Chapter 6: Multivariate Filters Flashcards

1
Q

Kalman Filter Algorithm - 3 Steps

A

1) Initialization (one-time)
2) Predict (repeatedly)
3) Update (repeatedly)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Initialization

A
  1. Initialize the state of the filter

2. Initialize our belief in the state

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Prediction

A
  1. Use the process model/dynamical model to estimate the state at the next time step
  2. Adjust your belief to adjust for uncertainty in position
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Update

A
  1. Obtain a measurement and associated belief about it’s accuracy
  2. Compute residual between estimated state and measurement
  3. Compute scaling factor based on whether the measurement or prediction is more accurate
  4. Set state between the prediction and measurement based on scaling factor
  5. Update belief in state based on how certain we are in measurement
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Multivariate Gaussians use ___ for the mean and — ——— for the covariances

A

Multivariate Gaussians use vectors for the mean and a matrix for the covariances

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

The multivariate Kalman filter needs to use ______ _______ to perform ___ ___________

A

The multivariate Kalman filter needs to use linear algebra to perform the estimations

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

x

A

state mean vector

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

P

A

state covariance matrix

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

F

A

state transition function. When multiplied by x in the predict step, it computes the prior.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Q

A

process covariance matrix

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

B

A

control-input model

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

u

A

control vector

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

H

A

= observation model = measurement function

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

z

A

measurement mean vector

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

R

A

measurement covariance matrix

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

y

A

residual

17
Q

K

A

Kalman gain

18
Q

hidden variables

A

variables that aren’t measured directly but can dramatically improve the state estimate since they can be inferred from and have a strong correlation to observed variables.

19
Q

observed variables

A

variables that are measured directly

20
Q

Despite all the fancy math, Kalman filters, in essence, are really only ___________.

A

multiplying and adding gaussians

21
Q

The way that we represent the number 1 in multiple dimensions

A

I, the identity matrix

22
Q

Ratio of how much prediction vs measurement we use

A

K, Kalman gain

23
Q

A function to convert from the state space into the measurement space

A

measurement function

24
Q

S

A

system uncertainty/innovation covariance