Skip to main content
There is currently no packaged DreamZero YAM simulator adapter in the public simulator examples in Reactor’s public cookbook. The DROID RoboLab gateway assumes a seven-joint Franka arm and DROID cameras; changing its model identifier does not make it a YAM simulator.

​
What you can run now

The first-action example tests a hosted connection and the (24, 14) reply shape using synthetic observations. Replacing those fixtures with recorded YAM observations can test observation encoding and output handling, but replay is not a closed-loop simulation or evidence of task success. The checkpoint model card describes an open-loop evaluation against recorded actions. Its metric and a simulator’s task-success rate measure different behavior; do not substitute one for the other.

​
Adapter requirements

A simulator integration needs all of the following:
  • Two six-joint YAM arms with matching joint order, gripper convention, and calibrated limits.
  • top, left, and right RGB views corresponding to the checkpoint’s camera layout.
  • Measured simulator state sent through all four arm/gripper commands before observation updates.
  • A controller that accepts absolute per-arm joint targets and maps the gripper columns.
  • An explicit control cadence, plan replacement rule, reset handling, and task scoring.
Use one Reactor session per simulated episode stream. At reset, clear the simulator’s pending plan, reset the model, and republish measured state and current frames before starting the next prompt. Log capture timing, action receipt, executed rows, and task outcomes so inference delay and control behavior can be evaluated separately. The reference defines the wire contract; integration covers execution responsibilities.