Starting viewport
Pollen Robotics (Hugging Face) · wheeled-humanoid
Reachy 2
Wheeled humanoid with two 7-DOF arms, Orbita neck/wrists and an omnidirectional base, aimed at AI and teleoperation research; Pollen was acquired by Hugging Face in April 2025.
Frames · Reachy 2
5 items · credit and license on each
Studio render of the published MJCF, the model's zero pose. Geometry only; colours are the model's own materials.Rendered by Hyperspawn from pollen-robotics/reachy2_mujoco (Apache-2.0) · Hyperspawn render · source 
Side view of the same MJCF render, the model's zero pose.Rendered by Hyperspawn from pollen-robotics/reachy2_mujoco (Apache-2.0) · Hyperspawn render · source 4 s turntable of the MJCF studio render.Rendered by Hyperspawn from pollen-robotics/reachy2_mujoco (Apache-2.0) · Hyperspawn render · source Reachy 2 (Beta) - Practicing his skillsPollen Robotics · official embed · source Reachy 2 Beta - Work in progressPollen Robotics · official embed · source
Provenance
- Model
- Pollen Reachy 2
- Commit
- f6d8284e812d
- Entry
- reachy2_mujoco/description/mjcf/test_scene.xml
- Files
- 20 · 18 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
- Pollen's MJCF on its omnidirectional base. Mesh paths assume a meshdir the scene does not set; the tab sets it.
Policies listed for Reachy 2
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 Reachy 2. The training page gives you the pinned model and the steps to write a robot config.