OpenBot
Platform
Manipulation datasetOpen
OBRS 40•Bronze

ABC-130k

ABC-130k is an open bimanual robot manipulation dataset released with the paper 'Scalable Behavior Cloning with Open Data, Training, and Evaluation'.

Source notes

ABC-130k is an open bimanual robot manipulation dataset released with the paper 'Scalable Behavior Cloning with Open Data, Training, and Evaluation'. It contains roughly 130,919 episodes (43,090 annotated) totaling about 3,598 hours collected on bimanual YAM stations with two 6-DoF arms and parallel-jaw grippers, spanning ~195 tasks such as pick-and-place, folding, sorting, handover, insertion, tool use, and assembly. Each episode includes three camera views (one top plus two wrist), joint states, end-effector poses, gripper aperture, and task/subtask annotations, plus 400 hours of accompanying sim-teleop data.

Scale
3,598.2 hours
Formats
custom
License
Apache-2.0
Published
2026-06-25
Official sourceAll recordsDataset index A–ZRun local preflightRequest scoped audit

Decision summary

Best for

teleoperation

Main blocker

Metadata requires review against the official source before publication.

Next check

Read the dataset manifest and feature schema.

Release history

Source-backed release timing for this canonical dataset record.

Important releases

  1. Dataset series published

    Release timing is recorded from official dataset metadata.

    Release evidence

Selection readiness

6 evidence dimensions for deciding whether this dataset is ready to inspect, compare, or adopt. This is not a model benchmark.

Catalog evidence · not task performance

73/100

Provisional

4/6 dimensions scored · 48% confidence

Access and governance75conf. 85
Schema and signal coverageNot scoredconf. 15
Policy training readiness85conf. 55
World-model readiness68conf. 50
Failure and recovery readinessNot scoredconf. 15
Download and processing readiness65conf. 65
Read the evidence behind all 6 dimensions

Access and governance

Access and license are declared by the source.

usefulfit 75 · confidence 85

Schema and signal coverage

No machine-readable schema has been verified yet.

unknownnot scored · confidence 15

Policy training readiness

Observation and action/state signals are declared; alignment quality still depends on sample verification.

usefulfit 85 · confidence 55

World-model readiness

Temporal observations plus geometry or semantic context are declared; sample alignment remains to be audited.

usefulfit 68 · confidence 50

Failure and recovery readiness

No verified failure/recovery annotation evidence is available yet.

unknownnot scored · confidence 15

Download and processing readiness

Scale is declared; transfer and processing estimates are not measured.

usefulfit 65 · confidence 65
Review unresolved evidence and next checks

Signal gaps

  • Gaze / attention. Not enough evidence is available to classify this signal.

Next checks

  • Read the dataset manifest and feature schema.
  • Run a bounded sample audit before assigning Strong readiness.

Dataset facts

Source
UC Berkeley / MIT / Amazon FAR / CMU / XDOF
Evidence
secondary claim
Formats
custom
episodes
130.9K
hours
3,598.2
tasks
195
Read paper

Loop signals

6/7 present or partial

Gaze / attention

No decision-grade evidence captured yet.

unknown
View 6 more signal categories
Observation / ego video

video · ABC-130k is an open bimanual robot manipulation dataset released with the paper 'Scalable Behavior Cloning with Open Data, Training, and Evaluation'. It contains roughly 130,919 episodes (43,090 annotated) totaling about 3,598 hours collected on bimanual YAM stations with two 6-DoF arms and parallel-jaw grippers, spanning ~195 tasks such as pick-and-place, folding, sorting, handover, insertion, tool use, and assembly. Each episode includes three camera views (one top plus two wrist), joint states, end-effector poses, gripper aperture, and task/subtask annotations, plus 400 hours of accompanying sim-teleop data.

present
Action / hand pose / robot state

ee_pose · ABC-130k is an open bimanual robot manipulation dataset released with the paper 'Scalable Behavior Cloning with Open Data, Training, and Evaluation'. It contains roughly 130,919 episodes (43,090 annotated) totaling about 3,598 hours collected on bimanual YAM stations with two 6-DoF arms and parallel-jaw grippers, spanning ~195 tasks such as pick-and-place, folding, sorting, handover, insertion, tool use, and assembly. Each episode includes three camera views (one top plus two wrist), joint states, end-effector poses, gripper aperture, and task/subtask annotations, plus 400 hours of accompanying sim-teleop data.

partial
Language intent / task phase

language · ABC-130k is an open bimanual robot manipulation dataset released with the paper 'Scalable Behavior Cloning with Open Data, Training, and Evaluation'. It contains roughly 130,919 episodes (43,090 annotated) totaling about 3,598 hours collected on bimanual YAM stations with two 6-DoF arms and parallel-jaw grippers, spanning ~195 tasks such as pick-and-place, folding, sorting, handover, insertion, tool use, and assembly. Each episode includes three camera views (one top plus two wrist), joint states, end-effector poses, gripper aperture, and task/subtask annotations, plus 400 hours of accompanying sim-teleop data.

present
Feedback / correction / failure

ABC-130k is an open bimanual robot manipulation dataset released with the paper 'Scalable Behavior Cloning with Open Data, Training, and Evaluation'. It contains roughly 130,919 episodes (43,090 annotated) totaling about 3,598 hours collected on bimanual YAM stations with two 6-DoF arms and parallel-jaw grippers, spanning ~195 tasks such as pick-and-place, folding, sorting, handover, insertion, tool use, and assembly. Each episode includes three camera views (one top plus two wrist), joint states, end-effector poses, gripper aperture, and task/subtask annotations, plus 400 hours of accompanying sim-teleop data.

present
Sim-real pairing

simulation · ABC-130k is an open bimanual robot manipulation dataset released with the paper 'Scalable Behavior Cloning with Open Data, Training, and Evaluation'. It contains roughly 130,919 episodes (43,090 annotated) totaling about 3,598 hours collected on bimanual YAM stations with two 6-DoF arms and parallel-jaw grippers, spanning ~195 tasks such as pick-and-place, folding, sorting, handover, insertion, tool use, and assembly. Each episode includes three camera views (one top plus two wrist), joint states, end-effector poses, gripper aperture, and task/subtask annotations, plus 400 hours of accompanying sim-teleop data.

present
License / format / access

Open · Apache-2.0 · custom

present
Evidence details and provenance

Official signal claims

Ee_poseLanguageProprioceptionVideo

Schema and annotations

No machine-readable schema facts are captured.

Sample verification

Pending. Metadata does not prove sample coverage, alignment, or file integrity.

curated official source

Integration notes

  • Metadata requires review against the official source before publication.
ABC-130k Dataset: License, Format & Readiness · OpenBot.ai