Put the cream cheese on the rack
libero_goal_task, task 9 · seed 2. DeepSeek-V4.1-Flash, code mode: 6 decisions, 15 motions, solved.
2× · 43 s of motion
- 1 of 6 · grasp1.py
- 2 of 6 · grasp2.py
- 3 of 6 · grasp3.py
- 4 of 6 · place2.py
- 5 of 6 · place3.py
- 6 of 6 · place4.py
- move_to
- move_to
- set_gripper
- move_to
- set_gripper
- move_to
- move_to
- set_gripper
- move_to
- move_pose
- move_pose
- move_pose
- move_pose
- move_pose
- set_gripper
Decisions
libero_goal_task-t09 libero_goal_task · task 9 · seed 2: Code mode · 6 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.