Gallery · LIBERO-Pro

put the white mug on the left plate and put the yellow and white mug on the right plate

libero_10_object, task 4 · seed 1. DeepSeek-V4.1-Flash, code mode: 7 decisions, 23 motions, solved.

2× · 72 s of motion
  1. 1 of 7 · step1.py
  2. 2 of 7 · step2.py
  3. 3 of 7 · step3.py
  4. 4 of 7 · step4.py
  5. 5 of 7 · step5.py
  6. 6 of 7 · step6.py
  7. 7 of 7 · step7.py
  1. set_gripper
  2. move_pose
  3. move_pose
  4. set_gripper
  5. move_pose
  6. move_pose
  7. move_pose
  8. move_pose
  9. set_gripper
  10. move_pose
  11. set_gripper
  12. move_pose
  13. move_pose
  14. set_gripper
  15. move_pose
  16. set_gripper
  17. move_pose
  18. move_pose
  19. set_gripper
  20. move_pose
  21. move_pose
  22. move_pose
  23. set_gripper
Decisions

The recording is the robot's own cameras at 2×; the time between motions, while the model thinks, is not filmed. The 3D replay is the camera's picture in depth after each decision, with the paths it planned, to turn and step through.