Skip to content
Robotics

Koopman DCM

нейросетевые DCM для балансировки роботов

2 min read

Набор ONNX-моделей от Stéphane Caron из статьи CoRL 2026. Каждая модель — это DCM-наблюдаемая: нейросеть по короткой истории измерений и действий предсказывает боковой DCM и обучается совместно с собственной частотой ω, чтобы DCM был неустойчивой собственной функцией оператора Купмана. В набор входят модели для колёсного бипеда Cookie (реальный робот и PyBullet) и гуманоида Unitree G1 (29 DoF) в PyBullet.

Ключевые особенности

  • Три ONNX-модели: Cookie на реальном роботе, Cookie в PyBullet и Unitree G1 (29 DoF) в PyBullet.
  • Вход — delay embedding на H = 10 шагов: 120 значений для Cookie и 373 для G1.
  • Выход — боковой DCM ξ[k] в нормированной координате; действие — заданный боковой ZMP.
  • Частота управления 100 Hz у Cookie и 240 Hz у G1; ω: 3.873 rad/s (реальный Cookie), 4.728 rad/s (PyBullet Cookie), 1.906 rad/s (G1).
  • Для G1 указан режим double support; данные обучения вынесены в отдельный датасет.

Пример

Запуск из каталога cookie_balancer репозитория кода:

pixi run pybullet-balance
pixi run evaluate-mpc
pixi run real-balance
ПодробнееТри ONNX-модели: Cookie (реальный робот и PyBullet) и Unitree G1 (29 DoF, double support).
Частота управления: 100 Hz для Cookie и 240 Hz для G1; ω — 3.873, 4.728 и 1.906 rad/s.
DCM боковой, в нормированной координате; действие — заданный боковой ZMP.
Данные обучения — в отдельном датасете; численных метрик в карточке нет, только ссылки на таблицы статьи.
Discuss Telegram 0

Will it run?

Working out the memory needs

The bot is still collecting this model's weight sizes; the estimate will appear here in a few minutes. Meanwhile you can rent a GPU with headroom.

Massed ComputeOpen Massed Compute

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # stephane-caron/koopman_dcm
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download stephane-caron/koopman_dcm --local-dir ~/models/koopman_dcm
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to koopman_dcm
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of koopman_dcm (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

stephane-caron/koopman_dcm
Author
stephane-caron
Category
Robotics
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments