bayes filters pieter abbeel uc berkeley eecs
DESCRIPTION
Bayes Filters Pieter Abbeel UC Berkeley EECS Many slides adapted from Thrun , Burgard and Fox, Probabilistic Robotics. TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.: A A A A A A A A A A A A A. Actions. Often the world is dynamic since - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/1.jpg)
Bayes Filters
Pieter AbbeelUC Berkeley EECS
Many slides adapted from Thrun, Burgard and Fox, Probabilistic Robotics
![Page 2: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/2.jpg)
2
Actions Often the world is dynamic since
actions carried out by the robot, actions carried out by other agents, or just the time passing by
change the world.
How can we incorporate such actions?
![Page 3: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/3.jpg)
3
Typical Actions The robot turns its wheels to move The robot uses its manipulator to grasp
an object Plants grow over time…
Actions are never carried out with absolute certainty.
In contrast to measurements, actions generally increase the uncertainty.
![Page 4: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/4.jpg)
4
Modeling Actions To incorporate the outcome of an action u into
the current “belief”, we use the conditional pdf
P(x|u,x’)
This term specifies the pdf that executing u changes the state from x’ to x.
![Page 5: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/5.jpg)
5
Example: Closing the door
![Page 6: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/6.jpg)
6
State TransitionsP(x|u,x’) for u = “close door”:
If the door is open, the action “close door” succeeds in 90% of all cases.
open closed0.1 10.9
0
![Page 7: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/7.jpg)
7
Integrating the Outcome of Actions
')'()',|()|( dxxPxuxPuxP
)'()',|()|( xPxuxPuxP
Continuous case:
Discrete case:
![Page 8: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/8.jpg)
8
Example: The Resulting Belief
![Page 9: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/9.jpg)
Bayes rule
Measurements
![Page 10: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/10.jpg)
10
Bayes Filters: Framework Given:
Stream of observations z and action data u:
Sensor model P(z|x). Action model P(x|u,x’). Prior probability of the system state P(x).
Wanted: Estimate of the state X of a dynamical system. The posterior of the state is also called Belief:
),,,|()( 11 tttt zuzuxPxBel
},,,{ 11 ttt zuzud
![Page 11: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/11.jpg)
11
Markov Assumption
Underlying Assumptions Static world Independent noise Perfect model, no approximation errors
![Page 12: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/12.jpg)
12111 )(),|()|( ttttttt dxxBelxuxPxzP
Bayes Filters
),,,|(),,,,|( 1111 ttttt uzuxPuzuxzP Bayes
z = observationu = actionx = state
),,,|()( 11 tttt zuzuxPxBel
Markov ),,,|()|( 11 tttt uzuxPxzP
Markov11111 ),,,|(),|()|( tttttttt dxuzuxPxuxPxzP
1111
111
),,,|(
),,,,|()|(
ttt
ttttt
dxuzuxP
xuzuxPxzP
Total prob.
Markov111111 ),,,|(),|()|( tttttttt dxzzuxPxuxPxzP
![Page 13: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/13.jpg)
Bayes Filter Algorithm 1. Algorithm Bayes_filter( Bel(x),d ):2. 03. If d is a perceptual data item z then4. For all x do5. 6. 7. For all x do8. 9. Else if d is an action data item u then10. For all x do11. 12. Return Bel’(x)
)()|()(' xBelxzPxBel
)(' xBel
)(')(' 1 xBelxBel
')'()',|()(' dxxBelxuxPxBel
111 )(),|()|()( tttttttt dxxBelxuxPxzPxBel
![Page 14: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/14.jpg)
Example Applications Robot localization:
Observations are range readings (continuous) States are positions on a map (continuous)
Speech recognition HMMs: Observations are acoustic signals (continuous valued) States are specific positions in specific words (so, tens
of thousands)
Machine translation HMMs: Observations are words (tens of thousands) States are translation options
![Page 15: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/15.jpg)
16
Summary Bayes rule allows us to compute probabilities that
are hard to assess otherwise. Under the Markov assumption, recursive Bayesian
updating can be used to efficiently combine evidence.
Bayes filters are a probabilistic tool for estimating the state of dynamic systems.
![Page 16: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/16.jpg)
Example: Robot Localization
t=0Sensor model: never more than 1 mistake
Know the heading (North, East, South or West)Motion model: may not execute action with small prob.
10Prob
Example from Michael Pfeiffer
![Page 17: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/17.jpg)
Example: Robot Localization
t=1Lighter grey: was possible to get the reading, but less likely
b/c required 1 mistake
10Prob
![Page 18: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/18.jpg)
Example: Robot Localization
t=2
10Prob
![Page 19: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/19.jpg)
Example: Robot Localization
t=3
10Prob
![Page 20: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/20.jpg)
Example: Robot Localization
t=4
10Prob
![Page 21: Bayes Filters Pieter Abbeel UC Berkeley EECS](https://reader035.vdocuments.net/reader035/viewer/2022062410/568160ef550346895dd0279f/html5/thumbnails/21.jpg)
Example: Robot Localization
t=5
10Prob