Open the top layer of the drawer and put the cream cheese inside
libero_goal_task, task 3 · seed 4. DeepSeek-V4.1-Flash, code mode: 5 decisions, 15 motions, solved.
2× · 51 s of motion
- 1 of 5 · open_drawer.py
- 2 of 5 · release_measure.py
- 3 of 5 · retract_measure.py
- 4 of 5 · pick_cheese.py
- 5 of 5 · place_cheese.py
- move_pose
- move_pose
- set_gripper
- move_pose
- set_gripper
- move_pose
- move_pose
- move_pose
- move_pose
- move_pose
- set_gripper
- move_pose
- move_pose
- move_pose
- move_pose
Decisions
libero_goal_task-t03 libero_goal_task · task 3 · seed 4: Code mode · 5 decisions, solved
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.