�
�g�Uc @` s� d Z d d l m Z m Z m Z m Z d d l m Z d d l m Z d d l
Z d d l
m Z m
Z
m Z m Z m Z d d l m Z m Z d e f d � � YZ d S(
u4 Copyright 2015 Roger R Labbe Jr.
FilterPy library.
http://github.com/rlabbe/filterpy
Documentation at:
https://filterpy.readthedocs.org
Supporting book at:
https://github.com/rlabbe/Kalman-and-Bayesian-Filters-in-Python
This is licensed under an MIT license. See the readme.MD file
for more information.
i ( t absolute_importt divisiont print_functiont unicode_literals( t dot3( t unscented_transformN( t eyet zerost dott isscalart outer( t invt choleskyt UnscentedKalmanFilterc B` sk e Z d Z d d d d d d � Z d d d d � Z d d d d � Z d d d d � Z d d d � Z RS( u� Implements the Scaled Unscented Kalman filter (UKF) as defined by
Simon Julier in [1], using the formulation provided by Wan and Merle
in [2]. This filter scales the sigma points to avoid strong nonlinearities.
You will have to set the following attributes after constructing this
object for the filter to perform properly.
**Attributes**
x : numpy.array(dim_x)
state estimate vector
P : numpy.array(dim_x, dim_x)
covariance estimate matrix
R : numpy.array(dim_z, dim_z)
measurement noise matrix
Q : numpy.array(dim_x, dim_x)
process noise matrix
You may read the following attributes.
**Readable Attributes**
xp : numpy.array(dim_x)
predicted state (result of predict())
Pp : numpy.array(dim_x, dim_x)
predicted covariance matrix (result of predict())
**References**
.. [1] Julier, Simon J. "The scaled unscented transformation,"
American Control Converence, 2002, pp 4555-4559, vol 6.
Online copy:
https://www.cs.unc.edu/~welch/kalman/media/pdf/ACC02-IEEE1357.PDF
.. [2] E. A. Wan and R. Van der Merwe, “The unscented Kalman filter for
nonlinear estimation,” in Proc. Symp. Adaptive Syst. Signal
Process., Commun. Contr., Lake Louise, AB, Canada, Oct. 2000.
Online Copy:
https://www.seas.harvard.edu/courses/cs281/papers/unscented.pdf
c C` s[ t | � | _ t | � | _ t | � | _ t | � | _ | | _ | | _ | | _ d | d | _ | | _
| | _ | | _ | | _
| | _ | d k r� t | _ n | | _ | j j � \ | _ | _ |
d k r� t j | _ n |
| _ | d k rt j | _ n | | _ t d | j d | j f � | _ t | j | j f � | _ d S( u� Create a Kalman filter. You are responsible for setting the
various state variables to reasonable values; the defaults below will
not give you a functional filter.
**Parameters**
dim_x : int
Number of state variables for the filter. For example, if
you are tracking the position and velocity of an object in two
dimensions, dim_x would be 4.
dim_z : int
Number of of measurement inputs. For example, if the sensor
provides you with position in (x,y), dim_z would be 2.
dt : float
Time between steps in seconds.
hx : function(x)
Measurement function. Converts state vector x into a measurement
vector of shape (dim_z).
fx : function(x,dt)
function that returns the state x transformed by the
state transistion function. dt is the time step in seconds.
points : class
Class which computes the sigma points and weights for a UKF
algorithm. You can vary the UKF implementation by changing this
class. For example, MerweScaledSigmaPoints implements the alpha,
beta, kappa parameterization of Van der Merwe, and
JulierSigmaPoints implements Julier's original kappa
parameterization. See either of those for the required
signature of this class if you want to implement your own.
sqrt_fn : callable(ndarray), default = scipy.linalg.cholesky
Defines how we compute the square root of a matrix, which has
no unique answer. Cholesky is the default choice due to its
speed. Typically your alternative choice will be
scipy.linalg.sqrtm. Different choices affect how the sigma points
are arranged relative to the eigenvectors of the covariance matrix.
Usually this will not matter to you; if so the default cholesky()
yields maximal performance. As of van der Merwe's dissertation of
2004 [6] this was not a well reseached area so I have no advice
to give you.
If your method returns a triangular matrix it must be upper
triangular. Do not use numpy.linalg.cholesky - for historical
reasons it returns a lower triangular matrix. The SciPy version
does the right thing.
x_mean_fn : callable (sigma_points, weights), optional
Function that computes the mean of the provided sigma points
and weights. Use this if your state variable contains nonlinear
values such as angles which cannot be summed.
.. code-block:: Python
def state_mean(sigmas, Wm):
x = np.zeros(3)
sum_sin, sum_cos = 0., 0.
for i in range(len(sigmas)):
s = sigmas[i]
x[0] += s[0] * Wm[i]
x[1] += s[1] * Wm[i]
sum_sin += sin(s[2])*Wm[i]
sum_cos += cos(s[2])*Wm[i]
x[2] = atan2(sum_sin, sum_cos)
return x
z_mean_fn : callable (sigma_points, weights), optional
Same as x_mean_fn, except it is called for sigma points which
form the measurements after being passed through hx().
residual_x : callable (x, y), optional
residual_z : callable (x, y), optional
Function that computes the residual (difference) between x and y.
You will have to supply this if your state variable cannot support
subtraction, such as angles (359-1 degreees is 2, not 358). x and y
are state vectors, not scalars. One is for the state variable,
the other is for the measurement state.
.. code-block:: Python
def residual(a, b):
y = a[0] - b[0]
if y > np.pi:
y -= 2*np.pi
if y < -np.pi:
y = 2*np.pi
return y
**References**
.. [3] S. Julier, J. Uhlmann, and H. Durrant-Whyte. "A new method for
the nonlinear transformation of means and covariances in filters
and estimators," IEEE Transactions on Automatic Control, 45(3),
pp. 477-482 (March 2000).
.. [4] E. A. Wan and R. Van der Merwe, “The Unscented Kalman filter for
Nonlinear Estimation,” in Proc. Symp. Adaptive Syst. Signal
Process., Commun. Contr., Lake Louise, AB, Canada, Oct. 2000.
https://www.seas.harvard.edu/courses/cs281/papers/unscented.pdf
.. [5] Wan, Merle "The Unscented Kalman Filter," chapter in *Kalman
Filtering and Neural Networks*, John Wiley & Sons, Inc., 2001.
.. [6] R. Van der Merwe "Sigma-Point Kalman Filters for Probabilitic
Inference in Dynamic State-Space Models" (Doctoral dissertation)
i i N( R t Qt RR t xt Pt _dim_xt _dim_zt _dtt _num_sigmast hxt fxt points_fnt x_meant z_meant NoneR t msqrtt weightst Wmt Wct npt subtractt
residual_xt
residual_zt sigmas_ft sigmas_h( t selft dim_xt dim_zt dtR R t pointst sqrt_fnt x_mean_fnt z_mean_fnR" R# ( ( s ./filterpy/kalman/UKF.pyt __init__Q s2 v #c C` s� | d k r | j } n t | t � s3 | f } n | d k rH t } n | j j | j | j � } x7 t | j
� D]& } | j | | | | � | j | <qs W| | j | j
| j | j | j | j � \ | _ | _ d S( u} Performs the predict step of the UKF. On return, self.x and
self.P contain the predicted state (x) and covariance (P). '
Important: this MUST be called before update() is called for the first
time.
**Parameters**
dt : double, optional
If specified, the time step to be used for this prediction.
self._dt is used if this is not provided.
UT : function(sigmas, Wm, Wc, noise_cov), optional
Optional function to compute the unscented transform for the sigma
points passed through hx. Typically the default function will
work - you can use x_mean_fn and z_mean_fn to alter the behavior
of the unscented transform.
fx_args : tuple, optional, default (,)
optional arguments to be passed into fx() after the required state
variable.
N( R R t
isinstancet tupleR R t sigma_pointsR R t rangeR R R$ R R R R R" ( R& R) t UTt fx_argst sigmast i( ( s ./filterpy/kalman/UKF.pyt predict� s $c
C` s� | d k r d St | t � s+ | f } n | d k r@ t } n | d k rX | j } n" t | � rz t | j � | } n x7 t | j � D]& } | j
| j | | � | j | <q� W| | j | j
| j | | j | j � \ } } t | j | j f � } xj t | j � D]Y } | j | j | | j � } | j | j | | � }
| | j | t | |
� 7} q Wt | t | � � } | j | | � } | j t | | � | _ | j t | | | j � | _ d S( u� Update the UKF with the given measurements. On return,
self.x and self.P contain the new mean and covariance of the filter.
**Parameters**
z : numpy.array of shape (dim_z)
measurement vector
R : numpy.array((dim_z, dim_z)), optional
Measurement noise. If provided, overrides self.R for
this function call.
UT : function(sigmas, Wm, Wc, noise_cov), optional
Optional function to compute the unscented transform for the sigma
points passed through hx. Typically the default function will
work - you can use x_mean_fn and z_mean_fn to alter the behavior
of the unscented transform.
hx_args : tuple, optional, default (,)
arguments to be passed into Hx function after the required state
variable.
residual_x : function (x, x2), optional
Optional function that computes the residual (difference) between
the two state vectors. If you do not provide this, then the
built in minus operator will be used. You will normally want to use
the built in unless your residual computation is nonlinear (for
example, if they are angles)
residual_h : function (z, z2), optional
Optional function that computes the residual (difference) between
the two measurement vectors. If you do not provide this, then the
built in minus operator will be used.
N( R R/ R0 R R R R R R2 R R R$ R% R R R R# R R R" R R
R R R R t T(
R& t zR R3 t hx_argsR6 t zpt Pzt Pxzt dxt dzt Kt y( ( s ./filterpy/kalman/UKF.pyt update s, $ $0 "c C` s� y | d } Wn t | � s1 t d � � n X| j d k r| t | � s� | j d k rm t | � d k s� t d � � n- t | � | j k s� t d j | j � � � | d k r� t j } n t j | d � } | d k r� d g | } n | j
j d k rt | | j f � } n t | | j d f � } t | | j | j f � } x~ t
t | | � � D]g \ } \ } }
| j � | j | |
� | j
| | d d � f <| j | | d d � d d � f <qbW| | f S( uc Performs the UKF filter over the list of measurement in `zs`.
**Parameters**
zs : list-like
list of measurements at each time step `self._dt` Missing
measurements must be represented by 'None'.
Rs : list-like, optional
optional list of values to use for the measurement error
covariance; a value of None in any position will cause the filter
to use `self.R` for that time step.
residual : function (z, z2), optional
Optional function that computes the residual (difference) between
the two measurement vectors. If you do not provide this, then the
built in minus operator will be used. You will normally want to use
the built in unless your residual computation is nonlinear (for
example, if they are angles)
UT : function(sigmas, Wm, Wc, noise_cov), optional
Optional function to compute the unscented transform for the sigma
points passed through hx. Typically the default function will
work - you can use x_mean_fn and z_mean_fn to alter the behavior
of the unscented transform.
**Returns**
means: ndarray((n,dim_x,1))
array of the state for each time step after the update. Each entry
is an np.array. In other words `means[k,:]` is the state at step
`k`.
covariance: ndarray((n,dim_x,dim_x))
array of the covariances for each time step after the update.
In other words `covariance[k,:,:]` is the covariance at step `k`.
i u zs must be list-likei u4 zs must be a list of scalars or 1D, 1 element arraysu1 each element in zs must be a1D array of length {}N( R t AssertionErrorR t ndimt lent formatR R R! t sizeR R R t enumeratet zipR7 RB R ( R& t zst Rst residualR3 R9 t z_nt meanst covariancesR6 t r( ( s ./filterpy/kalman/UKF.pyt batch_filter^ s0 ) 0 (
&c C` s� t | � t | � k s t � | j \ } } | d k rL | j g | } n t | � rh | g | } n | d k r� | j g | } n t | | | f � } d | d } | j � | j � } }
t | | f � } x�t | d d d � D]�} | j
j | | |
| � }
x2 t | � D]$ } | j |
| | | � | | <q Wt
| j | � } d } | | } x@ t | � D]2 } | | | } | | j | t | | � 7} qsW| | | 7} d } xR t | � D]D } |
| | | } | | | } | | j | t | | � 7} q�Wt
| t | � � } | | c t
| | | d | � 7<|
| c t | |
| d | | j � 7<| | | <q� W| |
| f S( uU Runs the Rauch-Tung-Striebal Kalman smoother on a set of
means and covariances computed by the UKF. The usual input
would come from the output of `batch_filter()`.
**Parameters**
Xs : numpy.array
array of the means (state variable x) of the output of a Kalman
filter.
Ps : numpy.array
array of the covariances of the output of a kalman filter.
Qs: list-like collection of numpy.array, optional
Process noise of the Kalman filter at each time step. Optional,
if not provided the filter's self.Q will be used
dt : optional, float or array-like of float
If provided, specifies the time step of each step of the filter.
If float, then the same time step is used for all steps. If
an array, then each element k contains the time at step k.
Units are seconds.
**Returns**
x : numpy.ndarray
smoothed means
P : numpy.ndarray
smoothed state covariances
K : numpy.ndarray
smoother gain at each step
**Example**
.. code-block:: Python
zs = [t + random.randn()*4 for t in range (40)]
(mu, cov, _, _) = kalman.batch_filter(zs)
(x, P, K) = rts_smoother(mu, cov, fk.F, fk.Q)
i i i����i N( RE RC t shapeR R R R R t copyR2 R R1 R R R R
R R R8 ( R& t Xst Pst QsR) t nR' t Kst
num_sigmast xst psR$ t kR5 R6 t xbt PbR RA t PxbR9 R@ ( ( s ./filterpy/kalman/UKF.pyt rts_smoother� sB . "
""%+N( ( ( t __name__t
__module__t __doc__R R. R7 RB RQ R` ( ( ( s ./filterpy/kalman/UKF.pyR
s 4 �+EP( Rc t
__future__R R R R t filterpy.commonR t filterpy.kalmanR t numpyR R R R R R
t scipy.linalgR R t objectR
( ( ( s ./filterpy/kalman/UKF.pyt <module> s " (