RoadExposureScenario
Statistics scenarios · Implementation: mlsysim/engine/scenario_definitions/statistics.py.
Construct this scenario with keyword inputs. The fields below show the types and defaults declared by this class.
Miles-to-demonstrate requirements per event class (zero failures, precision, improvement), in millions of miles at human benchmark rates per 100 million miles, against one dated fleet_miles total (millions) at one-sided confidence.
Notes
Equation: Zero-failure exposure inverts the constant-rate zero-event probability; the other requirements are supplied reference values.
Assumptions: Supplied event rates and exposure-requirement tables share the stated million-mile conventions.
Excludes: Re-estimation of precision/improvement tables, fleet-domain comparability, and an autonomous-driving safety claim.
References
Derivation: Zero-failure exposure inverts the constant-rate zero-event probability; the other requirements are supplied reference values. Individual property contracts identify the exact accounting expression or reusable calculation. Registry entries supply the scenario inputs; this class does not turn them into measured outcomes.
Examples
Evaluate a named scenario using its declared inputs.
>>> from mlsysim import Scenarios
>>> scenario = Scenarios.RoadMilesToDemonstrate
>>> round(float(scenario.cleared[0]), 4)
3.9Attributes
| Name | Description |
|---|---|
| cleared | Supplied exposure requirements in millions of miles that are below the fleet’s reported |
| confidence | |
| fleet_miles | |
| improvement | |
| precision | |
| rates | |
| zero_failure |
Methods
| Name | Description |
|---|---|
| precision_over_fleet | Dimensionless precision exposure requirement divided by fleet exposure for event. |
| recomputed_zero_failure | Required failure-free exposure in millions of miles from -log(1-confidence) divided by |
| requirements | Supplied zero-failure, precision, and improvement exposure requirements for event, |
| shortfall | Dimensionless zero-failure exposure requirement divided by the reported fleet exposure |
precision_over_fleet
engine.scenario_types.RoadExposureScenario.precision_over_fleet(event)Dimensionless precision exposure requirement divided by fleet exposure for event.
Equation: precision[event] / fleet_miles.
recomputed_zero_failure
engine.scenario_types.RoadExposureScenario.recomputed_zero_failure(event)Required failure-free exposure in millions of miles from -log(1-confidence) divided by the event rate.
-ln(1 - C) / rate, in millions of miles: RAND’s row (1) re-derived.
Equation: -_math.log(1.0 - confidence) / (rates[event] / 100.0).
requirements
engine.scenario_types.RoadExposureScenario.requirements(event)Supplied zero-failure, precision, and improvement exposure requirements for event, each in millions of miles.
RAND’s three rows for one event class: zero failures, precision, improvement (millions).
Equation: tuple((float(t[event]) for t in (zero_failure, precision, improvement))).
shortfall
engine.scenario_types.RoadExposureScenario.shortfall(event)Dimensionless zero-failure exposure requirement divided by the reported fleet exposure for event.
Equation: zero_failure[event] / fleet_miles.
rates
Type: Dict[str, float].
Declared default: required.
zero_failure
Type: Dict[str, float].
Declared default: required.
precision
Type: Dict[str, float].
Declared default: required.
improvement
Type: Dict[str, float].
Declared default: required.
fleet_miles
Type: float.
Declared default: required.
confidence
Type: float.
Declared default: required.
cleared
engine.scenario_types.RoadExposureScenario.cleared
Supplied exposure requirements in millions of miles that are below the fleet’s reported total.
Requirements, of every event class and question, the fleet total exceeds.
Equation: Select supplied requirements r for which r<fleet_miles; returned values retain million-mile units.