EmbodiedData
Datasets/Pick and place/SmolVLA SO-100 Pick-and-Place
✓ Source card reviewedSee source termsVersion: LeRobot v2.1

SmolVLA SO-100 Pick-and-Place

A compact real-robot dataset for language-conditioned VLA experiments, with 50 SO-100 episodes, two video streams, six-dimensional motor state, and actions at 30 Hz.

LT
Published by LeRobot TeamHugging Face · Source updated 16 Jul 2026 · Reviewed 17 Jul 2026
View dataset files 19,631 frames · LeRobot v2.1Downloads and licence terms are handled by the original publisher on Hugging Face.

START HERE

This dataset, explained simply

Beginner

A small real SO-100 robot picks up objects and places them at a target from language instructions.

WHAT CAN I TRAIN?Your first VLA experimentPick-and-place imitation policySmolVLA fine-tuning
WHAT DO I NEED?Python basicsLeRobot installedA GPU is helpful, not needed to inspect data
SUITABILITY✓ Contains robot actions✓ Real-world recordings• Check source for language labels
New to the terminology?Episode = one complete attemptObservation = what the robot sees and sensesAction = the command sent to the robot

VERIFICATION RECORD

What EmbodiedData checked

Source statusAvailable at publisherLast checked17 July 2026Dataset versionLeRobot v2.1Training instructionsNot tested by EmbodiedData

Verification confirms the linked metadata at the stated date. It is not a guarantee that upstream files, dependencies or licences will remain unchanged.

Dataset previewIllustrative image—not an original dataset frame
Preview only
PUBLISHER-HOSTED MEDIAOpen genuine dataset samplesLeRobot Team · source repositoryView real samples at source ↗
EXAMPLE OF THE TASKPick up the blue cube and place it inside the metal tray.
View real samples on Hugging Face ↗

Original media, file structure, and dataset viewer are provided by the publisher.

DATASET OVERVIEW

What the publisher reports

A compact real-robot dataset for language-conditioned VLA experiments, with 50 SO-100 episodes, two video streams, six-dimensional motor state, and actions at 30 Hz.

50Reported episodes
30 HzReported frequency
10m 54sReported duration
LeRobot v2.1Dataset format

KNOWN CONFIGURATION

Robot, observations and reuse

Robot or capture systemSO-100
Reported observations2× RGB video, Joint state, Motor actions
ActionsRobot actions are included
EnvironmentReal-world · VLA starter
Licence shown on source cardSee source terms

TRUST & LIMITATIONS

What EmbodiedData has—and has not—checked

Original Hugging Face source linkChecked
Summary against publisher cardReviewed
File integrity and missing valuesNot independently tested
Privacy, safety and legal complianceNot independently tested

Always read the original dataset card, licence, limitations and file documentation before training or redistribution.

SOURCE & CITATION

Use the publisher’s citation

EmbodiedData does not invent a citation or dataset version. Open the original card and copy the citation requested by the publisher.

Open original dataset card ↗