your SUT baseline (a margin analysis service item).
- The pack covers skeletons of common ADAS scenarios — scenarios specific to your ODD are derived from the skeletons or written fresh.
Run it on your own scenario
A 30-minute demo: AEB regression → inject a fault → open the evidence report.
Book a 30-min demo Get the scenario pack