Honeycomb Repacking
This example demonstrates how to use Tzara, the Telekinesis Physical AI Agent, to build a repackaging pipeline. Tzara generates code that picks parts from a regular rectangular source grid and places them into a staggered honeycomb destination grid, where alternating rows have different slot counts and an x-offset between them. The gripper uses a partial open width during picks to avoid disturbing tightly packed neighbours. Contributed by Arjun Vir Datta.
Demo
UR10e packing parts into a staggered honeycomb grid
The Natural Language Instruction
I want to do a repackaging task where the parts are placed in a rectangular grid
and need to be placed into another grid where there is a fixed offset on the x
axis and the y axis, and every other row is offset from the previous row.
The first row has n slots, second m, third n, etc. Every other row
is identical. When picking up the parts do not open the gripper all the way as the
parts are close together. Start and end the program at a home position.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.