Scribd
Upload
23 views

Robot Mapping: A Short Introduction To The Bayes Filter and Related Models

Uploaded by

Robertsen Putra Sugianto
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
23 views

Robot Mapping: A Short Introduction To The Bayes Filter and Related Models

Uploaded by

Robertsen Putra Sugianto
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 34

Robot Mapping

A Short Introduction to the


Bayes Filter and Related Models

Gian Diego Tipaldi, Wolfram Burgard

1
State Estimation
 Estimate the state of a system given
observations and controls
 Goal:

2
Recursive Bayes Filter 1

Definition of the belief

3
Recursive Bayes Filter 2

Bayes’ rule

4
Recursive Bayes Filter 3

Markov assumption

5
Recursive Bayes Filter 4

Law of total probability

6
Recursive Bayes Filter 5

Markov assumption

7
Recursive Bayes Filter 6

Markov assumption

8
Recursive Bayes Filter 7

Recursive term 9
Prediction and Correction Step
 Bayes filter can be written as a two
step process
 Prediction step

 Correction step

10
Motion and Observation Model
 Prediction step

motion model

 Correction step

sensor or observation model


11
Different Realizations
 The Bayes filter is a framework for
recursive state estimation
 There are different realizations
 Different properties
 Linear vs. non-linear models for motion
and observation models
 Gaussian distributions only?
 Parametric vs. non-parametric filters
…

12
In this Course
 Kalman filter & friends
 Gaussians
 Linear or linearized models

 Particle filter
 Non-parametric
 Arbitrary models (sampling required)

13
Motion Model

14
Robot Motion Models
 Robot motion is inherently uncertain
 How can we model this uncertainty?

Courtesy: Thrun, Burgard, Fox 15


Probabilistic Motion Models
 Specifies a posterior probability that
action u carries the robot from x to x’.

16
Typical Motion Models
 In practice, one often finds two types
of motion models:
 Odometry-based
 Velocity-based
 Odometry-based models for systems
that are equipped with wheel encoders
 Velocity-based when no wheel
encoders are available

17
Odometry Model
 Robot moves from to .
 Odometry information

18
Probability Distribution
 Noise in odometry
 Example: Gaussian noise

19
Examples (Odometry-Based)

Courtesy: Thrun, Burgard, Fox 20


Velocity-Based Model

-90

Courtesy: Thrun, Burgard, Fox 21


Motion Equation
 Robot moves from to .
 Velocity information

22
Problem of the Velocity-Based
Model
 Robot moves on a circle
 The circle constrains the final orientation
 Fix: introduce an additional noise term on
the final orientation

23
Motion Including 3rd Parameter

Term to account for the final rotation

24
Examples (Velocity-Based)

Courtesy: Thrun, Burgard, Fox 25


Sensor Model

26
Model for Laser Scanners
 Scan z consists of K measurements.

 Individual measurements are


independent given the robot position

27
Beam-Endpoint Model

Courtesy: Thrun, Burgard, Fox 28


Beam-Endpoint Model

map likelihood field

Courtesy: N. Roy 29
Ray-cast Model
 Ray-cast model considers the first
obstacle long the line of sight
 Mixture of four models

30
Model for Perceiving Landmarks
with Range-Bearing Sensors
 Range-bearing
 Robot’s pose
 Observation of feature j at
location

31
Summary
 Bayes filter is a framework for state
estimation
 Motion and sensor model are the
central models in the Bayes filter
 Standard models for robot motion and
laser-based range sensing

32
Literature
On the Bayes filter
 Thrun et al. “Probabilistic Robotics”,
Chapter 2
 Course: Introduction to Mobile Robotics,
Chapter 5
On motion and observation models
 Thrun et al. “Probabilistic Robotics”,
Chapters 5 & 6
 Course: Introduction to Mobile Robotics,
Chapters 6 & 7
33
Slide Information
 These slides have been created by Cyrill Stachniss as part of
the robot mapping course taught in 2012/13 and 2013/14. I
created this set of slides partially extending existing material
of Edwin Olson, Pratik Agarwal, and myself.
 I tried to acknowledge all people that contributed image or
video material. In case I missed something, please let me
know. If you adapt this course material, please make sure
you keep the acknowledgements.
 Feel free to use and change the slides. If you use them, I
would appreciate an acknowledgement as well. To satisfy my
own curiosity, I appreciate a short email notice in case you
use the material in your course.
 My video recordings are available through YouTube:
http://www.youtube.com/playlist?list=PLgnQpQtFTOGQrZ4O5QzbIHgl3b1JHimN_&feature=g-list

Cyrill Stachniss, 2014


[email protected]
34

You might also like