DatasetFeatured
RT-1 / Fractal real-robot data
Large real multi-task robot demonstration corpus behind RT-1 (often via OXE mixtures).
DatasetFeatured
BC-Z
Google BC-Z multi-task teleop dataset for zero-shot task generalization research.
Why: Classic multi-task real teleop set for IL/VLA history
Overview
BC-Z is a curated dataset on Embodied AI Hub.
Google BC-Z multi-task teleop dataset for zero-shot task generalization research.
Why it matters: Classic multi-task real teleop set for IL/VLA history
Always verify install pins, licenses, and hardware requirements on the official site before production use.
Who it is for
Builders mapping open embodied stacks; researchers comparing SOTA baselines.
Key highlights
- Google BC-Z multi-task teleop dataset for zero-shot task generalization research.
- Type: dataset; tags: 数据集, 真机, 多任务, Google
- Hub recommended
When to use
- You need this category of open resource in your stack map
- You are shortlisting baselines before deep evaluation
When not to use
- License or hardware constraints block adoption
- You only need a closed commercial stack with vendor SLA
Getting started
- 1Open the official URL and read the README / model card.
- 2Check license and citation requirements.
- 3Run the smallest official example before scaling.
- 4Cross-link related hub resources for a full pipeline.
Papers & reading
Caveats & pitfalls
- Hub cards are curated summaries — verify upstream docs.
- Stars and release names drift; treat metadata as approximate.
Content reviewed 2026-07-28