slide open the top drawer and place the bowl in it
libero_goal_lan, task 3 · seed 2. DeepSeek-V4.1-Flash, code mode: 12 decisions, 32 motions, solved.
2× · 107 s of motion
- 1 of 12 · step1.py
- 2 of 12 · open_drawer.py
- 3 of 12 · after_open.py
- 4 of 12 · after_open2.py
- 5 of 12 · go_bowl.py
- 6 of 12 · grasp_bowl.py
- 7 of 12 · survey_tray.py
- 8 of 12 · grasp_bowl2.py
- 9 of 12 · grasp_bowl3.py
- 10 of 12 · grasp_bowl4.py
- 11 of 12 · carry_bowl.py
- 12 of 12 · release3.py
- move_to
- move_pose
- move_pose
- move_pose
- set_gripper
- move_pose
- set_gripper
- move_pose
- set_gripper
- set_gripper
- move_pose
- move_to
- move_to
- move_pose
- move_pose
- move_pose
- set_gripper
- set_gripper
- move_pose
- move_pose
- move_pose
- move_pose
- move_pose
- set_gripper
- set_gripper
- move_to
- set_gripper
- move_pose
- set_gripper
- move_pose
- set_gripper
- set_gripper
Decisions
libero_goal_lan-t03 libero_goal_lan · task 3 · seed 2: Code mode · 12 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.