place white mug on plate and chocolate pudding to right
libero_10_lan, task 6 · seed 2. DeepSeek-V4.1-Flash, code mode: 7 decisions, 32 motions, solved.
2× · 95 s of motion
- 1 of 7 · grasp_mug.py
- 2 of 7 · grasp_mug2.py
- 3 of 7 · rim_grasp2.py
- 4 of 7 · place_mug2.py
- 5 of 7 · grasp_pudding.py
- 6 of 7 · pudding_grasp2.py
- 7 of 7 · place_pudding.py
- set_gripper
- move_pose
- move_pose
- set_gripper
- wait_ticks
- move_pose
- set_gripper
- move_pose
- move_pose
- set_gripper
- wait_ticks
- move_pose
- move_pose
- move_pose
- set_gripper
- wait_ticks
- move_pose
- set_gripper
- move_pose
- move_pose
- set_gripper
- wait_ticks
- move_pose
- move_pose
- set_gripper
- move_pose
- move_pose
- set_gripper
- wait_ticks
- move_pose
- move_pose
- move_pose
Decisions
libero_10_lan-t06 libero_10_lan · task 6 · seed 2: Code mode · 7 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.