Our top priority

We are as proud of our service as we are of our robots.

Forgot your password?

Splash Forums Support Mico URDF for the Mico is completely wrong

This topic contains 3 replies, has 3 voices, and was last updated by  gurusub90 1 year, 9 months ago.

Viewing 4 posts - 1 through 4 (of 4 total)
  • Author
  • #2014


    As noted in this bug: https://github.com/Kinovarobotics/kinova-ros/issues/54 , I have observed problems with the Mico arm’s URDF. The hardcoded kinematics which report the tool frame, finger positions, etc. is completely different than the URDF model.

    I have verified using an accelerometer than the orientation of the tool frame reported by the hardcoded kinematics is much closer to correct than that reported by the URDF. This is very bad for anyone trying to use the MICO arm with ROS, since most ROS nodes consume the URDF to get a kinematic model of the robot.

    I will take a look at the URDF in the coming weeks to see exactly where it goes wrong, but it would be great to get some help on this, as it really is a very severe bu



    Thanks very much for your interests in our product. According to your post on Github website, the
    mico’s URDF model shows obviously offsets for certain frames in Rviz. However, I didn’t find this
    problem on my side. The screenshot is attached below for your reference.


    I trigged on the frames on the origin (mico_api_origin, which is the “Fixed Frame” in Rviz Global
    Options), Joint2 (mico_link_2), Joint3 (mico_link_3) and the end-effector (mico_end_effector). Those
    are the frames you mentioned in your previous posts, which shown up in wrong locations in Rviz.
    However they are well-located in the desired position on my side. Therefore, would you please check
    if you are using the most recent Kinova-ROS package. My test environment is provided as below:
    Ubuntu 14.04.3, ROS indigo 1.11.16, Rviz 1.11.10
    Several posts also reported that the position values in URDF were not accurate as the kinematic model.
    I will check this out next week, and follow up with this issue.

    Best regards!



    Are the URDFs for the mico and mico2 the same, are they ‘kinematic-ally’ the same robot?



    I’m trying to check if the URDF model I am using is correct. I am referring to the following document which has a picture of the link geometry but I think it is incomplete.


    First off the distance from the base to the first joint isn’t specified clearly.
    The geometry between the 4th and 5th joint is specified completely either. I think it is missing a dimension.
    I’ll try to use the cad models but I am not sure if I would get the right geometry with the assembly since the links depend on each other.

    Thanks for your help!

Viewing 4 posts - 1 through 4 (of 4 total)

You must be logged in to reply to this topic.

Trending now

Expert Talk

Hitting the Mark with Marketing: The Do’s and Don’ts of Creating a Message Around Robotics

While robotics companies have been around for decades, the spotlight on the industry has only really intensified in recent years as new technologies become more readily available and more implicated in the lives of humans.

Read more
Expert Talk

For the Greater Good: The Importance of Fulfilling Corporate Social Responsibility

By now, it goes without saying that the cornerstone of Kinova’s DNA is our desire to create products that empower humanity, and that fulfilling our ethical, human and social responsibilities is fundamental to maintaining the core of our culture. Always has been, always will be.

Read more
Expert Talk


As discussions around the advancement of AI evolve, so too do the concerns. And for good reason. Machines are getting smarter and smarter, able to complete complex tasks and process information incredibly fast. But, what happens when the developments in AI move too quickly — and we lose sight of human ethics?

Read more