EuRoC Forum

[Andy]

Hello,

In the last updates the system detects as "good" insertion when the TCP is placed in the hole, without any insertion.

But in any case, I would say that is almost impossible to insert the TCP so deep without any collision between robot and workpiece even having a perfect detection. Adjusting the tolerances of the path to the maximum the UR5 has a precision error of 0.5mm in the best cases (I could not get a better precision, with lower tolerances the controller can not close the loop and the movement never finishes), making it pretty hard to insert the TCP without any collisions inside the hole.

Regards

I can absolutely confirm this. The UR would need a visual servoing approach to accurately hit the hole
Also when commanding a pose at the /rivet_home, Gazebo seems to simulate gravity and the hangs down almost one Milimeter.

[ZdenekM]

In my opinion, to achieve sub-millimeter accuracy it would be necessary to tune arm's controller (mainly PID) parameters pretty hard - which we can't do. Also, at the beginning of any trajectory arm drops a bit which is real issue for inserting rivet.

[AIS]

Good point Andy, the gravity can be the reason.

I am only able to rivet the holes inserted vertically, where the gravity affect "less". If the insertion is horizontal or tilted there is always a deviation when entering the hole even if the detection is accurate.

[dti]

Good point Andy, the gravity can be the reason.

I am only able to rivet the holes inserted vertically, where the gravity affect "less". If the insertion is horizontal or tilted there is always a deviation when entering the hole even if the detection is accurate.

Gravity was indeed the main challenge, but the controller gave us some headaches too. We ended up with a visual servoing approach, which both could compensate for the bad integral part of the controller and gravity.