Starting viewport
Fourier (Fourier Intelligence) · humanoid
Fourier GR-1
Fourier's first general-purpose humanoid, a 1.65 m robot unveiled in 2023 and later succeeded by GR-2 and GR-3.
Frames · Fourier GR-1
5 items · credit and license on each
Studio render of the published URDF, the model's zero pose. Geometry only; colours are the model's own materials.Rendered by Hyperspawn from FFTAI/Wiki-GRx-Models (GPL-3.0) · Hyperspawn render · source 
Side view of the same URDF render, the model's zero pose.Rendered by Hyperspawn from FFTAI/Wiki-GRx-Models (GPL-3.0) · Hyperspawn render · source 4 s turntable of the URDF studio render.Rendered by Hyperspawn from FFTAI/Wiki-GRx-Models (GPL-3.0) · Hyperspawn render · source Fourier Intelligence: The General-Purpose Robot GR-1 - Stunning Launch in July, 2023Fourier · official embed · source Fourier Intelligence's GR-1: Making History as World's First Mass-Produced Humanoid RobotFourier · official embed · source
Provenance
- Model
- Fourier GR1-T1
- Commit
- 48dc081997de
- Entry
- models/mujoco_menagerie/fourier_intelligence_gr1t1/gr1t1.xml
- Files
- 34 · 16 MB, fetched from raw.githubusercontent.com, cached in your browser
- License
- Apache-2.0
- Engine
- MuJoCo 3.14.0, official WebAssembly build · three.js renderer
- Controller
- PD hold on the stand keyframe with an ankle-strategy tilt term; not a learned policy
- Note
- From Fourier's Wiki-GRx-MJCF, branch gr1.
Policies listed for Fourier GR-1
No published policy we can replay yet.
Nothing is playing a trained controller in the viewport above. What you see is a PD hold on the stand pose, computed in your tab. A policy plays here when a checkpoint is published with an obs/action contract we can reproduce exactly in MuJoCo, and it passes a 30 s walk test in the tab.
Set up a training runTrain on GPUs
mjlab ships no stock task for Fourier GR-1. The training page gives you the pinned model and the steps to write a robot config.