Skip to main content
There are four steps. You run scripts for the first and last. The middle two happen in the dashboard, under Robotics. No code needed there. Two things carry through every step:
  • The task text, like pick up the cube. You set it when you record. The policy learns to do that task.
  • The Training ID. You copy it from the dashboard after training. The inference script uses it to download your policy.

Before you start

  • Two SO-101 arms, calibrated. See SO-101.
  • An auth token and a room id. Use the same ones on both machines. Cloud recording is billed to the token’s account.
  • Python 3.12 or newer, and the examples repo:
Then go to step 1: Cloud recording.

Cloud recording

Step 1: record demos.

Datasets

Step 2: turn a recording into a dataset.

Fine-tuning

Step 3: train a policy.

Running a policy

Step 4: let the policy drive the arm.