Skip to content
humanoidrobots.training

Starting viewport

Unitree Robotics · humanoid

Unitree H1-2

Revised H1 with 7-DOF arms, added ankle DOF and higher arm payload, trading top speed for manipulation.

Frames · Unitree H1-2

3 items · credit and license on each
  • Unitree H1-2 studio render, three-quarter front view
    Studio render of the published MJCF, the model's zero pose. Geometry only; colours are the model's own materials.Rendered by Hyperspawn from unitreerobotics/unitree_mujoco (BSD-3-Clause) · Hyperspawn render · source
  • Unitree H1-2 studio render, side view
    Side view of the same MJCF render, the model's zero pose.Rendered by Hyperspawn from unitreerobotics/unitree_mujoco (BSD-3-Clause) · Hyperspawn render · source
  • 4 s turntable of the MJCF studio render.Rendered by Hyperspawn from unitreerobotics/unitree_mujoco (BSD-3-Clause) · Hyperspawn render · source

Provenance

Model
Unitree H1-2
Entry
unitree_robots/h1_2/h1_2_handless.xml
Files
29 · 26 MB, fetched from raw.githubusercontent.com, cached in your browser
License
BSD-3-Clause
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
unitree_mujoco's handless H1-2, torque-driven.

Policies listed for Unitree H1-2

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 run

Train on GPUs

mjlab ships no stock task for Unitree H1-2. The training page gives you the pinned model and the steps to write a robot config.