Hang Mugs

RoboDojo simulation reference

SE3 Labs real setup

Task ID
SE3 language instruction	“Hang the white mug on peg and the pink mug on peg of the wooden mug tree, by their handles.”
Official language instruction	Hang all the mugs on the mug rack.
RoboDojo category	Generalization
Materials	two ceramic mugs, white and pink, and a freestanding wooden mug tree with six pegs.
Difference	SE3 has 2 mugs rather than 3, and each mug has an assigned peg.
RoboDojo task page	Hang Mugs

Progress score

Score the highest milestone whose condition holds at the end of the episode; the episode succeeds at 100. Also record the failure mode and the execution metrics below.

A mug hangs when it hangs securely by its handle on its assigned peg; a mug resting on the base or table does not hang.

Progress	Condition
0	No milestone below is reached.
10	A mug is grasped and lifted clear of the table.
25	A held mug's handle reaches its assigned peg.
50	One mug hangs and the gripper is open.
100	Both mugs hang and the rack is upright. Both arms are back at origin.

Execution metrics

Record these alongside progress; they do not change it. Count over the whole episode, including events later corrected.

Metric	What to count	Answer
Failed grasps	Grasps that close on or around a task object without lifting it clear of the table.	0 · 1 · 2 · 3+
Drops	Held objects that fall before they are released at a target.	0 · 1 · 2 · 3+
Missed hangs	Attempts where a handle reaches a peg but the mug does not end up hanging from it.	0 · 1 · 2 · 3+
Rack disturbed	Did the rack tip or slide at any time?	yes · no

Randomization

Each episode samples every variable below and records its values.

Variable	Domain
,	Two distinct pegs, 1–6, numbered by peg-tip height from lowest to highest.
Start layout	Rack position near the back; mug positions and handle directions anywhere, clear of the arms.

Schematic start layout, not to scale. Hover a shape for details.

Python SDK

from se3labs.sdk.eval.tasks import TaskRegistry

definition = TaskRegistry.get_task("ROBODOJO-REAL-05")
# Sample one episode's parameters and initial layout.
task = definition.sample(seed=42)
# Sample 20 episodes with separate seeds; seed=42 reproduces the same set.
tasks = definition.sample_set(seed=42, episodes=20)

Create and run a job:

from se3labs.sdk import eval_client

job = TaskRegistry.get_job(
    "ROBODOJO-REAL-05", policy=policy, seed=42, episodes=20,
)
report = eval_client.serve_policy("your-station", "your-relay:7443", job)

task.layout.visualize("layout.png") saves the sampled layout.