← Back to the chapter · Next detail →

Technical detail · Kalman Filters for Sensor Fusion

Calculate a normalized innovation gate

This scalar position example makes the gate decision explicit. The normalized innovation squared (NIS) divides squared innovation by innovation variance, so the disagreement is judged against the uncertainty expected for this update.

Worked example: normalized innovation gate
predicted state: 12.0 m
predicted variance P: 0.64
measurement z: 14.0 m
measurement variance R: 0.36

innovation:
y = z - prediction = 14.0 - 12.0 = 2.0 m

innovation variance:
S = P + R = 0.64 + 0.36 = 1.00

normalized innovation squared:
NIS = y^2 / S = 4.0 / 1.00 = 4.0

decision example:
If the configured one-dimensional gate is 3.84, this measurement is outside
the gate. Quarantine it, publish the predicted state with degraded evidence,
and record the rejection reason for review.

The configured 3.84 gate is the decision rule in this example. Record the threshold, NIS and rejection reason together so a reviewer can distinguish a rejected input from a missing input.

← Back to the chapter · Next detail →