Part III: Running a trained policy · §34 of 43
Do these every time, in order. The first run has extra steps (§35).
- Base clamped, area clear, a person at the motor power switch. A policy can do anything the arm can do, including things it never did in training.
- Nothing else owns the buses: no
safe_teleop.py,lerobot-teleoperate,lerobot-recordor ROS launch running (§25). Quick check:candump -n 20 -T 500 can0and… can1print nothing. bash ~/Documents/openarm_lerobot/setup_openarm_lerobot.sh: CAN up, 16/16 motors answer, follower calibration files present. A motor that doesn’t answer reads as 0° in LeRobot (§26 item 6), and that would also corrupt the stored “initial position”.- Scene as in training: cameras plugged in, at the same positions and angles, same lighting, the objects in a typical start position.
- Arms at the training start pose (§31.3), torque off. Check with the follower columns of
python ~/Documents/openarm_lerobot/compare_mini_follower.py --once. - Command checked:
--robot.id=my_bimanual_follower,can0= left /can1= right, bothsides,max_relative_targetset, the same--robot.camerasas recording,--durationset,--display_data=false. - Hands and heads out of the workspace. Run.