DatasetFeatured
RoboMIND (full)
Large multi-embodiment Chinese open robot dataset covering dual-arm and diverse skills.
large multi-robotResearch / check siteBest for pretrainBest for finetuneCross-embodimentBimanualUpdated 2026-07-28
DatasetFeatured
RoboTwin 2.0
RoboTwin 2.0: scalable dual-arm data generator and benchmark with domain randomization (50 tasks, 5 embodiments, RoboTwin-OD).
Why we recommend it
Official RoboTwin 2.0 platform: generator + dual-arm benchmark
Overview
RoboTwin 2.0 is the current official dual-arm data generator and benchmark (moved from robotwin-benchmark.github.io to robotwin-platform.github.io).
It covers ~50 bimanual tasks, five embodiments, RoboTwin-OD (731 objects), and strong domain randomization for sim-to-real.
Code: github.com/RoboTwin-Platform/RoboTwin · Paper: arXiv:2506.18088 · Docs on the official site.
Who it is for
Researchers, students, and builders comparing open embodied stacks.
Key highlights
- RoboTwin 2.0 official platform URL and version
- 50 dual-arm tasks + domain randomization + RoboTwin-OD
- Marked recommended on the hub
When to use
- You are mapping the open embodied AI landscape
- You need a starting URL and judgment note before deep-diving
When not to use
- You need production SLAs or certified industrial support only
- License or hardware constraints are incompatible with your deployment
Getting started
- 1Open the official URL and read README install pins.
- 2Skim license and citation requirements.
- 3Run the smallest official example before scaling experiments.
- 4Cross-link related hub resources (sim / data / policy) for a full stack.
Papers & reading
Caveats & pitfalls
- Hub cards are curated summaries — always verify upstream docs.
- Stars and dates drift; treat extra.stars as approximate.
Content reviewed 2026-07-28