GR1 · PosttrainPnPNovelFromTrayToTieredbasketSplitA¶
Agent runs
Each mode of this task runs once per run. Est. cost is tokens at list price (data/prices.yml), never a bill; see the RoboCasa-GR1 runs for every task of a run.
Codex + GPT-6 Luna, reasoning xhigh (ChatGPT login)default runclosed
Not in this run: not in the sample (robot_coding_bench PR
Task instruction (upstream)
Pick the lemon from the tray and place it in the tiered basket.
Playback speed
Recorded by us: our reference solution, replayed by the verifier (the scene camera).
What RoboCasa-GR1 states about this task
| Success criteria | 1. the lemon is in the tiered basket: at least two of its bounding-box keypoints inside the tiered basket's top tier (its highest spawn region) 2. the lemon does not touch the counter 3. the tiered basket is upright (its z axis has a world-z component above 0.8) 4. both hands are clear: each grip site (left and right) is more than 0.25 m from the lemon's origin and more than 0.25 m from the tiered basket's origin (any_gripper_obj_far, th = 0.25) -- release the lemon and move both hands away before the end. 5. unlimited (privileged): both fresh-process replays of the handed-in trajectory end in the same state, and the check holds on it 6. limited (standard): the one episode (no reset) is recorded by the service and replays to the same state; the check holds on it live and in the replay |
| Family | robocasa-gr1/PosttrainPnPNovelFromTrayToTieredbasketSplitA |
| Robot | Fourier GR1 humanoid: two arms, waist and two six-command Fourier hands; fixed base |
| Category | Pick and place (novel objects) |
| Instance | the initial state of official demonstration episode 0 (demo_1, HDF5/PosttrainPnPNovelFromTrayToTieredbasketSplitA.hdf5); MuJoCo state, model arrays, task state and RNG frozen in instance.npz (SHA-256 b68a5613ff52…, checked on load) |
| Deliverable | (T, 24) native controller commands, 1 ≤ T ≤ 3000, 20 Hz |
| Reference Solution | The demonstration's own actions (original: 263 actions), executed from the frozen scene by the robot's own controller: 263 actions in solution/oracle.npz. The demonstration is a reference solution: it is not in the image and the agent cannot reach it. |
| Limited Mode | Standard mode (robot as a service, eai-standard/2.1) of robocasa-gr1-tray-to-tieredbasket-i00-privileged: the same frozen instance and success check, served by the sim sidecar (images/robocasa-gr1/standard/server_casa.py, tool module casa_tool), which records the episode, replays it in a fresh simulator and judges it; the verifier grades the sidecar's record in a container of its own. The agent sees the robot's cameras (RGB-D, calibrated), its own joints and end effector, and the instruction. |
| Oracle | full |
| Base Image | ghcr.io/mll-lab-nu/eai-robocasa-gr1:0.1.0 |
| Agent Budget | 3600 s of wall clock per mode |
| Environment Source | https://github.com/robocasa/robocasa-gr1-tabletop-tasks/blob/4840e671596f93ca03651524b9f72ffb1aadfeff/README.md#L121 |
| Task Dirs | robocasa-gr1-tray-to-tieredbasket-i00-privileged, robocasa-gr1-tray-to-tieredbasket-i00-standard |
From https://github.com/robocasa/robocasa-gr1-tabletop-tasks @ 4840e67, as defined in our task definitions @ 8c5594a43.
Tags¶
CapabilityControl & Coordination
Task DomainManipulation
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.