DetectionShortfallScenario
Robotics scenarios · Implementation: mlsysim/engine/scenario_definitions/robotics/supervision.py.
Construct this scenario with keyword inputs. The fields below show the types and defaults declared by this class.
site.machine at speed with a stop sized for a group detected in reference of frames, met by groups detected less often; misses allowed in every frame with probability all_miss_probability, frames independent.
Notes
Equation: Camera frame period is reciprocal frame rate; DetectionShortfallModel converts independent miss streaks into stopping delay and exposure.
Assumptions: The supplied group detection rates are per-frame probabilities and frame misses are independent.
Excludes: Correlated detection failures, fitted group error rates, and a physical safety guarantee.
References
Derivation: the scenario composes mlsysim.solvers.DetectionShortfallModel. Their contracts supply the underlying equations; property equations show the remaining unit conversions and accounting.
Examples
>>> from mlsysim import Scenarios
>>> scenario = Scenarios.WarehouseGroupDetectionShortfall
>>> value = scenario.frame_period
>>> str(value.units)
'ms'Attributes
| Name | Description |
|---|---|
| all_miss_probability | |
| frame_period | Camera frame interval in milliseconds, reciprocal of its registered frame rate. |
| groups | |
| reference | |
| result | Stopping and exposure result from DetectionShortfallModel.solve using the site’s |
| site | |
| speed |
site
Type: Any.
Declared default: required.
speed
Type: Quantity.
Declared default: required.
all_miss_probability
Type: float.
Declared default: required.
reference
Type: float.
Declared default: required.
groups
Type: Tuple[float, ...].
Declared default: required.
frame_period
engine.scenario_types.DetectionShortfallScenario.frame_period
Camera frame interval in milliseconds, reciprocal of its registered frame rate.
Equation: (1 / site.machine.nav_camera.frame_rate).to('ms').
result
engine.scenario_types.DetectionShortfallScenario.result
Stopping and exposure result from DetectionShortfallModel.solve using the site’s delay and brake budget.
Equation: DetectionShortfallModel().solve(speed, frame_period, s.a_brake, s.machine.loaded_mass, all_miss_probability, reference, groups, delay=s.tau_delay).