GitHub 火線榜/hybridrobotics/supermimic/技術文件

hybridrobotics/supermimic技術文件

Humanoid whole-body motion tracking with one differentiable world model.

目錄大綱 (TOC) (4 章節)▾

Setup Usage Acknowledgements License

多語言回退提示：當前倉庫原作者暫未發布在地化文件，已為您無縫切換至官方英文原版（English），排版及程式碼實例完整保真。

極速安裝

pip install supermimic

SuperMimic

Project page | Paper

SuperMimic trains a humanoid whole-body motion tracker with one differentiable world model, built on mjlab.

Setup

Install uv:

curl -LsSf https://astral.sh/uv/install.sh | sh

Clone both repos as siblings:

mkdir supermimic_ws && cd supermimic_ws
git clone [email protected]:HybridRobotics/supermimic.git
git clone [email protected]:HybridRobotics/mjlab_research.git
cd supermimic

Usage

Available task IDs:

SuperMimic-GenCoord-G1 — generalized coordinates representation
SuperMimic-MaxCoord-G1 — maximal coordinates representation

Train a world model and policy:

CUDA_VISIBLE_DEVICES=<GPU_ID> uv run src/supermimic/scripts/train.py \
  <TASK_ID> --runner.run_name <description>

Play back a trained model:

uv run src/supermimic/scripts/play.py \
  <TASK_ID> --wandb-path <RUN_PATH>

Acknowledgements

SuperMimic contains code inspired by these projects:

ControlVAE (BSD-3-Clause)
robotic_world_model (Apache-2.0)
DreamerV3 (MIT)

License

Released under the Apache License 2.0.

文件鏡像歸檔自 GitHub 官方源路徑 · 造訪原專案 GitHub

最後同步快照：2026-11-13