Skip to content

Metal Rod Repackaging (Angled Tray) ​

This example demonstrates how to use Tzara, the Telekinesis Physical AI Agent, to build a repackaging pipeline. The source tray is tilted roughly 23 degrees around the robot's X axis, so Tzara accounts for the tilt when computing pick poses — keeping the TCP aligned with the tray surface for all grid slots. Parts are picked from the angled tray and dropped (unstructured) into a flat destination box grid.

Demo ​

UR10e picking aluminum rods from an angled tray and placing into a box grid

The Natural Language Instruction ​

I have an angled tray where aluminum cylindrical parts sorted in a grid structure. The tray has about 23 degrees rotation around X axis of robot base. First pick pose of the grid on the tray i have measured is [-0.3869, 1.3308, 0.1729, -180, -23, 90], note that this is starting pick on the angled tray (that is why -23 deg Y). I need to pick the objects and place in a box also in a grid format. You can drop the objects instead of placing them. Add logging at each step.

About this demonstration

This demonstration used an earlier SDK version. Breaking API changes have made the original code incompatible with the current SDK, so we have temporarily removed it. Updated code is coming soon.

Try It Yourself ​

Set up Tzara, open it in your configured workspace, and use the instructions above as a starting prompt. Review the generated code before running it.

For current APIs and examples, see Robot Motion.