RoboManipBaselines
- Software
- Humanoids and robot learning
- Framework
A framework bundling imitation learning policies and benchmark manipulation environments, offering baselines for training, evaluating and deploying robot manipulation policies.
Made by isri-aist.
Source on GitHub: github.com/isri-aist/RoboManipBaselines (opens in a new tab). Facts read at commit 8535948 (opens in a new tab).
Licenses
- Code
- BSD-2-Clause (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (BSD-2-Clause) at commit 8535948 (opens in a new tab), on 22 Oct 2026.
- Commercial use
- Yes
What it does
- Provides policy architectures including MLP, SARNN, ACT, MT-ACT, Diffusion Policy and several flow-matching and vision-language based policies.
- Supplies pre-collected expert demonstration datasets and trained model checkpoints.
- Lets users collect expert data through custom teleoperation interfaces, including multiple SpaceMouse setups.
- Includes a catalog of manipulation task environments and a guide for adding new ones.
- Offers a MuJoCo tactile sensor guide and misc standalone tools.
- Documents benchmarked performance across environments and policies.
Written by Robotheca from the project's README (opens in a new tab) at commit 8535948.
Getting started
- Difficulty
- Advanced
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 29 Jun 2026 on master
- Latest release
- None published on GitHub
Checked on GitHub on 22 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.