Kitchen · TurnOnStove¶
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 RoboCasa365 runs for every task of a run.
Codex + GPT-6 Luna, reasoning xhigh (ChatGPT login)default runclosed
| Trial | Started | Agent time | Model requests | Tokens in / out | Est. cost | Grade |
|---|---|---|---|---|---|---|
| U✓ 10m | 10-01 20:25 | 10m | — | 935k / 20k | $0.027 | deterministic 1, grader_error 0, missing_trajectory 0, n_actions 220, replay_success 1, video_rendered 1 |
| L✗ 59m | 10-01 20:25 | 59m | — | 16.3M / 132k | $0.253 | deterministic 1, grader_error 0, live_success 0, missing_log 0, replay_success 0, video_rendered 1 |
Task instruction (upstream)
Turn on the rear left burner of the stove.
Playback speed
Recorded by us: our reference solution, replayed by the verifier (the scene camera).
What RoboCasa365 states about this task
| Success criteria | 1. The check for TurnOnStove requires that the rear left burner's knob is on: its angle from off, in absolute value, is between 0.35 rad and 2π − 0.35 rad. 2. unlimited (privileged): both fresh-process replays of the handed-in trajectory end in the same state, and the check holds on it 3. 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 | robocasa365/TurnOnStove |
| Robot | Franka Panda on an Omron mobile base with a torso lift (PandaOmron) |
| Category | Atomic |
| Instance | the initial state of an official demonstration episode (which one is not in PR #4's authoring record); MuJoCo state, model arrays, task state and RNG frozen in instance.npz (SHA-256 a52a0718df3e…, checked on load) |
| Deliverable | (T, 13) native controller commands, 1 ≤ T ≤ 3000, 20 Hz |
| Reference Solution | PR #4's reference for this frozen instance (an official demonstration's initial state; PR #4's authoring record for this task names neither the demonstration episode nor the retargeting method). Executed from the frozen scene by the robot's own controller: 241 actions in solution/oracle.npz. Neither the demonstration nor the reference is in the image; the agent cannot reach them. |
| Limited Mode | Standard mode (robot as a service, eai-standard/2.1) of robocasa365-turn-on-stove-i00-privileged: the same frozen instance and success check, served by the sim sidecar (images/robocasa365/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-robocasa365:0.1.0 |
| Agent Budget | 3600 s of wall clock per mode |
| Environment Source | None |
| Task Dirs | robocasa365-turn-on-stove-i00-privileged, robocasa365-turn-on-stove-i00-standard |
From https://github.com/robocasa/robocasa @ 4f8a298 (robocasa 1.0.1), 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.