## page was renamed from world_modeling/Tutorials/Fusing multiple measurements originating from the same object
## page was renamed from ros.org/wiki/world_modeling/Tutorials/Fusing multiple measurements originating from the same object
## For instruction on writing tutorials
## http://www.ros.org/wiki/WritingTutorials
####################################
##FILL ME IN
####################################
## for a custom note with links:
## note =
## for the canned note of "This tutorial assumes that you have completed the previous tutorials:" just add the links 
## note.0=[[ROS/Tutorials|ROS tutorials]]
## descriptive title for the tutorial
## title = Fusing multiple measurements originating from the same object
## multi-line description to be displayed in search 
## description = One object can generate multiple measurements at one time step. This can be the result of a poor object detection, but is also common in scenarios including multiple sensors or robots. This tutorial demonstrates the world model's ability to fuse multiple measurements with the same time stamp originating from the same object.
## the next tutorial description (optional)
## next =
## links to next tutorial (optional)
## next.0.link=[[wire/Tutorials/Data association exploiting multiple object attributes|Data association exploiting multiple object attributes]]
## next.1.link=
## what level user is this tutorial for 
## level= BeginnerCategory
## keywords =
####################################

<<IncludeCSTemplate(TutorialCSHeaderTemplate)>>

<<TableOfContents(4)>>

== Goal ==

The goal of the [[wire]] meta package is fusing measurements into one consistent world state estimate. In order to achieve this goal the data association problem has to be solved. This demo shows how the data association problem is solved in a static scene where multiple measurements originate from the same object. The video shows both the detections and the estimated world state.

<<Youtube(-izVpwDZpqA&rel=0)>>

== Approach ==

All measurements are close to each other and have a relatively high measurement covariance matrix. As a result, the world modeling algorithm associates all measurements with the same object. All measurements are used to update the object position at each time step using a Kalman filter with constant velocity motion model.

== Data ==

In order to be able to reproduce the result shown in the video above, make sure that you have downloaded and compiled the [[wire]] packages:
{{{
$ git clone https://github.com/tue-robotics/wire.git
$ catkin_make
}}}

Download the bag-file containing the data ([[attachment:demo01.bag]]) and decompress the file:
{{{
$ rosbag decompress demo01.bag
}}}

The bag file contains [[tf]]s, object detections and both rgb and depth images. The images are only included for ease of interpretation and inspection. These are not used by wire.

== Reproducing the result ==

Start a ROS core:

{{{
$ roscore
}}}

Then, set the [[Clock#Using_Simulation_Time_from_the_.2BAC8-clock_Topic|use_sim_time]] parameter to true:
{{{
$ rosparam set use_sim_time true
}}}

and launch the [[wire_core]]:
{{{
$ roslaunch wire_core start.launch
}}}
In a second terminal, launch the visualization:
{{{
$ roslaunch wire_tutorials rviz_wire_kinetic.launch
}}}
Finally, play back the data:
{{{
$ rosbag play demo01.bag --clock
}}}
The results should be similar to the results shown in the video above.

## AUTOGENERATED DO NOT DELETE 
## TutorialCategory
## FILL IN THE STACK TUTORIAL CATEGORY HERE