Local demonstrations of predictable bin picking

Local demonstrations of predictable bin picking

With SHAFTS, we demonstrate to shaft and axle manufacturers that bin picking cells are today reliable and that the installation time is limited (< one week). We do this by organizing local events for interested customers where we demonstrate 24/7 running bin-picking cells.

The solution

Pickit novel robotic gripper initially developed for forge billets (steel cylinders) was expanded and successfully validated for random bin picking of shafts. Using a passive joint in combination with compliance, this gripper can reach shafts deep in a bin regardless of their orientation. This smart mechanical design is very robust since the passive compliance self-adapts to the pose of the parts. Additionally, this extra passive degree of freedom is leveraged to optimise the robot motion improving the robot reach and cycle time. A set of different magnets and suction cup modules allows it to cover a wide range of shafts and axles.


Shafts and axels manufacturing companies want to automate machine loading processes to deal with labour shortages and to remain competitive with lower-wage countries. This requires random bin picking robot cells. The main challenges for picking shafts and axles from bins are the ability to reliably detect the part orientation, the definition of smart part extraction motions (in and out of the bin), and adaptable grippers that can reliably pick
different part types in unstructured and constrained environments.


As a direct result of TRINITY demonstrator and dissemination events, AI.EC won a strategic project at Volkswagen (Slovakia) to install Pickit’s (SHAFTS) solution and Delta Tech won a project at Kovacs KFT Forge (Hungary) to install Pickit’s (SHAFTS) solution.

Facts and figures

  • Technology Area:

    Robot Cell Development

  • End User:

    System integrators of robot cells - Deltatech - Ai crowd

  • Start Date - End Date:

    01/11/2021 - 31/08/2022

  • Duration:

    11 months

  • FSTP Funding:

    195 507,00 €

  • TRL Level at Start:


  • TRL Level at End:


  • Number of early adopters raised:


  • Project results
    The intuitive and simple user interface including the kinematics of the gripper is very good even for places, from which it is difficult to get the part.

    Ing. Michal Bušfy, Application programmer (Ai crowd)

    back to success stories
    Subscribe to newsletter

    Please subscribe to our mailing list to be the first one informed about the new open calls, events and other hot news!

      Please check if the email you entered is correct
      All done!

      Your have successfully subscribed to Trinity newsletter.