Information about Kalman Filter

The Kalman filter is an efficient recursive filter that estimates the state of a dynamic system from a series of incomplete and noisy measurements. It was developed by Rudolf Kalman.

Example applications

An example application would be providing accurate continuously-updated information about the position and velocity of an object given only a sequence of observations about its position, each of which includes some error. It is used in a wide range of engineering applications from radar to computer vision. Kalman filtering is an important topic in control theory and control systems engineering.

For example, in a radar application, where one is interested in tracking a target, information about the location, speed, and acceleration of the target is measured with a great deal of corruption by noise at any time instant. The Kalman filter exploits the dynamics of the target, which govern its time evolution, to remove the effects of the noise and get a good estimate of the location of the target at the present time (filtering), at a future time (prediction), or at a time in the past (interpolation or smoothing).

Naming and historical development

The filter is named after Rudolf E. Kalman, though Thorvald Nicolai Thiele^[1] and Peter Swerling actually developed a similar algorithm earlier. Stanley F. Schmidt is generally credited with developing the first implementation of a Kalman filter. It was during a visit of Kalman to the NASA Ames Research Center that he saw the applicability of his ideas to the problem of trajectory estimation for the Apollo program, leading to its incorporation in the Apollo navigation computer. The filter was developed in papers by Swerling (1958), Kalman (1960), and Kalman and Bucy (1961).

In control theory, the Kalman filter is most commonly referred to as linear quadratic estimation (LQE).

A wide variety of Kalman filters have now been developed, from Kalman's original formulation, now called the simple Kalman filter, to Schmidt's extended filter, the information filter and a variety of square-root filters developed by Bierman, Thornton and many others. Perhaps the most commonly used type of Kalman filter is the phase-locked loop now ubiquitous in radios, computers, and nearly any other type of video or communications equipment.

Underlying dynamic system model

Kalman filters are based on linear dynamical systems discretised in the time domain. They are modelled on a Markov chain built on linear operators perturbed by Gaussian noise. The state of the system is represented as a vector of real numbers. At each discrete time increment, a linear operator is applied to the state to generate the new state, with some noise mixed in, and optionally some information from the controls on the system if they are known. Then, another linear operator mixed with more noise generates the visible outputs from the hidden state. The Kalman filter may be regarded as analogous to the hidden Markov model, with the key difference that the hidden state variables are continuous (as opposed to being discrete in the hidden Markov model). Additionally, the hidden Markov model can represent an arbitrary distribution for the next value of the state variables, in contrast to the Gaussian noise model that is used for the Kalman filter. There is a strong duality between the equations of the Kalman Filter and those of the hidden Markov model. A review of this and other models is given in Roweis and Ghahramani (1999).

In order to use the Kalman filter to estimate the internal state of a process given only a sequence of noisy observations, one must model the process in accordance with the framework of the Kalman filter. This means specifying the matrices F_k, H_k, Q_k, R_k, and sometimes B_k for each time-step k as described below.



The Kalman filter model assumes the true state at time k is evolved from the state at (k − 1) according to

where

• F_k is the state transition model which is applied to the previous state x_k−1;
• B_k is the control-input model which is applied to the control vector u_k;
• w_k is the process noise which is assumed to be drawn from a zero mean multivariate normal distribution with covariance Q_k.

At time k an observation (or measurement) z_k of the true state x_k is made according to

where H_k is the observation model which maps the true state space into the observed space and v_k is the observation noise which is assumed to be zero mean Gaussian white noise with covariance R_k.

The initial state, and the noise vectors at each step {x₀, w₁, ..., w_k, v₁ ... v_k} are all assumed to be mutually independent.

Many real dynamical systems do not exactly fit this model; however, because the Kalman filter is designed to operate in the presence of noise, an approximate fit is often good enough for the filter to be very useful. Variations on the Kalman filter described below allow richer and more sophisticated models.

The Kalman filter

The Kalman filter is a recursive estimator. This means that only the estimated state from the previous time step and the current measurement are needed to compute the estimate for the current state. In contrast to batch estimation techniques, no history of observations and/or estimates is required. It is unusual in being purely a time domain filter; most filters (for example, a low-pass filter) are formulated in the frequency domain and then transformed back to the time domain for implementation.

The state of the filter is represented by two variables:

• , the estimate of the state at time k;
• , the error covariance matrix (a measure of the estimated accuracy of the state estimate).

The Kalman filter has two distinct phases: Predict and Update. The predict phase uses the state estimate from the previous timestep to produce an estimate of the state at the current timestep. In the update phase, measurement information at the current timestep is used to refine this prediction to arrive at a new, (hopefully) more accurate state estimate, again for the current timestep.

The notation represents the estimate of at time n given observations up to, and including time m.

Predict

Predicted state
Predicted estimate covariance

Update

Innovation or measurement residual
Innovation (or residual) covariance
Optimal Kalman gain
Updated state estimate
Updated estimate covariance

The formula for the updated estimate covariance above is only valid for the optimal Kalman gain. Usage of other gain values require a more complex formula found in the derivations section.

Invariants

If the model is accurate, and the values for and accurately reflect the distribution of the initial state values, then the following invariants are preserved: all estimates have mean error zero

• 
• 

where is the expected value of , and covariance matrices accurately reflect the covariance of estimates

• 
• 
• 

Example

Consider a truck on perfectly frictionless, infinitely long straight rails. Initially the truck is stationary at position 0, but it is buffeted this way and that by random acceleration. We measure the position of the truck every Δt seconds, but these measurements are imprecise; we want to maintain a model of where the truck is and what its velocity is. We show here how we derive the model from which we create our Kalman filter.

There are no controls on the truck, so we ignore B_k and u_k. Since F, H, R and Q are constant, their time indices are dropped.

The position and velocity of the truck is described by the linear state space

where is the velocity, that is, the derivative of position with respect to time.

We assume that between the (k − 1)^th and k^th timestep the truck undergoes a constant acceleration of a_k that is normally distributed, with mean 0 and standard deviation σ_a. From Newton's laws of motion we conclude that

where

and

We find that

(since σ_a is a scalar).

At each time step, a noisy measurement of the true position of the truck is made. Let us suppose the noise is also normally distributed, with mean 0 and standard deviation σ_z.

where

and

We know the initial starting state of the truck with perfect precision, so we initialize

and to tell the filter that we know the exact position, we give it a zero covariance matrix:

If the initial position and velocity are not known perfectly the covariance matrix should be initialized with a suitably large number, say B, on its diagonal.

The filter will then prefer the information from the first measurements over the information already in the model.

Derivations

Deriving the posterior estimate covariance matrix

Starting with our invariant on the error covariance P_k|k as above

substitute in the definition of

and substitute

and

and by collecting the error vectors we get

Since the measurement error v_k is uncorrelated with the other terms, this becomes

by the properties of vector covariance this becomes

which, using our invariant on P_k|k-1 and the definition of R_k becomes

This formula is valid no matter what the value of K_k. It turns out that if K_k is the optimal Kalman gain, this can be simplified further as shown below.

Kalman gain derivation

The Kalman filter is a minimum mean-square error estimator. The error in the posterior state estimation is

We seek to minimize the expected value of the square of the magnitude of this vector, . This is equivalent to minimizing the trace of the posterior estimate covariance matrix P_k|k. By expanding out the terms in the equation above and collecting, we get:

The trace is minimized when the matrix derivative is zero:

Solving this for K_k yields the Kalman gain:

This gain, which is known as the optimal Kalman gain, is the one that yields MMSE estimates when used.

Simplification of the posterior error covariance formula

The formula used to calculate the posterior error covariance can be simplified when the Kalman gain equals the optimal value derived above. Multiplying both sides of our Kalman gain formula on the right by S_kK_k^T, it follows that

Referring back to our expanded formula for the posterior error covariance,

we find the last two terms cancel out, giving

This formula is computationally cheaper and thus nearly always used in practice, but is only correct for the optimal gain. If arithmetic precision is unusually low causing problems with numerical stability, or if a non-optimal Kalman gain is deliberately used, this simplification cannot be applied; the posterior error covariance formula as derived above must be used.

Relationship to the digital filter

The Kalman filter can be regarded as an adaptive low-pass infinite impulse response digital filter, with cut-off frequency depending on the ratio between the process- and measurement (or observation) noise, as well as the estimate covariance. Frequency response is, however, rarely of interest when designing state estimators such as the Kalman Filter, whereas for digital filters such as IIR and FIR filters, frequency response is usually of primary concern. For the Kalman Filter, the important goal is how accurate the filter is, and this is most often decided based on empirical Monte Carlo simulations, where "truth" (the true state) is known.

Relationship to recursive Bayesian estimation

The true state is assumed to be an unobserved Markov process, and the measurements are the observed states of a hidden Markov model.

Hidden Markov model

Because of the Markov assumption, the true state is conditionally independent of all earlier states given the immediately previous state.

Similarly the measurement at the k-th timestep is dependent only upon the current state and is conditionally independent of all other states given the current state.

Using these assumptions the probability distribution over all states of the hidden Markov model can be written simply as:

However, when the Kalman filter is used to estimate the state x, the probability distribution of interest is that associated with the current states conditioned on the measurements up to the current timestep. (This is achieved by marginalizing out the previous states and dividing by the probability of the measurement set.)

This leads to the predict and update steps of the Kalman filter written probabilistically. The probability distribution associated with the predicted state is product of the probability distribution associated with the transition from the (k − 1)th timestep to the kth and the probability distribution associated with the previous state, with the true state at (k − 1) integrated out.

The measurement set up to time t is

The probability distribution of updated is proportional to the product of the measurement likelihood and the predicted state.

The denominator

is a normalization term.

The remaining probability density functions are

Note that the PDF at the previous timestep is inductively assumed to be the estimated state and covariance. This is justified because, as an optimal estimator, the Kalman filter makes best use of the measurements, therefore the PDF for given the measurements is the Kalman filter estimate.

Information filter

In the information filter, or inverse covariance filter, the estimated covariance and estimated state are replaced by the information matrix and information vector respectively. These are defined as:

Similarly the predicted covariance and state have equivalent information forms, defined as:

as have the measurement covariance and measurement vector, which are defined as:

The information update now becomes a trivial sum.

The main advantage of the information filter is that N measurements can be filtered at each timestep simply by summing their information matrices and vectors.

To predict the information filter the information matrix and vector can be converted back to their state space equivalents, or alternatively the information space prediction can be used.

Note that if F and Q are time invariant these values can be cached. Note also that F and Q need to be invertible.

Non-linear filters

The basic Kalman filter is limited to a linear assumption. However, most non-trivial systems are non-linear. The non-linearity can be associated either with the process model or with the observation model or with both.

Extended Kalman filter

In extended Kalman filter (EKF) the state transition and observation models need not be linear functions of the state but may instead be (differentiable) functions.

The function f can be used to compute the predicted state from the previous estimate and similarly the function h can be used to compute the predicted measurement from the predicted state. However, f and h cannot be applied to the covariance directly. Instead a matrix of partial derivatives (the Jacobian) is computed.

At each timestep the Jacobian is evaluated with current predicted states. These matrices can be used in the Kalman filter equations. This process essentially linearizes the non-linear function around the current estimate.

This results in the following extended Kalman filter equations:

Predict

Update

Where the state transition and observation matrices are defined to be the following Jacobians

Criticism of the EKF

Unlike its linear counterpart, the EKF is not an optimal estimator. In addition, if the initial estimate of the state is wrong, or if the process is modeled incorrectly, the filter may quickly diverge, owing to its linearisation. Another problem with the EKF is that the estimated covariance matrix tends to underestimate the true covariance matrix and therefore risks becoming inconsistent in the statistical sense without the addition of "stabilising noise".

Having stated this, the EKF can give reasonable performance, and is arguably the de facto standard in navigation systems and GPS.

Unscented Kalman filter

When the state transition and observation models – that is, the predict and update functions and (see above) – are highly non-linear, the extended Kalman filter can give particularly poor performance [citation/evidence needed]. This is because only the mean is propagated through the non-linearity. The unscented Kalman filter (UKF) [JU97] uses a deterministic sampling technique known as the unscented transform to pick a minimal set of sample points (called sigma points) around the mean. These sigma points are then propagated through the non-linear functions and the covariance of the estimate is then recovered. The result is a filter which more accurately captures the true mean and covariance. (This can be verified using Monte Carlo sampling or through a Taylor series expansion of the posterior statistics.) In addition, this technique removes the requirement to analytically calculate Jacobians, which for complex functions can be a difficult task in itself.

Predict

As with the EKF, the UKF prediction can be used independently from the UKF update, in combination with a linear (or indeed EKF) update, or vice versa.

The estimated state and covariance are augmented with the mean and covariance of the process noise.

A set of 2L+1 sigma points is derived from the augmented state and covariance where L is the dimension of the augmented state.

The sigma points are propagated through the transition function f.

The weighted sigma points are recombined to produce the predicted state and covariance.

Where the weights for the state and covariance are given by:

Typical values for , , and are , 2 and 0 respectively. (These values should suffice for most purposes.)

Update

The predicted state and covariance are augmented as before, except now with the mean and covariance of the measurement noise.

As before, a set of 2L + 1 sigma points is derived from the augmented state and covariance where L is the dimension of the augmented state.

Alternatively if the UKF prediction has been used the sigma points themselves can be augmented along the following lines

where

The sigma points are projected through the observation function h.

The weighted sigma points are recombined to produce the predicted measurement and predicted measurement covariance.

The state-measurement cross-covariance matrix,

is used to compute the UKF Kalman gain.

As with the Kalman filter, the updated state is the predicted state plus the innovation weighted by the Kalman gain,

And the updated covariance is the predicted covariance, minus the predicted measurement covariance, weighted by the Kalman gain.

Kalman-Bucy filter

The Kalman Bucy filter is a continuous time version of the Kalman filter.^{[2] [3]}

Applications

• Batteries State of Charge(SoC) Estimation http://dx.doi.org/10.1016/j.jpowsour.2007.04.011http://dx.doi.org/10.1016/j.enconman.2007.05.017
• Autopilot
• Dynamic positioning
• Economics, in particular macroeconomics, time series, and econometrics
• Inertial guidance system
• Radar tracker
• Satellite navigation systems
• Simultaneous localization and mapping
• Chaotic Signals
• Weather Forecasting
• Speech Enhancement

See also

• Ensemble Kalman filter
• Fast Kalman filter
• Compare with: Wiener filter, and the multimodal Particle filter estimator.
• Separation principle
• Zakai equation
• Recursive least squares
• Data assimilation
• Stochastic differential equations

References

General

• Gelb A., editor. Applied optimal estimation. MIT Press, 1974.
• Kalman, R. E. "A New Approach to Linear Filtering and Prediction Problems," Transactions of the ASME - Journal of Basic Engineering Vol. 82: pp. 35-45 (1960).
• Kalman, R. E., Bucy R. S., "New Results in Linear Filtering and Prediction Theory", Transactions of the ASME - Journal of Basic Engineering Vol. 83: pp. 95-107 (1961).
• [JU97] Julier, Simon J. and Jeffery K. Uhlmann. "A New Extension of the Kalman Filter to nonlinear Systems." In The Proceedings of AeroSense: The 11th International Symposium on Aerospace/Defense Sensing, Simulation and Controls, Multi Sensor Fusion, Tracking and Resource Management II, SPIE, 1997.
• Harvey, A.C. Forecasting, Structural Time Series Models and the Kalman Filter. Cambridge University Press, Cambridge, 1989.
• Roweis, S, and Z Ghahramani. "A Unifying Review of Linear Gaussian Models." Neural Computation Vol 11 No 2 (1999).
• Simon, D. Optimal state estimation: Kalman, H-infinity, and nonlinear approaches. John Wiley & Sons, 2006. (Book web site at http://academic.csuohio.edu/simond/estimation/)
• Stengel, R. F., Optimal Control and Estimation Dover, 1994.
• Bierman, Gerald J., Factorization Methods for Discrete Sequential Estimation. Dover Publications, 1977
• Bozic, S. M., Digital and Kalman Filtering. Edward Arnald Publications, 1979 (1st edition), 1994 (2nd edition)
• Amir Vasebi, Maral Partovibakhsha and S. Mohammad Taghi Bathaee, A novel combined battery model for state-of-charge estimation in lead-acid batteries based on extended Kalman filter for hybrid electric vehicle applications doi:10.1016/j.jpowsour.2007.04.011.
• A. Vasebi, S.M.T. Bathaeea and M. Partovibakhsh, Predicting state of charge of lead-acid batteries for hybrid electric vehicles by extended Kalman filter doi:10.1016/j.enconman.2007.05.017.

Notes

1. ^ Steffen L. Lauritzen, Thiele: Pioneer in Statistics, Oxford University Press, 2002. ISBN 0-19-850972-3.
2. ^ Bucy, R.S. and Joseph, P.D., Filtering for Stochastic Processes with Applications to Guidance, John Wiley & Sons, 1968; 2nd Edition, AMS Chelsea Publ., 2005. ISBN 0821837826
3. ^ Jazwinski, Andrew H., Stochastic processes and filtering theory, Academic Press, New York, 1970. ISBN 0123815509

External links

• An Introduction to the Kalman Filter, SIGGRAPH 2001 Course, Greg Welch and Gary Bishop
• Kalman filtering chapter from Stochastic Models, Estimation, and Control, vol. 1, by Peter S. Maybeck
• Kalman Filter webpage, with lots of links
• Kalman Filtering
• Kalman Filters, thorough introduction to several types, together with applications to Robot Localization
• Kalman filters used in Weather models, SIAM News, Volume 36, Number 8, October 2003.
• Critical Evaluation of Extended Kalman Filtering and Moving-Horizon Estimation, Ind. Eng. Chem. Res., 44 (8), 2451 -2460, 2005.
• Example of Estimation Techniques used in Industry: Moving Horizon Estimation for Polymer Reactors

Infinite impulse response (IIR) is a property of signal processing systems. Systems with that property are known as IIR systems or when dealing with electronic filter systems as IIR filters.
..... Click the link for more information.

dynamical system concept is a mathematical formalization for any fixed "rule" which describes the time dependence of a point's position in its ambient space. Examples include the mathematical models that describe the swinging of a clock pendulum, the flow of water in a pipe, and
..... Click the link for more information.

NOiSE is a one volume manga created by Tsutomu Nihei as a prequel to his acclaimed ten-volume work, Blame!.

It offers some rather sketchy information concerning the Megastructure's origins and initial size, as well as the origins of Silicon life.
..... Click the link for more information.

Measurement is the estimation of the magnitude of some attribute of an object, such as its length or weight, relative to a unit of measuremnt. Measurement usually involves using a measuring instrument, such as a ruler or scale, which is calibrated to compare the object to some
..... Click the link for more information.

Rudolf Emil Kálmán (born May 19 1930 in Budapest, Hungary) is an American-Hungarian mathematical system theorist, who is an electrical engineer by training. He is most famous for his co-invention of the Kalman filter, a mathematical technique widely used in control systems and
..... Click the link for more information.

coordinate system is a system for assigning an n-tuple of numbers or scalars to each point in an n-dimensional space. "Scalars" in many cases means real numbers, but, depending on context, can mean complex numbers or elements of some other commutative ring.
..... Click the link for more information.

velocity is defined as the rate of change of position. It is a vector physical quantity, both speed and direction are required to define it. In the SI (metric) system, it is measured in meters per second (m/s). The scalar absolute value (magnitude) of velocity is speed.
..... Click the link for more information.

Radar is a system that uses electromagnetic waves to identify the range, altitude, direction, or speed of both moving and fixed objects such as aircraft, ships, motor vehicles, weather formations, and terrain.
..... Click the link for more information.

Computer vision is the science and technology of machines that see.

As a scientific discipline, computer vision is concerned with the theory and technology for building artificial systems that obtain information from images.
..... Click the link for more information.

For control theory in psychology and sociology, see .

Control theory is an interdisciplinary branch of engineering and mathematics, that deals with the behavior of dynamical systems. The desired output of a system is called the reference.
..... Click the link for more information.

In military aviation, a Control system is frequently used in place of a Ground Control Station when describing an Unmanned Aircraft System control element which may be located anywhere, not just on the ground.
..... Click the link for more information.

Radar is a system that uses electromagnetic waves to identify the range, altitude, direction, or speed of both moving and fixed objects such as aircraft, ships, motor vehicles, weather formations, and terrain.
..... Click the link for more information.

A radar tracker is a component of a radar system that aggregates individual radar observations into tracks. It is particularly useful when the radar system is reporting data from several different targets.
..... Click the link for more information.

Rudolf Emil Kálmán (born May 19 1930 in Budapest, Hungary) is an American-Hungarian mathematical system theorist, who is an electrical engineer by training. He is most famous for his co-invention of the Kalman filter, a mathematical technique widely used in control systems and
..... Click the link for more information.

Thorvald Nicolai Thiele (December 24 1838 – September 26 1910) was a Danish astronomer, actuary, and mathematician, most notable for his work in statistics, interpolation, and the three-body problem.
..... Click the link for more information.

Peter Swerling was perhaps the most influential radar theoretician in the second half of the 20th century. He is best known for the class of statistically "fluctuating target" scattering models he developed at the RAND Corporation in the early 1950s to characterize the performance
..... Click the link for more information.

Stanley F. Schmidt was born in Hollister, Calif., on January 21,1926. He received the B.E.E. degree from Marquette University in 1946, and M.S. and Ph.D. degrees in electrical engineering from Stanford University in 1952 and 1959, respectively.
..... Click the link for more information.

NASA Ames Research Center (ARC) is a NASA facility located at Moffett Federal Airfield, which covers 43 acres at the borders of the cities of Mountain View and Sunnyvale in California. This research center is most commonly called NASA Ames.
..... Click the link for more information.

Apollo program was a human spaceflight program undertaken by NASA during the years 1961 – 1975 with the goal of conducting manned moon landing missions. John F. Kennedy announced this goal in 1961, and it was accomplished on July 20 1969 by Neil Armstrong and Buzz Aldrin
..... Click the link for more information.

For control theory in psychology and sociology, see .

Control theory is an interdisciplinary branch of engineering and mathematics, that deals with the behavior of dynamical systems. The desired output of a system is called the reference.
..... Click the link for more information.

A phase-locked loop or phase lock loop (PLL) is an electronic control system that generates a signal that has a fixed relation to the phase of a "reference" signal. A phase-locked loop circuit responds to both the frequency and the phase of the input signals, automatically
..... Click the link for more information.

In a linear dynamical system, the variation of a state vector (an -dimensional vector denoted ) equals a constant matrix (denoted ) multiplied by . This variation can take two forms: either as a flow, in which varies continuously with time

..... Click the link for more information.

This article or section may be confusing or unclear for some readers.
Please [improve the article] or discuss this issue on the talk page. This article has been tagged since September 2007.
..... Click the link for more information.

In mathematics, a linear map (also called a linear transformation or linear operator) is a function between two vector spaces that preserves the operations of vector addition and scalar multiplication.
..... Click the link for more information.

normal distribution, also called the Gaussian distribution, is an important family of continuous probability distributions, applicable in many fields. Each member of the family may be defined by two parameters, location and scale: the mean ("average",
..... Click the link for more information.

In science, and especially in physics and telecommunication, noise is fluctuations in and the addition of external factors to the stream of target information (signal) being received at a detector.
..... Click the link for more information.

In control engineering, a state space representation is a mathematical model of a physical system as a set of input, output and state variables related by first-order differential equations.
..... Click the link for more information.

In mathematics, a vector space (or linear space) is a collection of objects (called vectors) that, informally speaking, may be scaled and added. More formally, a vector space is a set on which two operations, called (vector) addition and (scalar) multiplication, are
..... Click the link for more information.

In mathematics, the real numbers may be described informally as numbers that can be given by an infinite decimal representation, such as 2.4871773339…. The real numbers include both rational numbers, such as 42 and −23/129, and irrational numbers, such as π and
..... Click the link for more information.

Discrete time is non-continuous time. Sampling at non-continuous times results in discrete-time samples. For example, a newspaper may report the price of crude oil once every 24 hours.
..... Click the link for more information.