mujoco

Featured

Simulate robots and scenes with MuJoCo — Menagerie robots (Unitree Go2, G1, H1, Berkeley Humanoid, Booster T1), your own MJCF, controllers and policies — record rollouts the pane runs as a live simulation, and train with MJX and MuJoCo Playground. Use for any request that ends in a simulation, a rollout or a policy.

AI & Automation 957 stars 79 forks Updated today MIT

Install

View on GitHub

Quality Score: 93/100

Stars 20%
99
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# mujoco MuJoCo is a physics engine for robotics: a model (MJCF XML → `MjModel`), a state (`MjData`), a step (`mj_step`). Tools: `$MUJOCO_PYTHON` (the pinned venv), `$MENAGERIE` (the robots), `harness_mujoco` on `PYTHONPATH` (load, servos, record, PD hold). Never install another MuJoCo. ## Simulate, record — the pane runs it live ```bash "$MUJOCO_PYTHON" sim/hello.py # → out/rollout.qpos.json (+ .model.xml, rollout.json, rollout.mp4) "$MUJOCO_PYTHON" "$MUJOCO_TOOLCHAIN/verdict.py" # record() already refreshes it; run it after anything else ``` ```python from harness_mujoco import load_menagerie, load_xml, pd_hold, record model, data = load_menagerie("unitree_go2", servos=(60, 2)) # torque motors → position servos (PD in the model) def ctrl(model, data, t): # called before every step data.ctrl[:] = model.key_ctrl[0] # joint-angle targets: hold the "home" pose record(model, data, ctrl, seconds=4, track="base") # track: the body the cameras follow ``` **The pane is MuJoCo's `simulate`, not a video player.** It opens `out/rollout.qpos.json` and runs the model *live* in the browser (MuJoCo's WebAssembly build): from the rollout's first frame, with the controls your controller produced, so the robot does what it did — and then the user can shove it, drive any actuator from a slider, pose joints, load keyframes, look at contacts and forces, or replay the exact recording frame by frame. What `recor...

Details

Author
autonomous-ai
Repository
autonomous-ai/openharness
Created
1 months ago
Last Updated
today
Language
C
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category