Starting viewport
Open Dynamic Robot Initiative · quadruped
Solo-12
Lightweight, torque-controlled 12-DOF research quadruped built from open-source brushless actuator modules by the Open Dynamic Robot Initiative.
Frames · Solo-12
6 items · credit and license on each
Studio render of the published URDF (xacro), the model's zero pose. Geometry only; colours are the model's own materials.Rendered by Hyperspawn from open-dynamic-robot-initiative/robot_properties_solo (BSD-3-Clause) · Hyperspawn render · source 
Side view of the same URDF (xacro) render, the model's zero pose.Rendered by Hyperspawn from open-dynamic-robot-initiative/robot_properties_solo (BSD-3-Clause) · Hyperspawn render · source 4 s turntable of the URDF (xacro) studio render.Rendered by Hyperspawn from open-dynamic-robot-initiative/robot_properties_solo (BSD-3-Clause) · Hyperspawn render · source Reactive Walking Controller for Solo-12Open Dynamic Robot Initiative · official embed · source Controlling the Solo12 Quadruped Robot with Deep Reinforcement LearningOpen Dynamic Robot Initiative · official embed · source Introduction Video - Open Dynamic Robot InitiativeOpen Dynamic Robot Initiative · official embed · source
Provenance
No browser-ready model packaged yet.
The description is public, but nobody has pinned a commit and checked it compiles in MuJoCo WASM. Clone it and drop the folder on the viewport above (MJCF, or URDF with STL/OBJ meshes). Files stay in your tab.
Policies listed for Solo-12
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 Solo-12. The training page gives you the pinned model and the steps to write a robot config.