Zagolo recording reference — for your engineer

No preparation is required before the first conversation. Start with your robot, simulator, and motion mismatch; existing logs can stay in their current format.

This reference supports the recording plan we prepare with your engineer if new runs are needed. We review the requirements together and agree the exact signals, sampling rate, and script for your robot.

1. Record commands and response.
Capture issued joint commands alongside measured positions and torques. Include velocities when available. Identify the control mode and distinguish measured torque from commanded or estimated effort.

2. Preserve timing.
Include timestamps for commands and measurements, the clock source, and the sampling rate. Flag dropped samples, clock resets, and any known offset between streams; keep the original timing.

3. Document the robot and model.
Include joint names, ordering, units, and sign conventions. Record the model and simulator versions, firmware, controller settings, payload, and starting state for each run.

4. Agree excitation before recording.
Use the robot-specific script agreed with us, within your operating limits. The motion should expose the parameters being fitted; repeated movement at one speed may leave them hard to distinguish.

5. Separate calibration and test runs.
Reserve complete runs for final evaluation before fitting. Keep their identifiers separate from calibration data and freeze the robot, firmware, and payload across the comparison.

6. Keep raw recordings and run notes.
Preserve unfiltered logs. Note contacts, saturation, faults, and interruptions. Agree the file format and required fields before exporting; do not resample or smooth data without recording what changed.

Next step: email hello@zagolo.com with your robot, simulator, and a brief description of the motion mismatch. We will guide the data review and recording plan.

Background:
https://docs.isaacsim.omniverse.nvidia.com/latest/robot_setup/ext_isaacsim_robot_setup_sysid.html
https://github.com/google-deepmind/mujoco/blob/main/python/mujoco/sysid/README.md