Skip to content

Wash A Baseball Cap

pendingmediumhouse_single_floorUtility Room4m 38sunowned

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 BEHAVIOR-1K runs for every task of a run.

Codex + GPT-6 Luna, reasoning xhigh (ChatGPT login)default run

Not in this run: not among the 30 chosen for the first round (2026-09-26): mostly particles, cutting and liquids, or long tidy-ups like chosen ones

Task instruction (upstream)

Wash the two baseball caps on the countertop in the utility room using the washer until they are no longer dirty.

Measured on the stack we run — BEHAVIOR-1K v3.9.2 / OmniGibson 3.9.2 / Isaac Sim 5.1
Goal predicates covered
Quantifiers forall
Goal clauses 1
Objects named in the goal baseball_cap.n.01 dirt.n.02
Objects in the problem 7 in 6 categories
Rooms loaded corridor_0 dining_room_0 entryway_0 garden_0 utility_room_0
Demonstrations 200 teleoperated episodes
Mean episode 4m 38s (8,349 control steps at 30 Hz)
Base travel, mean 28.94 m
Gripper travel, mean left 10.71 m · right 11.49 m
Evaluation instances 20 public test instances (ids 301–320)

Read from BDDL activity definitions + 2026-challenge-task-instances (licensed download), 2026-09-21.

Tags

Why this task is interesting

Not yet written.

Capability notes

Not yet written.

Oracle demo review

Not yet reviewed.

Discussion