Transcript of Slam is a State Estimation Problem. Predicted belief corrected belief.
Slam is a State Estimation
Problem
Predicted belief
corrected belief
Bayes Filter Reminder
Gaussians
Standard deviation
Covariance matrix
Gaussians in one and two dimensionsOne standard deviation
two standard deviations
Gaussians in three dimensions
Multivariate probability
Properties of Gaussians for Univariate case
Linear system
Standard deviation on output of linear system
Mean on output of linear system
For two-dimensional system:
Properties of GaussiansProperties of Gaussians for Multivariate case
From previous slide
Properties of GaussiansImportant Property of all these methods
Discrete Kalman Filters
Kalman Filter background1. Kalman Filter is a Bayes Filter2. Kalman Filter uses Gaussians3. Estimator for the linear Gaussian case4. Optimal solution for linear models and Gaussian
distributions5. Developed in late 1950’s6. Most relevant Bayes filter variant in practice7. Applications in econcomics, weather forecasting, satellite
navigations, GPS, robotics, robot vision and many other8. Kalman filter is just few matrix operations such as
multiplication.
Discrete Kalman Filter
Components of a Kalman Filter
Example of Kalman Filter Updates in one dimension
Kalman Filter calculates a weighted mean value!
Kalman Filter Updates in 1D: PREDICTION
Single dimension
Matrices in multi-dimensions
Again generalization to many dimensions here
Kalman Filter Updates in 1D: CORRECTION
Variant single variable Generalization:
Variant of multiple variables
matrix
Kalman Filter Updates
Linear Gaussian Systems
Linear Gaussian Systems: Initialization
• Initial belief has a normal distribution:
Linear Gaussian Systems: Dynamics
Gaussian
Linear Gaussian Systems: DynamicsFrom previous slide
Linear, gaussian
Linear Gaussian Systems: Observations
R = correction
Linear Gaussian Systems: Observations
Properties: Marginalization and Conditioning
Notation for Gaussians
All are Gaussian
Kalman Filter assumes linearity
Zero-mean Gaussian Noise
Linear Motion Model
We want to calculate this probability variable
We want to calculate this probability variable
Theorem 1
We want to calculate this probability variable
We want to calculate this probability variable
Theorem 2
Everything stays Gaussian: the belief is Gaussian!
• Proofs of these theorems and properties are not trivial and can be found in the book by ‘three Germans” called Probabilistic Robotics.
Theorem 3
Kalman Filter
Algorithm
The Kalman Filter Assumptions are:1. Gaussian distributions2. Gaussian noise3. Linear motion4. Linear observation model
Discuss later
Calculates multi-dimensional mean and covariance matrix
Prediction phase
Correction phase
R for motion
Q for measurement
Prediction of multi-dimensional mean
Prediction of multi-dimensional covariance matrix
Calculates corrected multi-dimensional mean and covariance matrix
Kalman
Kalman Filter Algorithm
Different notation to previous slide
Measurement noise
Kalman Filter Algorithm: navigation using odometry and measurement to landmark
Predicted and corrected position of the ship
The Prediction-Correction-Cycle
The phase of Prediction
The Prediction-Correction-Cycle
The phase of Correction
The Prediction-Correction-Cycle
The general Optimal State
EstimationProblem
Diagram of general State Estimation
123
2 or 3 !
Discrete Kalman Filter
This is what we discussed
Linear-Optimal State Estimation
Compare with this
Change with timederivative
Linear-Optimal State Estimation (Kalman-Bucy Filter)
Similar to before
Kalman
Estimation Gain for the Kalman-Bucy Filter
• Same equations as those that define control gain, except– solution matrix, P, propagated forward in time– Matrices and matrix sequences are different