unscented particle filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xxy...
TRANSCRIPT
![Page 1: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/1.jpg)
The Unscented Particle Filter
Rudolph van der Merwe (OGI)
Nando de Freitas (UC Berkeley)
Arnaud Doucet (Cambridge University)
Eric Wan(OGI)
![Page 2: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/2.jpg)
Outline
l Optimal Estimation & Filtering
l Optimal Recursive Bayesian Solution
l Practical Solutions
w Gaussian approximations (EKF, UKF)
w Sequential Monte Carlo methods (Particle Filters)
l The Unscented Particle Filter
w The Unscented Transformation and UKF
w Applications of UT/UKF to Particle Filters
l Experimental Results
l Conclusions
![Page 3: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/3.jpg)
Filtering
l General problem statement
w Filtering is the problem of sequentially estimating the states (parameters or hidden variables) of a system as a set of observations become available on-line.
kx1k −x2k −x
2k −y 1k −y ky
1( | )k kp −x x
( | )k kp y x
Unobserved
Observed
![Page 4: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/4.jpg)
Filtering
l Solution of sequential estimation problem given by
w Posterior density :
w By recursively computing a marginal of the posterior, the filtering density,
one need not keep track of the complete history of the states.
( | )k kp X Y
1 2
1 2
{ , , , }
{ , , , }k k
k k
==
X x x x
Y y y y
LL
( | )k kp x Y
![Page 5: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/5.jpg)
Filtering
l Given the filtering density, a number of estimates of the system state can be calculated:
w Mean (optimal MMSE estimate of state)
w Mode
w Median
w Confidence intervals
w Kurtosis, etc.
[ ]ˆ | ( | )k k k k k k kE x p d= = ∫x Y x x Y x
![Page 6: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/6.jpg)
State Space Formulation of System
l General discrete-time nonlinear, non-Gaussian dynamic system
w Assumptions :
1) States follow a first order Markov process
2) Observations independent given the states
1 1 1( , , )
( , , )k k k k
k k k k
− − −==
x f x u v
y h x u n
state
noisy observation measurement noise
process noise
known input
1 2 0 1( | , , , ) ( | )k k k k kp p− − −=x x x x x xL
( | , ) ( | )k k k kp A p=y x y x
![Page 7: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/7.jpg)
Recursive Bayesian Estimation
l Given this state space model, how do we recursively estimate the filtering density ?
1
1
1
1 1
1
1
1 1
1
1
1
1
( | ) ( )( )
( )
( , | ) ( )
( , )
( | , ) ( )
( | ) ( )
( )
( | )
( | )
( )
( | )
( | )
( | , )
(
( | ) ( )
(
)
)
|
k k kk k
k
k k k k
k k
k k k k
k k k
k
k k
k k
k k k
kk
k k
k
k k k
k k
k
p pp
p
p p
p
p p
p p
p
p p
p
p
p p
p
p
p
p
−
−
−
− −
−
−
−
− −
−
−
−
=
=
=
=
=
Y x
x Y Yx
Y x xx Y
Y
y Y x xy Y
y Y x xy Y Y
xy Y Y
x Yy Y
y Y x
y x
![Page 8: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/8.jpg)
Recursive Bayesian Estimation
w Prior :
(Propagation of past state into future before new observation is made.)
w Likelihood : defined in terms of observation model
w Evidence :
1
1
( | ) ( | )( )
( | )k k k k
k kk k
p pp
p−
−
=y x x Y
x Yy Y
priorlikelihood
evidenceposterior
11 1 1 1( | )( | ) ( | )k k kk k k kp p dp− − − −−= ∫x Y x Y xx x
transition density given by process model
1 1( | ) ( | ) ( | )k k k k k k kp p p d− −= ∫y Y y x x Y x
![Page 9: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/9.jpg)
Practical Solutions
l Gaussian Approximations
l Perfect Monte Carlo Simulation
l Sequential Monte Carlo Methods : “Particle Filters”
w Bayesian Importance Sampling
w Sampling-importance resampling (SIR)
![Page 10: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/10.jpg)
Gaussian Approximationsl Most common approach.l Assume all RV statistics are Gaussian.l Optimal recursive MMSE estimate is then given by
l Different implementations :
w Extended Kalman Filter (EKF) : optimal quantities approximated via first order Taylor series expansion (linearization) of process and measurement models.
w Unscented Kalman Filter (UKF) : optimal quantities calculated using the Unscented Transformation (accurate to second order for any nonlinearity). Drastic improvement over EKF [Wan, van der Merwe,Nelson 2000].
l Problem : Gaussian approximation breaks down for most nonlinear real-world applications (multi-modal distributions, non-Gaussian noise sources, etc.)
observation oprediction of predictif on ofˆ ( ) [( ) ( )]k k kkk κ= + −x yx y
![Page 11: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/11.jpg)
Perfect Monte Carlo Simulation
l Allow for a complete representation of the posterior distribution.
l Map intractable integrals of optimal Bayesian solution to tractable discrete sums of weighted samples drawn from the posterior distribution.
l So, any estimate of the form
may be approximated by :
( )( )1
1
ˆ ( | )N
ik k k kN
i
p δ=
= −∑x Y x x . . .( ) ( | )I I Dik k kp←x x Y
[ ]( ) ( ) ( | )k k k k kE f f p d= ∫x x x Y x
[ ] ( )( )1
1
( )N
ik kN
i
E f f=
≈ ∑x x
![Page 12: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/12.jpg)
Particle Filters
l Bayesian Importance Samplingw It is often impossible to sample directly from the true
posterior density.w However, we can rather sample from a known, easy-to-
sample, proposal distribution,
and make use of the following substitution
( | )k kq x Y
[ ] ( ) ( )( )
( ) ( ) ( )
( ) ( )( )
( )
|
( | )
( | )
( )
( | )
|
|( ) ( )
( ) |
( |
( )
|
)
k k
k
k k
k k
k
k k k
k
k
k
k
k
k
k
pk k k
k k k kq
wk k k k
p
k kq
p
pk
p
p
pk q
E f f d
f q d
f q
q
d
w
=
=
=
=
∫∫∫
x Y
x
Y
Y
x Y
Y x x
Y
x
x
Y
x
Y
xx x x
x x Y x
x x Y x
x
x Y
![Page 13: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/13.jpg)
[ ] ( ) ( )
( )( )( )
( )( )
( ) [ ]( ) [ ]
1
|
|
|
|
( ) ( ) ( ) |
( ) ( ) |
( ) ( ) |
( ) |
( ) ( )
( )
( | ) ( )
k
k k
k
k
k
k
k
k
p
q
k k k k k k
k k k kq
k
k k k k k k
k k k k k k
k k k k k
k k kq
k kq
E f f w q d
f w q d
f w q d
p p
w q d
E w f
E w
d
=
=
=
=
∫
∫∫∫
∫x
Y
x
x Y
Y
x
Y
Y
x x x x Y x
x x x Y x
x x x Y x
x x Y x
x x
x x
x
Y x
Particle Filters
![Page 14: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/14.jpg)
Particle Filters
w So, by drawing samples from , we can approximate expectations of interest by the following:
w Where the normalized importance weights are given by
( | )k kq x Y
[ ]( ) ( )1
1
( )11
( ) ( )
1
( ) ( )( )
( )
( ) ( )
N i ik k kN i
k N ik kN i
Ni i
k k ki
w fE f
w
w f
=
=
=
≈
≈
∑∑
∑
x xx
x
x x%
( )( )
( )
1
( )( )
( )
ii k k
k k N jk kj
ww
w=
=∑
xx
x%
![Page 15: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/15.jpg)
Particle Filters
w Using the state space assumptions (1st order Markov / observational independence given state), the importance weights can be estimated recursively by [proof in De Freitas (2000)]
w Problem with SIS is that the variance of the importance weights increase stochastically over time [Kong et al. (1994), Doucet et al. (1999)]
w To solve this, we need to resample the particles • keep / multiply particles with high importance weights• discard particles with low importance weights
w Sampling-importance Resampling (SIR)
( ) ( )( )
11
1
| |
| ,k k k k
k kk k k
p pw w
q−
−−
=y x x x
x X Y
![Page 16: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/16.jpg)
Particle Filters
l Sampling-importance Resampling w Maps the N unequally weighted particles into a new set of N
equally weighted samples.
w Method proposed by Gordon, Salmond & Smith (1993) and proven mathematically by Gordon (1994).
{ } { }( ) ( ) ( ) 1, ,i i jk k kw N −→x x%
j resampled index p(i)
cdf
1
( )jtw%
1N −
![Page 17: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/17.jpg)
Particle Filters
![Page 18: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/18.jpg)
Particle Filters
l Choice of Proposal Distribution
critical design issue for successful particle filter• samples/particles are drawn from this distribution• used to evaluate importance weights
w Requirements
1) Support of proposal distribution must include support of true posterior distribution, i.e. heavy-tailed distributions are preferable.
2) Must include most recent observations.
( ) ( )( )
11
1
| |
| ,k k k k
k kk k k
p pw w
q−
−−
=y x x x
x X Y
![Page 19: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/19.jpg)
Particle Filters
w Most popular choice of proposal distribution does not satisfy these requirements though:
[Isard and Blake 96, Kitagawa 96, Gordon et al. 93, Beadle and Djuric 97, Avitzour 95]
w Easy to implement :
w Does not incorporate most recent observation though !
( ) ( )( )
( )
11
1
1
| |
|
|
k k k kk k
k k
k k k
p pw w
p
w p
−−
−
−
=
=
y x x x
x x
y x
( ) ( )1 1| , |k k k k kq p− −=x X Y x x
![Page 20: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/20.jpg)
Improving Particle Filters
l Incorporate New Observations into Proposal
w Use Gaussian approximation (i.e. Kalman filter) to generate proposal by combining new observation with prior
( ) ( )( )
1 1| , | ,
ˆ ,cov[ ]
k k k G k k k
k k
q p− −=
=
x X Y x X Y
x xN
![Page 21: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/21.jpg)
Improving Particle Filters
l Extented Kalman Filter Proposal Generation
w De Freitas (1998), Doucet (1998), Pitt & Shephard (1999).
w Greatly improved performance compared to standard particle filter in problems with very accurate measurements, i.e. likelihood very peaked in comparison to prior.
w In highly nonlinear problems, the EKF tends to be very inaccurate and underestimates the true covariance of the state. This violates the distribution support requirement for the proposal distribution and can lead to poor performance and filter divergence.
l We propose the use of the Unscented Kalman Filterfor proposal generation to address these problems !
![Page 22: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/22.jpg)
Improving Particle Filters
l Unscented Kalman Filter Proposal Generation
w UKF is a recursive MMSE estimator based on the Unscented Transformation (UT).
w UT : Method for calculating the statistics of a RV that undergoes a nonlinear transformation (Julier and Uhlmann 1997)
w UT/UKF : - accurate to 3rd order for Gaussians- higher order errors scaled by choice of
transform parameters.
w More accurate estimates than EKF (Wan, van der Merwe, Nelson 2000)
w Have some control over higher order moments, i.e. kurtosis, etc. heavy tailed distributions !
![Page 23: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/23.jpg)
a
x
Px
c a ai x xl q = + -x x P x P
f b g
Weightedsample mean
Weightedsample
covariance
b i
b i
y
Py
y i
+-
Unscented Transformation
8
![Page 24: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/24.jpg)
mean
covariance sigmapoints
Actual (sampling) UT Linearized (EKF)
( )=y f x ( )i iψ χ= f
transformedsigma points
UTcovariance
UTmean
y f x P P= =( ) y A ATx
truemean
truecovariance f x( )A AT
xP
The Unscented Transformation
9
![Page 25: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/25.jpg)
+
Unscented Particle Filter
Particle Filter UKF Proposal
Unscented Particle Filter
![Page 26: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/26.jpg)
Experimental Results
l Synthetic Experiment
w Time-series
• process model :
• nonstationary observation model :
( )1 1 sink k kx k x vωπ φ+ = + + +
process noise (Gamma)
2 30
302k k
k
k k
k
k
x ny
x n
φφ
≤
>
+=
− +
measurement noise (Gaussian)
![Page 27: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/27.jpg)
Experimental Results
l Synthetic Experiment : (100 independent runs)
0.0060.070Unscented Particle Filter
0.0160.310Particle Filter : EKF proposal
0.0530.424Particle Filter : generic
0.0120.280Unscented Kalman Filter (UKF)
0.0150.374Extended Kalman Filter (EKF)
variancemean
MSEFilter
![Page 28: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/28.jpg)
Experimental Resultsl Synthetic Experiment
![Page 29: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/29.jpg)
Experimental Results
l Pricing Financial Optionsw Options : financial derivative that gives the holder the right
(but not obligation) to do something in the future.• Call option : - allow holder to buy an underlying cash product
- at a specified future date (“maturity time”) - for a predetermined price (“strike price”)
• Put option : - allow holder to sell an underlying cash product
w Black Scholes partial differential equation• Main industry standard for pricing options
22 21
2 2
f f frS S rf
t S Sσ
∂ ∂ ∂+ + =
∂ ∂ ∂option value
value of underlying cash product
risk-free interest ratevolatility of cash product
![Page 30: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/30.jpg)
Experimental Results
l Pricing Financial Optionsw Black & Scholes (1973) derived the following pricing solution:
1 2
2
( ) ( )
( 1) ( )
m
m
rtc c
rtc c
C S d Xe d
P S d Xe d
−
−
= −
= − − + −
N NN N
212
1
2 1
ln( / ) ( )
(.) cumulative normal distribution
m
m
m
c
S X r td
t
d d t
σσ
σ
+ +=
= −
=N
![Page 31: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/31.jpg)
Experimental Results
l Pricing Financial Optionsw State-space representation to model system for particle filters
• Hidden states :
• Output observations:
• Known control signals:
w Estimate call and put prices over a 204 day period on the FTSE-100 index.
• Performance : normalized square error for one-step-ahead predictions
, C P
, r σ
, mt S
( )ˆk kk
NSE = −∑ y y
![Page 32: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/32.jpg)
Experimental Results
l Options Pricing Experiment : (100 independent runs)
0.0000.008Unscented Particle Filter
0.0070.024Particle Filter : EKF proposal
0.0000.023Particle Filter : generic
0.0000.023Unscented Kalman Filter (UKF)Put
0.0000.023Extended Kalman Filter (EKF)
0.0000.035Trivial
0.0000.009Unscented Particle Filter
0.5080.092Particle Filter : EKF proposal
0.0000.037Particle Filter : generic
0.0000.037Unscented Kalman Filter (UKF)Call
0.0000.037Extended Kalman Filter (EKF)
0.0000.078Trivial
varmean
NSEAlgorithmOption Type
![Page 33: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/33.jpg)
Experimental Results
l Options Pricing Experiment : UPF one-step-ahead predictions
![Page 34: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/34.jpg)
Experimental Results
l Options Pricing Experiment : Estimated interest rate and volatility
![Page 35: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/35.jpg)
Experimental Results
l Options Pricing Experiment : Probability distributions of implied interest rate and volatility
![Page 36: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/36.jpg)
Particle Filter Demosl Visual Dynamics Group, Oxford. (Andrew Blake)
Tracking agile motion
Tracking motion against camouflage Mixed state tracking
![Page 37: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/37.jpg)
Conclusionsl Particle filters allow for a practical but complete representation of
posterior probability distribution.
l Applicable to general nonlinear, non-Gaussian estimation problems where standard Gaussian approximations fail.
l Particle filters rely on importance sampling, so the proper choice of proposal distribution is very important:
w Standard approach (i.e. transition prior proposal) fails when likelihood of new data is very peaked (accurate sensors) or for heavy-tailed noise sources.
w EKF proposal : Incorporates new observations, but can diverge due to inaccurate and inconsistent state estimates.
w Unscented Particle Filter : UKF proposal• More consistent and accurate state estimates.• Larger support overlap, can have heavier tailed distributions.• Theory predicts and experiments prove significantly better performance.
![Page 38: Unscented Particle Filtermotionplanning/papers/sbp_papers/...kkk pp ww q − − − = yxxx xXY Particle Filters w Most popular choice of proposal distribution does not satisfy these](https://reader035.vdocuments.net/reader035/viewer/2022070212/61022c0fdcdb457c411eaabc/html5/thumbnails/38.jpg)
The End