White Mug In Center Of Table¶
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 67% | 09-27 21:28 | 1h 30m | 185 | 23.3M / 114k | $0.321 | deterministic 1, grader_error 0, instance_exact 1, instance_ok 1, n_actions 345, video_rendered 1 |
| L✓ 43m | 09-29 10:14 | 43m | 78 | 5.2M / 53k | $0.092 | deterministic 1, grader_error 0, live_success 1, n_actions 515, replay_success 1, video_rendered 1 |
Task instruction (upstream)
Put the white mug in the center of the table.
Playback speed
What RoboLab states about this task
| Success predicate | object_on_center |
| Predicate arguments | object: mug · reference_object: table · require_contact_with: True · require_gripper_detached: True |
| Scored subtasks | 1 |
| Subtask predicates | Subtask |
| Objects | mug bowl alphabet_soup_can orange_juice_carton smartphone milk_carton banana rubiks_cube |
| Upstream attributes | color spatial |
| Upstream difficulty | simple |
| Episode budget | 30 s |
| Other wordings | vague — Move the mug to the center specific — Pick up the white ceramic mug and place it in the center of the table surface away from the other objects |
| Environment class | WhiteMugInCenterOfTableTask |
| Upstream name | WhiteMugInCenterOfTableTask |
| Defined in | robolab/tasks/benchmark/white_mug_in_center_of_table.py |
From https://github.com/NVlabs/RoboLab @ v0.3.1.
Tags¶
Task DomainManipulation
Skill primitives in the demo: colorspatial
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.