Aruco detection and Real life VS Gazebo

asked 2015-09-07 09:57:11 -0600

End-Effector gravatar image

Hello everyone,

I'm a student working with a Aruco Package(https://github.com/Sahloul/ar_sys). I'm using it with ROS and I have 2 questions:

1) Why are the Aruco giving more error when the Aruco is straight to the camera? When the Aruco is in an angle I seem to get better results, there is less error in the poses.

2) I tried the Aruco with Gazebo and I was getting really high error in the poses, now that I'm working with actual robots and with Kinects and I get almost no error in the measurements of the Aruco poses. They are almost perfect, like 1 degrees of error, comparing to the almost ~10degree error in the Gazebo simulator. I was expecting worst results in the real life situation. How can I explain this?

This package is amazing if you want to work with Aruco Markers this is the one to use, thx you so much for the help.

edit retag flag offensive close merge delete