Graphical Models for Mobile Robot Localization

19
Graphical Models for Mobile Robot Localization Shuang Wu

description

Graphical Models for Mobile Robot Localization. Shuang Wu. Global Localization. In an occupancy map, estimate the pose of the robot X = . (0,0). occupied. free. θ. The inputs. Laser readings z t = {r 1 ,r 2 … r 180 } Odometer reading a t = {d,theta} - PowerPoint PPT Presentation

Transcript of Graphical Models for Mobile Robot Localization

Page 1: Graphical Models for Mobile Robot Localization

Graphical Models for Mobile Robot Localization

Shuang Wu

Page 2: Graphical Models for Mobile Robot Localization

Global Localization In an occupancy map, estimate the

pose of the robot X = <x,y,θ>

(0,0)

θ

occupied

free

Page 3: Graphical Models for Mobile Robot Localization

The inputs Laser readings zt = {r1,r2…r180} Odometer reading at = {d,theta} Prior sample set, Bel(X0) = <Xi,wi>, n

possible pose

Page 4: Graphical Models for Mobile Robot Localization

Could use Bayes Filter

)|()( ...0 ttt dXPXBel

1 1 0 1 0

1 0

( | , , ,... ) ( | , ,..., )( )

( | ,... )t t t t t t t

tt t

P z X a z z P X a z zBel X

P z a z

0.. 1 0( , ,..., )t t td a z z

1 0( ) ( | ) ( | , ,..., )t t t t t tBel X P z X P X a z z predictionupdate

1 1 1 1 0 1( ) ( | ) ( | , ) ( | , ... )t t t t t t t t t tBel X p z X p X X a p X a z z dX 1 1 1 1( ) ( | ) ( | , ) ( )t t t t t t t tBel X p z X p X X a Bel X dX

Page 5: Graphical Models for Mobile Robot Localization

Recursive Bayes Filter

sensor model

action modelnormalizing constant

)(),|()|()( '11

'1

ntt

ntttt

nt XBelaXXPXzPCXBel

Page 6: Graphical Models for Mobile Robot Localization

New Positions:Generate X’ according to P(X’|X,a)

<x,y,θ>todometer reading <x’,y’,θ’>t

+1

at = (1, 45˚) p(X’|X,a) ~ X’ + N(0,Σd) + N(0, Σθ)

)cos(*a x x’ )sin(*a y y’

Page 7: Graphical Models for Mobile Robot Localization

Sensor model weight w’ by p(z|X’)

zt = (1, 1.41,…,3)

w,<x’,y’,θ’>t+1 p(z|X’)*w, <x’,y’,θ’>t+1

p(z|X’) = N(d,Σs), where Σs is the measure of noise in the laser readings d is the distance to the closest obstacle

p(z|X’) =

180

1

)'|(r

r Xzp

Page 8: Graphical Models for Mobile Robot Localization

Sampling

Likelihood weighted sampling

Samples are drawn from the target distribution

Importance Sampling

Samples are drawn from a proposal distribution(g)

Re-weight samples to account for the difference between the proposal and target distribution

proposaltarget

Key: represent belief states by set of weighted samples

( )( )

( )

f xp x

g x

g 0, f 0

Page 9: Graphical Models for Mobile Robot Localization

Resampling

Reason: Waste of CPU time if we keep propagating particles that have 0 weight.

Goal: Minimize variance of the importance weights

Page 10: Graphical Models for Mobile Robot Localization

Rao-Blackwell Theorem Particle Filters approximate any distribution

independent of size of state space. The complexity of the standard PF algorithm is O(N).

Motivation: In very high-dimensional spaces, a large number of particles is needed to represent the posterior Solution: Reduce size of state space by marginalizing out some

of the variables.

]]|[[]|[[)( LRVarLRVarRVar ]]|[[)( LRVarRVar

Page 11: Graphical Models for Mobile Robot Localization

Rao-Blackwellised

Step1. Divide the set of variables into sets R and L where R = set of sampled variables and L = remaining variables in the DBN at time t. Choice of RB variables: nodes that have no parents in the current

time slice or have parents that are already in R. Keep growing R until the remaining variables can be updated exactly.

Step2. Sample the set of variables Rt from Rt-1 using standard PF Step3. Compute the remain variables analytically.

Page 12: Graphical Models for Mobile Robot Localization

RBPF Now the particle set is represented by

) , | ( ) , | ( ) , | (1 :1 1 :1 1 1 1 :1

1

: 1

it t t t

it t

X

it tz X P X X P z X P

t

t

),|(),|(),|( 1:11:1111:1

1

:1

itttt

itt

X

itt zYPYYPzYP

t

t

Prediction:

Update:

),|()|(),|( :11:1:1:1itttt

Yt

ittt zYPYzPzYP

),|()|(),|( :11:1:1:1itttt

Xt

ittt zXPXzPzXP

Proposal distribution:)|()|()|( 1:11:11:1:1 t

itttt

it zPPzq

),|()|(),|()|()|(),|( 1:11:11:11:1:11:1 ttttY

Yttttt

X

Xttttttt zYPYzPzXPXzPzPzzPw

tt

Importance weights

),|(),,|(, :1:1:1:1:1ittt

ittt

it zYPzXP

Page 13: Graphical Models for Mobile Robot Localization

Implementation

Implementation Summary: • Used Rao-Blackwellised particle filtering to solve localization problem. • Able to localize within about 4cm (using a 20 x 20 x 10 resolution grid). • Implementation is written in Java. • Takes 16 seconds on my 2.4 GHz 512MB Windows XP machine for data set 1 (not counting loading data and ray tracing pre-computations). • Ray tracing takes 8 seconds, plus 14 seconds for pre-computing grid ranges.

Page 14: Graphical Models for Mobile Robot Localization

Results(Implemented in Java)

Page 15: Graphical Models for Mobile Robot Localization

Step 110

Page 16: Graphical Models for Mobile Robot Localization

Step 565

Page 17: Graphical Models for Mobile Robot Localization

Step 580

Page 18: Graphical Models for Mobile Robot Localization

End of Forward Run

Page 19: Graphical Models for Mobile Robot Localization

The End