Utensils In Mug¶
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 RoboLab runs for every task of a run.
Codex + GPT-6 Luna, reasoning xhigh (ChatGPT login)default run
| Trial | Started | Agent time | Model requests | Tokens in / out | Est. cost | Grade |
|---|---|---|---|---|---|---|
| U✓ 1h 30m | 09-26 19:21 | 1h 30m | 188 | 24.0M / 108k | $0.326 | deterministic 1, grader_error 0, instance_exact 1, instance_ok 1, n_actions 510, video_rendered 1 |
| L✗ 1h 10m | 09-29 09:56 | 1h 10m | 124 | 13.6M / 93k | $0.207 | deterministic 1, grader_error 0, live_success 0, n_actions 1717, replay_success 0, video_rendered 1 |
Task instruction (upstream)
Put the fork and spoon in the ceramicmug
No oracle video published upstream — this is the scene it starts from.
What RoboLab states about this task
| Success predicate | object_in_container |
| Predicate arguments | object: ['fork_big', 'spoon_big'] · container: ceramic_mug · logical: all · require_gripper_detached: True |
| Scored subtasks | 1 |
| Subtask predicates | pick_and_place |
| Objects | bowl banana bagel_07 coffee_can banana_01 yogurt_cup coffee_pot ceramic_mug pitcher fork_big spoon_big apple_01 orange2 milk_carton orange_juice_carton bagel_01 bagel_02 plate_small plate_large |
| Upstream attributes | semantics affordance |
| Upstream difficulty | simple |
| Episode budget | 90 s |
| Other wordings | vague — Put the utensils in the mug specific — Take the fork on the bagel plate and put it in the ceramic mug, and take the spoon from the red bowl and put it in the mug |
| Environment class | UtensilsInMugTask |
| Upstream name | UtensilsInMugTask |
| Defined in | robolab/tasks/benchmark/utensils_in_mug.py |
From https://github.com/NVlabs/RoboLab @ v0.3.1.
Tags¶
Task DomainManipulation
Skill primitives in the demo: affordancesemantics
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.