Put Two Mugs On Shelf¶
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 00m | 09-26 04:21 | 1h 00m | 147 | 15.1M / 78k | $0.219 | deterministic 1, grader_error 0, instance_exact 1, instance_ok 1, n_actions 2461, video_rendered 1 |
| L✗ 1h 30m | 09-29 03:35 | 1h 30m | 243 | 28.7M / 198k | $0.453 | deterministic 1, grader_error 0, live_success 0, n_actions 5837, replay_success 0, video_rendered 1 |
Task instruction (upstream)
Put two (2) mugs on the wire shelf
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: ['ceramic_mug', 'mug', 'mug_01'] · container: wireshelving_a01 · require_contact_with: True · require_gripper_detached: True · logical: choose · K: 2 |
| Scored subtasks | 1 |
| Subtask predicates | pick_and_place |
| Objects | wireshelving_a01 spatula_01 plate_small fork_big fork_small ceramic_mug mug mug_01 |
| Upstream attributes | affordance spatial counting |
| Upstream difficulty | complex |
| Episode budget | 180 s |
| Other wordings | vague — Put the mugs on shelf specific — Select two mugs from the right side of the table and place them on the wire shelf in front of you |
| Environment class | PutTwoMugsOnShelfTask |
| Upstream name | PutTwoMugsOnShelfTask |
| Defined in | robolab/tasks/benchmark/put_two_mugs_on_shelf.py |
From https://github.com/NVlabs/RoboLab @ v0.3.1.
Tags¶
Task DomainManipulation
Skill primitives in the demo: affordancecountingspatial
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.