RoboTwin
- Software
- Humanoids and robot learning
- Framework
A bimanual robot manipulation platform with a simulator, generated demonstration data, and benchmark tasks for training and evaluating dual-arm policies.
Made by RoboTwin-Platform.
Source on GitHub: github.com/RoboTwin-Platform/RoboTwin (opens in a new tab). Facts read at commit ea8b211 (opens in a new tab).
Licenses
- Code
- MIT (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit ea8b211 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Provides a benchmark of bimanual manipulation tasks with domain randomization to test policy robustness.
- Offers over 100,000 pre-collected trajectories that can be downloaded and used for training.
- Lets users collect their own demonstrations with custom task configs, randomization, and embodiment setups.
- Includes scripts to convert collected data into LeRobot v2.1 and v3.0 dataset formats.
- Evaluates policies through XPolicyLab, locally across multiple GPUs or split between a remote policy server and a local simulator.
- Maintains a public leaderboard and official benchmark checkpoints for comparison.
Written by Robotheca from the project's README (opens in a new tab) at commit ea8b211.
Getting started
- Difficulty
- Intermediate
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 24 Sept 2026 on main
- Latest release
- Stable Version (26 Feb 2026)
Checked on GitHub on 16 Oct 2026.
Links
Robots that can run it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.