Motor identification preprint

2021-12-15

A little while ago, we posted about experiments we’re doing for identifying the torque-current relationship of the motors of the UR5. We’ve been working silently, but steadily, and we are happy to announce that we have some good results! We can now identify torque-current and friction parameters for each one of the joints of the UR5 individually.

This is possible by performing velocity steps on each joint, and by measuring the current that is drawn by the motors. Knowing the masses of the robot’s links is also essential for calculating the torques that are acting on the robot due to gravity.

This work has been send for publications to ICONS 2022, but we also made it publicly available as a pre-print. The associated dataset that we generated and used for the identification is also freely available.

Load Disqus Comments