# RoboTwin 2.0

From the catalogue. Listed by one researcher from one source page.

- id: `robotwin-2-0`
- kind: real manipulation scripted or autonomous
- robot or device: 5 dual-arm embodiments in simulation (class: simulation)
- how collected: scripted, not teleop (MLLM-generated task code)
- size as stated: 50 dual-arm tasks; trajectory count not stated in abstract
- hours: not stated | hours only claimed: none | episodes: not stated
- year: 2025
- organisation: not stated in abstract
- licence: MIT (TianxingChen/RoboTwin2.0 on the Hub) (class: open)
- access: open (class: open)
- link (paper): https://arxiv.org/abs/2506.18088
- note: Very widely used bimanual set, but synthetic expert data.

## Copies and ports on the Hugging Face Hub

Uploads whose name carries this dataset's name, most downloaded first. Each has its own licence, which can differ from the original's.

| repository | robot | class | kind | episodes | hours | licence | downloads (30 d) |
|---|---|---|---|---|---|---|---|
| [kimtaey/robotwin2.0-egowam-flow-cam_high-subset](https://huggingface.co/datasets/kimtaey/robotwin2.0-egowam-flow-cam_high-subset) | not stated | other | other |  |  | custom terms | 1,933 |
| [OpenMOSS-Team/robotwin2.0-lerobot-v3.0](https://huggingface.co/datasets/OpenMOSS-Team/robotwin2.0-lerobot-v3.0) | not stated | other | other |  |  | open | 1,477 |
| [Traly/Robotwin2.0-lerobot](https://huggingface.co/datasets/Traly/Robotwin2.0-lerobot) | Other robots | other | recording | 114,001 | 173 | open | 1,035 |
| [ShuaKang/my_roboTwin2.0_training](https://huggingface.co/datasets/ShuaKang/my_roboTwin2.0_training) | ALOHA | bimanual | recording |  |  | open | 536 |
| [JackieMM/robotwin2.0-hard-aloha-vision-features](https://huggingface.co/datasets/JackieMM/robotwin2.0-hard-aloha-vision-features) | ALOHA | bimanual | other |  |  | open | 142 |
| [RoMALab/RoboTwin2.0-15tasks-randomized500-wide](https://huggingface.co/datasets/RoMALab/RoboTwin2.0-15tasks-randomized500-wide) | ALOHA | bimanual | other |  |  | open | 78 |

Each repository links to its Hugging Face page, where the files download. Everything this index knows about one upload: https://datasets.gurasees.com/datasets/{repository}.md

Confirm the licence at the link before relying on it.