Skip to content
humanoidrobots.training

Starting viewport

Agility Robotics · biped

Cassie

Torso-less bipedal research robot spun out of Oregon State University and sold to research labs. Superseded by Digit, which reuses its leg design.

Frames · Cassie

8 items · credit and license on each
  • Cassie studio render, three-quarter front view
    Studio render of the published MJCF, keyframe pose from the model. Geometry only; colours are the model's own materials.Rendered by Hyperspawn from mujoco_menagerie/agility_cassie (MIT) · Hyperspawn render · source
  • Cassie studio render, side view
    Side view of the same MJCF render, keyframe pose from the model.Rendered by Hyperspawn from mujoco_menagerie/agility_cassie (MIT) · Hyperspawn render · source
  • 4 s turntable of the MJCF studio render.Rendered by Hyperspawn from mujoco_menagerie/agility_cassie (MIT) · Hyperspawn render · source
  • Cassie bipedal robot walking on a forest trail next to its operator
    Via Wikimedia Commons (CC BY-SA 2.0).Oregon State University, via Wikimedia Commons · CC-BY-SA-2.0 · source
  • Cassie bipedal robot, front view of pelvis and legs, outdoors
    Via Wikimedia Commons (CC BY-SA 2.0).Oregon State University, via Wikimedia Commons · CC-BY-SA-2.0 · source
  • Meet CassieAgility · official embed · source

+2 more on humanoidrobots.systems/agility/cassie

Provenance

Model
Agility Cassie
Repo
google-deepmind/mujoco_menagerie
Commit
c96a32d28fb5
Entry
agility_cassie/scene.xml
Files
16 · 4.9 MB, fetched from raw.githubusercontent.com, cached in your browser
License
MIT
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
Caveat
Loads and runs, but Cassie's compliant closed-chain legs need a dedicated controller; our generic PD stand hold lets it fold.

Policies listed for Cassie

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 Cassie. The training page gives you the pinned model and the steps to write a robot config.

Build the job →