CMU CS 10708 - Kalman Filters Gaussian MNs (22 pages)

Previewing pages 1, 2, 21, 22 of 22 page document View the full content.
View Full Document

Kalman Filters Gaussian MNs



Previewing pages 1, 2, 21, 22 of actual document.

View the full content.
View Full Document
View Full Document

Kalman Filters Gaussian MNs

128 views


Pages:
22
School:
Carnegie Mellon University
Course:
Cs 10708 - Probabilistic Graphical Models
Probabilistic Graphical Models Documents
Unformatted text preview:

Readings K F 6 1 6 2 6 3 14 1 14 2 14 3 14 4 Kalman Filters Gaussian MNs Graphical Models 10708 Carlos Guestrin Carnegie Mellon University December 1st 2008 1 Multivariate Gaussian Mean vector Covariance matrix 2 Conditioning a Gaussian Joint Gaussian p X Y N Conditional linear Gaussian p Y X N Y X 2Y X 3 Gaussian is a Linear Model Conditional linear Gaussian p Y X N 0 X 2 4 Conditioning a Gaussian Joint Gaussian p X Y N Conditional linear Gaussian p Y X N Y X YY X 5 Conditional Linear Gaussian CLG general case Conditional linear Gaussian p Y X N 0 X YY X 6 Understanding a linear Gaussian Variance increases over time the 2d case motion noise adds up Object doesn t necessarily move in a straight line 7 Tracking with a Gaussian 1 p X0 N 0 0 p Xi 1 Xi N Xi Xi 1 Xi 8 Tracking with Gaussians 2 Making observations We have p Xi Detector observes Oi oi Want to compute p Xi Oi oi Use Bayes rule Require a CLG observation model p Oi Xi N W Xi v Oi Xi 9 Operations in Kalman filter X1 O1 X2 O2 X3 O3 Compute Start with At each time step t X4 O4 X5 O5 Condition on observation Prediction Multiply transition model Roll up marginalize previous time step I ll describe one implementation of KF there are others Information filter 10 Exponential family representation of Gaussian Canonical Form 11 Canonical form Standard form and canonical forms are related Conditioning is easy in canonical form Marginalization easy in standard form 12 Conditioning in canonical form First multiply Then condition on value B y 13 Operations in Kalman filter X1 O1 X2 O2 X3 O3 Compute Start with At each time step t X4 O4 X5 O5 Condition on observation Prediction Multiply transition model Roll up marginalize previous time step 14 Prediction roll up in canonical form First multiply Then marginalize Xt 15 What if observations are not CLG Often observations are not CLG CLG if Oi Xi o Consider a motion detector Oi 1 if person is likely to be in the region Posterior is not Gaussian 16 Linearization incorporating nonlinear evidence p Oi Xi not CLG but Find a Gaussian approximation of p Xi Oi p Xi p Oi Xi Instantiate evidence Oi oi and obtain a Gaussian for p Xi Oi oi Why do we hope this would be any good Locally Gaussian may be OK 17 Linearization as integration Gaussian approximation of p Xi Oi p Xi p Oi Xi Need to compute moments E Oi E Oi2 E Oi Xi Note Integral is product of a Gaussian with an arbitrary function 18 Linearization as numerical integration Product of a Gaussian with arbitrary function Effective numerical integration with Gaussian quadrature method Approximate integral as weighted sum over integration points Gaussian quadrature defines location of points and weights Exact if arbitrary function is polynomial of bounded degree Number of integration points exponential in number of dimensions d Exact monomials requires exponentially fewer points For 2d 1 points this method is equivalent to effective Unscented Kalman filter Generalizes to many more points 19 Operations in non linear Kalman filter X1 O1 X2 O2 X3 O3 Compute Start with At each time step t X4 O4 X5 O5 Condition on observation use numerical integration Prediction Multiply transition model use numerical integration Roll up marginalize previous time step 20 Canonical form Markov Nets 21 What you need to know about Gaussians Kalman Filters Gaussian MNs Kalman filter Non linear Kalman filter Usually observation or motion model not CLG Use numerical integration to find Gaussian approximation Gaussian Markov Nets Probably most used BN Assumes Gaussian distributions Equivalent to linear system Simple matrix operations for computations Sparsity in precision matrix equivalent to graph structure Continuous and discrete hybrid model Much harder but doable and interesting see book 22


View Full Document

Access the best Study Guides, Lecture Notes and Practice Exams

Loading Unlocking...
Login

Join to view Kalman Filters Gaussian MNs and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Kalman Filters Gaussian MNs and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?