Author: Job van Dieten
|Please ask about problems and questions regarding this tutorial on answers.ros.org. Don't forget to include in your question the link to this page, the versions of your OS & ROS, and also add appropriate tags.|
ArUco marker detection (C++)Description: This tutorial shows how to detect fiducial markers using the ArUco library and to get its 3D pose.
Tutorial Level: BEGINNER
Next Tutorial: Person detection
This tutorial shows how to run fiducial marker detection with TIAGo using the OpenCV-based library ArUco. Fiducial markers is an example of robust model-based object detection. The ArUco markers are planar square binary markers that, provided the length of its square side, its 6 DoF pose can be estimated precisely from monocular vision.
First, make sure that the tutorials are properly installed along with the TIAGo simulation, as shown in the Tutorials Installation Section.
Open two consoles and source the catkin workspace as follows in each one:
cd ~/tiago_public_ws source ./devel/setup.bash
Now run the simulation in the first console as follows
$ roslaunch tiago_gazebo tiago_gazebo.launch public_sim:=true robot:=steel world:=tutorial_office gzpose:="-x -3.5 -y -0.85 -z 0 -R 0 -P 0 -Y -3.0"
This will spawn TIAGo in front of a board composed of multiple ArUco markers
In the second console launch the aruco detector:
$ roslaunch tiago_aruco_demo detector.launch
In the launchfile above we are telling the node to identify the marker with ID 584 (default) and that the length of the square side is 10 cm (default).
It is possible to choose the aruco tag detected by replacing <marker_ID> with wanted ID tag:
$ roslaunch tiago_aruco_demo detector.launch markerId:=<marker_ID>
An rviz window will appear with the position of the marker
If the marker is not detected, the look_to_point demo is also launched and permit to move the head around (For more information, see :http://wiki.ros.org/Robots/TIAGo/Tutorials/motions/head_action)