Mobile Robotics

oregontrimmingAI and Robotics

Nov 2, 2013 (4 years and 10 days ago)

127 views

Probabilistic
Robotics

Yrd. Doç. Dr. SIRMA YAVUZ

sirma@ce.yildiz.edu.tr

Room

109

Orgazinational

Yrd. Doç. Dr. Sırma YAVUZ

2

Lecture:

Thursday 13:00


15:50


Exams: 1 Midterm (%20), 1 Final (%30)


Assignments and midterm projects (%50)



Course Meterial

Yrd. Doç. Dr. Sırma YAVUZ

3

Sebastian Thrun, Wolfram Burgard and Dieter Fox,

Probabilistic Robotics, The MIT Press, 2005.


http://www.probabilistic
-
robotics.org/




ROS
F
ramework

(Hydro)

Yrd. Doç. Dr. Sırma YAVUZ

4

ROS is an open
-
source, meta
-
operating system for your
robot. It provides the services you would expect from an
operating system, including hardware abstraction, low
-
level device control, implementation of commonly
-
used
functionality, message
-
passing between processes, and
package management. It also provides tools and libraries
for obtaining, building, writing, and running code across
multiple computers. ROS is similar in some respects to
'robot frameworks,' such as
Player
,
YARP
,
Orocos
,
CARMEN
,
Orca
,
MOOS
, and
Microsoft Robotics Studio
.


http://www.ros.org/wiki/ROS/Tutorials






Python

& C
++.



Yrd. Doç. Dr. Sırma YAVUZ

5

ROS is the Robot Operating System, originally from
Stanford and now supported by Willow Garage.


ROS has a mature Python interface and is being used
around the world by both amateur and professional
roboticists


http://python.org/



LaTeX

Yrd. Doç. Dr. Sırma YAVUZ

6

LaTeX is a high
-
quality typesetting system; it includes
features designed for the production of technical and
scientific documentation. LaTeX is the
de facto

standard
for the communication and publication of scientific
documents. LaTeX is available as
free software
.
,


http://www.latex
-
project.org/guides/



7

Yrd. Doç. Dr. Sırma YAVUZ

Olasılıksal Robotik Grubu

8

Yrd. Doç. Dr. Sırma YAVUZ

Robot Pose




2D world (floor plan)




3 DOF

:
x,y,
q

Very simple model

the difficulty is in autonomy

10

Yrd. Doç. Dr. Sırma YAVUZ

the pose is a vector
containing the x and y
coordinates of the robot
along with the orientation,
theta

Major Issues with Autonomy


Movement


Inaccuracy


Sensor


Inaccuracy


Environmental


Uncertainty

12

Robot Navigation

Fundamental problems to provide a mobile
robot with autonomous capabilities:


Where am I going


What’s the best way there?



Where have I been?



how to create an
environmental map with imperfect sensors?



Where am I?



h潷 a⁲潢潴⁣an 瑥汬⁷here
楴⁩ 潮 aa瀿




W
hat if you’re lost and don’t have a map?

M
apping

L
ocalization

R
obot SLAM

Path Planning

Mission Planning

Yrd. Doç. Dr. Sırma YAVUZ

Problem One: Localization

Given:




World map



Robot’s initial pose



Sensor updates


Find:




Robot’s pose as it moves


How do we Solve Localization?



Represent beliefs as a probability density



Markov assumption


Pose distribution at time t conditioned on:



pose dist. at time t
-
1



movement at time t
-
1



sensor readings at time t



Discretize the density by


sampling




Localization Foundation

At every time step t:


UPDATE

each sample’s new location based on movement


RESAMPLE
the pose distribution based on sensor readings



Algorithms



Markov localization (simplest)



Kalman

filters (historically most popular)



Monte Carlo localization / particle filters


Same: Sampled probability distribution



Basic update
-
resample loop

Different: Sampling techniques



Movement assumptions

Localization’s Sidekick: Globalization

Credi t to Dieter Fox for this demo

Global robot localization using sonar sensors

Thi s example shows the ability of particle filters to represent the
ambiguities occurring during global robot localization. The
ani mation shows a series of sample sets (projected into 2D)
generated during gl obal localization using the robot's ri ng of 24
sonar sensors. The samples are shown i n red and the sensor
readings are plotted in blue. Notice that the robot is drawn at
the estimated position, which is not the correct one i n the
begi nning of the experiment.






One step further: “kidnapped robot problem”



Localization without knowledge of
start location

Problem Two: Mapping

Given:





Robot



Sensors


Find:




Map of the environment


(and implicitly, the robot’s
location as it moves)

Simultaneous Localization

And Mapping (SLAM)

If we have a map:

We can localize!

If we can localize:

We can
build

a map!

Circular Error Problem

If we have a map:

We can localize!

If we can localize:

We can make a map!

NOT THAT SIMPLE!

21


Given:


The robot’s controls


Observations of nearby features


Estimate:


Map of features


Path of the robot

The SLAM Problem

A robot is exploring an
unknown, static environment.

22

Structure of the Landmark
-
based
SLAM
-
Problem

23

Representations


Grid maps or scans






[Lu & Milios, 97; Gutmann, 98: Thrun 98; Burgard, 99; Konolige & Gutmann, 00; Thrun, 00; Arras, 99; Haehnel, 01;…]



Landmark
-
based




[Leonard et al., 98; Castelanos et al., 99: Dissanayake et al., 2001; Montemerlo et al., 2002;…

24

Why is SLAM a hard problem?

SLAM
: robot path and map are both
unknown


Robot path error correlates errors in the map

25

Why is SLAM a hard problem?


In the real world, the mapping between
observations and landmarks is unknown


Picking wrong data associations can have
catastrophic consequences


Pose error correlates data associations

Robot pose

uncertainty

26

SLAM:

Simultaneous Localization and Mapping


Full SLAM:




Online SLAM:



Integrations typically done one at a time

Estimates most recent pose and map!

Estimates entire path and map!

27

Graphical Model of Online SLAM:

28

Graphical Model of Full SLAM:

29

Techniques for Generating
Consistent Maps


Scan matching


EKF SLAM


Fast
-
SLAM


Probabilistic mapping with a single map and a
posterior about poses

Mapping + Localization


Graph
-
SLAM, SEIFs

30

Scan Matching

Maximize the likelihood of the i
-
th pose and map relative
to the (i
-
1)
-
th pose and map.







Calculate the map according to “mapping with known
poses” based on the poses and observations.

robot motion

current measurement

map constructed so far

Assignment

Yrd. Doç. Dr. Sırma YAVUZ

31


Reading
:
pages 1
-

26 of the book



Writing: Summarize wha
t

you have learned using
Latex



due in next Thursday