← Back to Sample Lab
SignIQ · curated sampleInteractive viewer50 Hz4 cameras

SignIQ ALOHA Bimanual — Coffee Prep

ALOHA dual-arm (14-DOF leader/follower bimanual) · Bimanual tabletop manipulation

Episode Summary

InstructionPlace the coffee capsule inside the capsule container, then place the cup onto the center of the cup tray, then push the 'Hot Water' and 'Travel Mug' buttons.

900
Frames
18.0s
Duration
50 Hz
Control
4
Cameras
14
State dim
14
Action dim
5
Subtasks
success
Outcome
CamerasHigh · Left Wrist · Low · Right Wrist
Modalitiesvideo × 4 · state (14-D proprioception) · action (14-D) · joint effort / torque
Format exportsLeRobot · HDF5 · MCAP
LicenseDemo data licensed for inspection; production deliveries are SignIQ commercial.

QA Health

10of 10 checks pass
  • Schema parsedPASS
  • Timestamps monotonicPASS
  • Video ↔ state frame countPASS
  • No NaN/Inf in actionsPASS
  • Frame-interval jitterPASS
  • Outcome label presentPASS
Download health.json →

Camera previews

High preview
High
download MP4 ↓
Left Wrist preview
Left Wrist
download MP4 ↓
Low preview
Low
download MP4 ↓
Right Wrist preview
Right Wrist
download MP4 ↓

Schema preview

observation.state
shape [14]
  • [0]left_waist
  • [1]left_shoulder
  • [2]left_elbow
  • [3]left_forearm_roll
  • [4]left_wrist_angle
  • [5]left_wrist_rotate
  • …and 8 more
action
shape [14]
kind:joint_target
control_hz:50 Hz
Bundle downloadsmanifest.jsonmetadata.jsontimeseries.jsontrajectory.jsonhealth.json

Interactive inspector

Synchronized cameras, action vs. observed state, joint-space trajectory, and dataset health — driven by the live bundle.

Loading episode bundle…

Why look at this

Real bimanual coffee-prep episode at 50 Hz with four synchronized camera views (overhead, low-angle, and two wrist cameras), full leader/follower joint streams, and per-frame action targets.

Best for

  • →ACT
  • →Diffusion Policy
  • →openpi
  • →VLA fine-tuning

Capture & license

CaptureSignIQ curated sample

LicenseCommercial — sample for inspection

See full dataset details →

Need ACT data at scale?

Talk to a SignIQ data engineer about a tailored collection run, or browse our commercial datasets.