GR1 · PosttrainPnPNovelFromPlacematToTieredshelfSplitA¶
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 tomato from the placemat and place it in the tiered shelf.
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 tomato is in the tiered shelf: at least two of its bounding-box keypoints inside the tiered shelf's top tier (its highest spawn region) 2. the tomato does not touch the counter 3. the tiered shelf 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 tomato's origin and more than 0.25 m from the tiered shelf's origin (any_gripper_obj_far, th = 0.25) -- release the tomato and move both hands away before the end 5. the distractor object that starts on the placemat with the tomato is not in the tiered shelf. 6. unlimited (privileged): both fresh-process replays of the handed-in trajectory end in the same state, and the check holds on it 7. 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/PosttrainPnPNovelFromPlacematToTieredshelfSplitA |
| 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/PosttrainPnPNovelFromPlacematToTieredshelfSplitA.hdf5); MuJoCo state, model arrays, task state and RNG frozen in instance.npz (SHA-256 ce90bafeadb1…, checked on load) |
| Deliverable | (T, 24) native controller commands, 1 ≤ T ≤ 3000, 20 Hz |
| Reference Solution | The demonstration's own actions (original: 228 actions), executed from the frozen scene by the robot's own controller: 228 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-placemat-to-tieredshelf-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#L113 |
| Task Dirs | robocasa-gr1-placemat-to-tieredshelf-i00-privileged, robocasa-gr1-placemat-to-tieredshelf-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.