Skip to content
humanoidrobots.training

Starting viewport

Stanford (Tony Zhao et al.) · arm

ALOHA

Low-cost open-source bimanual teleoperation system with two leader and two follower arms plus four cameras, used to collect data for ACT imitation learning.

Frames · ALOHA

4 items · credit and license on each
  • ALOHA 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/aloha (BSD-3-Clause) · Hyperspawn render · source
  • ALOHA studio render, side view
    Side view of the same MJCF render, keyframe pose from the model.Rendered by Hyperspawn from mujoco_menagerie/aloha (BSD-3-Clause) · Hyperspawn render · source
  • 4 s turntable of the MJCF studio render.Rendered by Hyperspawn from mujoco_menagerie/aloha (BSD-3-Clause) · Hyperspawn render · source
  • ALOHA Robot at Stanford UniversityZipeng Fu · 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 ALOHA

  • Bimanual cube transfer (simulation, human demos)

    LeRobot ACT · not replayed in the tab

    source

  • Bimanual peg insertion (simulation, human demos)

    LeRobot ACT · not replayed in the tab

    source

Train on GPUs

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

Build the job →