← Back to Sample Lab
SignIQ · curated sampleInteractive viewerLanguage-conditioned3 cameras

SignIQ Collaborative Single-Arm — xArm Pick & Place

Collaborative single-arm (7-DOF + parallel gripper) · Single-arm tabletop pick-and-place

Episode Summary

InstructionPick up a white plate, and then place it on the red plate.

65
Frames
6.5s
Duration
10 Hz
Control
3
Cameras
8
State dim
7
Action dim
5
Subtasks
success
Outcome
CamerasHand Image · Image2 · Image
Modalitiesvideo × 3 · state (8-D proprioception) · action (7-D)
Format exportsLeRobot · HDF5
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

Hand Image preview
Hand Image
download MP4 ↓
Image2 preview
Image2
download MP4 ↓
Image preview
Image
download MP4 ↓

Schema preview

observation.state
shape [8]
  • [0]motor_0
  • [1]motor_1
  • [2]motor_2
  • [3]motor_3
  • [4]motor_4
  • [5]motor_5
  • …and 2 more
action
shape [7]
kind:joint_target
control_hz:10 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

Single-arm pick-and-place episode with three synchronized cameras (scene + hand-mount + side), proprioceptive state, and language instruction — ideal for OpenVLA-style fine-tuning.

Best for

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

Capture & license

CaptureSignIQ curated sample

LicenseCommercial — sample for inspection

See full dataset details →

Need openpi data at scale?

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