Egocentric Adjust Bottle Dataset
Apache-2.0 LeRobot bottle-adjustment task
A LeRobot-style robotics dataset for an egocentric bottle adjustment task, packaged as Parquet with image, text, and timeseries modalities.
LeRobot conversion tests
One of the more directly robot-task-shaped open HF entries.
Inspect schema and run a bounded sample audit before committing to the full release.
Has observation, action/state proxy, and task or language context.
fit 85 · confidence 55
Has rich observation and semantic context, but limited geometry/sim-real alignment.
fit 68 · confidence 55
Contains observation, intent, and action/state, but feedback/correction signal is weak.
fit 72 · confidence 55
Verified facts and provenance
Claims, metadata verification, and sample verification are shown separately.
Unknown — no machine-readable schema facts have been captured.
Unknown — metadata conclusions do not prove sample coverage, alignment, or file integrity.
Declared loop signal coverage
Signals inferred from official metadata; Data pipeline verification is still pending.
Observation / ego video
images · image · A LeRobot-style robotics dataset for an egocentric bottle adjustment task, packaged as Parquet with image, text, and timeseries modalities.
Action / hand pose / robot state
robot state · timeseries · Single-task manipulation curation · Dataset quality checks for action traces
Gaze / attention
No decision-grade evidence captured yet.
Language intent / task phase
language · Single-task manipulation curation · One of the more directly robot-task-shaped open HF entries. · Apache-2.0 LeRobot bottle-adjustment task
Feedback / correction / failure
No decision-grade evidence captured yet.
Sim-real pairing
No decision-grade evidence captured yet.
License / format / access
Open · Apache-2.0 · LeRobot · Parquet
Model and task fit · OpenBot inference
Has observation, action/state proxy, and task or language context.
fit 85 · confidence 55
Has rich observation and semantic context, but limited geometry/sim-real alignment.
fit 68 · confidence 55
Contains observation, intent, and action/state, but feedback/correction signal is weak.
fit 72 · confidence 55
Failure, correction, intervention, and recovery annotations have not been verified.
fit 50 · confidence 15
Good tasks
Blockers and unresolved evidence
- Gaze / attentionunknownNot enough evidence to classify this signal. Verify metadata or a bounded sample.
- Feedback / correction / failureunknownNot enough evidence to classify this signal. Verify metadata or a bounded sample.
- Sim-real pairingunknownNot enough evidence to classify this signal. Verify metadata or a bounded sample.
Raw dataset signals
OpenBot fit
- LeRobot conversion tests
- Single-task manipulation curation
- Dataset quality checks for action traces
Related models and papers
Model references linked to similar loop signals.
OpenVLA
Open-source vision-language-action model for generalist robotic manipulation, trained on diverse real-world robot demonstrations.
RT-X
Cross-embodiment RT model family trained from the Open X-Embodiment mixture to study transfer across robots and tasks.
SmolVLA
Compact open vision-language-action policy designed for practical robot fine-tuning and deployment through the LeRobot ecosystem.
Octo
Open-source generalist robot policy pretrained on Open X-Embodiment trajectories and designed for fine-tuning to new robots and tasks.
Diffusion Policy
Visuomotor policy approach that represents robot behavior as a conditional denoising diffusion process.
Integration notes
- One of the more directly robot-task-shaped open HF entries.
- Good target for OpenBot Data export and validation examples.