Align Blocks

RoboDojo simulation reference

SE3 Labs real setup

Task ID
SE3 language instruction	“Without picking up any cube, use the clear ruler to push the three purple cubes into one straight, aligned row.”
Official language instruction	Use the set square to push the three blocks into a straight, aligned row, then reset the robot arm.
RoboDojo category	Instruction-Conditioned
Materials	three purple cubes and a straight clear acrylic ruler.
Difference	a ruler replaces the set square, so the robot has one straight pushing edge rather than an L-shaped alignment tool.
RoboDojo task page	Align Blocks

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.

Progress	Condition
0	No milestone below is reached.
10	The ruler is grasped.
25	The ruler pushes a cube, and no cube was ever lifted above the no-lift height.
50	Two cubes rest flush against the same ruler edge with faces parallel within tolerance, and no cube was ever lifted above the no-lift height.
100	The three cube centers are collinear and their faces parallel within tolerance, and no cube was ever lifted above the no-lift height. 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
Ruler regrasps	Times the ruler is released and grasped again.	0 · 1 · 2 · 3+
Cube lifts	Times a cube rises above the no-lift height.	0 · 1 · 2 · 3+
Cubes off the line	Cubes outside the collinearity or yaw tolerance at the end.	0 · 1 · 2 · 3

Randomization

Each episode samples every variable below and records its values.

Variable	Domain
Start layout	Cube positions and yaw and the ruler pose, 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-35")
# 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-35", 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.