AI model
GMT (General Motion Tracking)
From github.com/zixuan417/humanoid-general-motion-tracking (opens in a new tab)
- Humanoids and robot learning
- Apache-2.0 (code)
- Apache-2.0 (weights)
A MuJoCo simulation codebase for tracking human motions with a Unitree G1 humanoid robot, using a pretrained whole-body control policy. Intended for research use.
- Stale. No commit in 12 months: the newest is from 8 Aug 2025.
Facts
- Code last updated
- 8 Aug 2025Newest commit on master
- Maintenance
- Staleno commit in 12 months
- Difficulty
- Advanced
Checked on GitHub on 6 Nov 2026.
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) at commit 2a590de (opens in a new tab), on 4 Nov 2026. A license text Robotheca's reader does not know: a person at Robotheca set it on 9 Nov 2026.
- Weights
- Apache-2.0 (opens in a new tab)
Read on github.com/zixuan417/humanoid-general-motion-tracking/blob/… (opens in a new tab).
- Commercial use
- Yes
Overview
What it does: Robotheca's summary
- Runs sim-to-sim tests of a pretrained motion-tracking policy on Unitree G1 in MuJoCo.
- Ships a pretrained checkpoint and several example motions to try out.
- Lets you swap in other motions from the motions folder to change the tracked movement.
- Includes a viewer script to display the kinematic motion without simulation.
- Built as a lightweight, easy-to-use codebase, tested on Linux and M1 macOS.
- The authors note the pretrained policy may behave differently on other robots and do not guarantee deployment success.
Written by Robotheca from the project's README (opens in a new tab) at commit 2a590de, not by its creator.
The model card
Files and versions
- Repository on GitHubgithub.com/zixuan417/humanoid-general-motion-tracking (opens in a new tab)
- The version Robotheca read2a590de (opens in a new tab)
- Latest releaseNone published on GitHub
- Where the weights' license was readgithub.com/zixuan417/humanoid-general-motion-tracking/blob/… (opens in a new tab)
Robotheca never hosts the code or the weights: each link goes to the creator's own page.
Use it
How to load it, in the creator's words: The project's README (opens in a new tab)
Robotheca doesn't review code. Read it before running it.
Robotheca lists AI models as a reference: nothing is hosted or run here, and every fact links to where it was read.