Marker 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✓ 35m | 09-27 18:08 | 35m | 77 | 5.4M / 36k | $0.087 | deterministic 1, grader_error 0, instance_exact 1, instance_ok 1, n_actions 347, video_rendered 1 |
| L✓ 25m | 09-29 07:45 | 25m | 49 | 2.9M / 43k | $0.061 | deterministic 1, grader_error 0, live_success 1, n_actions 175, replay_success 1, video_rendered 1 |
Task instruction (upstream)
Put the whiteboard marker in the mug
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: marker · container: ceramic_mug · require_gripper_detached: True |
| Scored subtasks | 1 |
| Subtask predicates | pick_and_place |
| Objects | ceramic_mug glasses keyboard lizard_figurine marker remote_control rubiks_cube smartphone wooden_bowl spoon_big computer_mouse yogurt_cup oatmeal_raisin_cookies granola_bars |
| Upstream attributes | affordance |
| Upstream difficulty | simple |
| Episode budget | 40 s |
| Other wordings | vague — Put the marker in the mug specific — Pick up the marker and drop it vertically into the mug, make sure the marker stands upright |
| Environment class | MarkerInMugTask |
| Upstream name | MarkerInMugTask |
| Defined in | robolab/tasks/benchmark/marker_in_mug_task.py |
From https://github.com/NVlabs/RoboLab @ v0.3.1.
Tags¶
CapabilityControl & Coordination
Task DomainManipulation
Skill primitives in the demo: affordance
Why this task is interesting¶
Not yet written.
Capability notes¶
Not yet written.
Oracle demo review¶
Not yet reviewed.