Chapter 6: Multivariate Filters Flashcards
Kalman Filter Algorithm - 3 Steps
1) Initialization (one-time)
2) Predict (repeatedly)
3) Update (repeatedly)
Initialization
- Initialize the state of the filter
2. Initialize our belief in the state
Prediction
- Use the process model/dynamical model to estimate the state at the next time step
- Adjust your belief to adjust for uncertainty in position
Update
- Obtain a measurement and associated belief about it’s accuracy
- Compute residual between estimated state and measurement
- Compute scaling factor based on whether the measurement or prediction is more accurate
- Set state between the prediction and measurement based on scaling factor
- Update belief in state based on how certain we are in measurement
Multivariate Gaussians use ___ for the mean and — ——— for the covariances
Multivariate Gaussians use vectors for the mean and a matrix for the covariances
The multivariate Kalman filter needs to use ______ _______ to perform ___ ___________
The multivariate Kalman filter needs to use linear algebra to perform the estimations
x
state mean vector
P
state covariance matrix
F
state transition function. When multiplied by x in the predict step, it computes the prior.
Q
process covariance matrix
B
control-input model
u
control vector
H
= observation model = measurement function
z
measurement mean vector
R
measurement covariance matrix