open-edge-platform/physical-ai-studio

Letzte erfasste Quellaktivität: 15. Oktober 2026 um 15:38

SkillsMP-Katalog aktualisiert: 26. Oktober 2026 um 11:37

gesammelte Skills: 8

GitHub-Stars: 143
GitHub-Forks: 56

Mit einem KI-Assistenten installieren

Diesen Prompt kopieren und in den verwendeten KI-Assistenten einfügen.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/open-edge-platform/physical-ai-studio.

README des Repositorys

README-Quelldatei: README.md

README-Quelldatei lesen

Vollständige README anzeigen

<p align="center"> <img src="docs/assets/physical_ai_studio.png" alt="Physical AI Studio" width="100%"> </p> <div align="center"> **Physical AI Studio helps teams train, benchmark, and deploy robot policies from demonstrations.** [Studio UI](#studio-ui) • [Python API](#python-api) • [CLI](#cli) • [Policies](#policies) • [Install](#install) • [Documentation](#documentation) </div> --- ## Studio UI Collect demonstrations, train policies, and run inference through a visual interface.  <p align="center"> <img src="docs/assets/readme/gui-demo.gif" alt="Physical AI Studio UI demo: configure robots and cameras, record data, train, review models, and deploy to robots" width="100%"> </p>  [Start Studio with Docker](./application/docs/01-installation.md#install-with-docker-recommended) · [Native setup](./application/docs/01-installation.md#alternatively-install-natively) <details> <summary>Copy Docker start commands</summary> ```bash git clone https://github.com/open-edge-platform/physical-ai-studio.git cd physical-ai-studio/application/docker cp .env.example .env ./setup-devices.sh --cpu # or --xpu or --cuda docker compose up -d ``` Open <http://localhost:7860>. See the [Docker guide](./application/docker/README.md) for hardware options and setup. Configure `HF_TOKEN` in `application/docker/.env` for Hugging Face-backed policies; see [Hugging Face integration](./application/backend/docs/huggingface_integration.md). </details> <details> <summary>Native development commands</summary> Native setup is for contributors and requires OS-level libraries, [uv](https://docs.astral.sh/uv/getting-started/installation/), and [Node.js v24](https://nodejs.org/en/download). See the [prerequisites](./application/docs/01-installation.md#prerequisites). In one terminal, from the repository root: ```bash cd application/backend uv run --extra xpu physicalai-studio serve # or --extra cpu / --extra cuda ``` In a second terminal, also from the repository root: ```bash cd application/ui npm install npm run start ``` Open <http://localhost:3000>. For native Hugging Face setup, use **Settings > General > Hugging Face**. </details> ## Python API Train, benchmark, and export policies programmatically.  <p align="center"> <img src="docs/assets/readme/api-demo.gif" alt="Python API demo: train, benchmark, export, and deploy a policy" width="100%"> </p>  The library also supports LIBERO and RoboCasa benchmarks; see the [benchmarking guide](./library/docs/getting-started/first-benchmark.md) for suite-specific setup and checkpoint requirements. <details> <summary>Copy the Python example</summary> ```python test="skip" reason="requires dataset download and robot observation" from physicalai.benchmark.gyms import PushTBenchmark from physicalai.data import LeRobotDataModule from physicalai.inference import InferenceModel from physicalai.policies import ACT from physicalai.train import Trainer datamodule = LeRobotDataModule(repo_id="lerobot/pusht", num_workers=0) policy = ACT() trainer = Trainer(max_epochs=100) trainer.fit(model=policy, datamodule=datamodule) benchmark = PushTBenchmark(num_episodes=50) results = benchmark.evaluate(policy) policy.export("./exports/act", backend="openvino") runtime_policy = InferenceModel("./exports/act") ``` </details> A PushT-trained policy is not directly usable on a physical robot; use a policy trained for that robot with a matching Runtime config. See the [robot deployment guide](https://github.com/openvinotoolkit/physicalai/blob/main/docs/getting-started/run-a-policy.md). ## CLI Run Studio training, benchmarking, and export from Runtime's `physicalai` CLI; Runtime also provides the `run` command for deployment. <details> <summary>Copy the CLI commands</summary> The example configs live in `library/configs`; run these Studio commands from `library/` in a cloned repository: ```bash # From the repository root cd library # Train on PushT physicalai fit \ --config configs/physicalai/act/pusht/default.yaml # Benchmark the trained checkpoint physicalai benchmark \ --config configs/benchmark/pusht.yaml \ --policy physicalai.policies.ACT \ --ckpt_path experiments/lightning_logs/version_0/checkpoints/last.ckpt # Export for deployment physicalai export \ --policy physicalai.policies.ACT \ --ckpt_path experiments/lightning_logs/version_0/checkpoints/last.ckpt \ --backend openvino \ --output_dir exports/act ``` From your Runtime project, run a robot policy with: ```bash physicalai run --config runtime.yaml ``` Use the [Runtime config example](https://github.com/openvinotoolkit/physicalai/blob/main/docs/how-to/config/write-runtime-config.md) as `runtime.yaml`; it is separate from the PushT training config above. </details> ## Policies Native policy families include ACT, Pi0.5, SmolVLA, MolmoAct2, RLDX-1, XR0, and Cosmos3; see the library’s [supported policies](./library/README.md#supported-policies). ## Install Use the library for Python API and CLI workflows, or follow the Studio UI setup above. The library supports Python 3.12–3.14. See the [library installation guide](./library/docs/getting-started/installation.md) for source installs and optional dependencies. <details> <summary>Copy the Python install command</summary> ```bash # Choose one hardware extra: pip install 'physicalai-train[cpu]' # CPU # pip install 'physicalai-train[cu128]' # NVIDIA GPU # pip install 'physicalai-train[xpu]' # Intel GPU ``` </details> ## Documentation [Library](./library/README.md) · [Application](./application/README.md) · [Contributing](./CONTRIBUTING.md)

README des Repositorys wird geladen…

Skills in diesem Repository

Klassifizierung ausstehend

Skill

Beruf

Beschreibung

Aktualisiert

add-benchmark

nicht klassifiziert

Adds or changes a first-party simulation Benchmark in the Physical AI Studio library. Use when implementing a Benchmark class under library/src/physicalai/benchmark, adding a library benchmark config or gym integration, or changing benchmark tests. DO NOT USE…

Quellsprache: Englisch

2026-10-15

add-policy

nicht klassifiziert

Adds or modifies a policy in the Physical AI Studio library source tree. Use when implementing a policy family under library/src/physicalai/policies, exposing it to policy discovery and Studio's training wizard, or changing its Lightning training and export…

Quellsprache: Englisch

2026-10-15

add-robot-form-field

nicht klassifiziert

Adds an interactive robot form field to Physical AI Studio's UI and plugin SDK. Use when introducing a new robot_payload_ui item kind, changing application/ui robot-form components and SDK validation, and documenting plugin adoption. DO NOT USE FOR creating…

Quellsprache: Englisch

2026-10-15

prepare-release

nicht klassifiziert

Prepares and publishes versioned releases of the Physical AI Studio repository. Triggered by requests to bump `physicalai-studio` or `physicalai-train`, prepare release notes or a release PR, cut `app/vX.Y.Z` or `lib/vX.Y.Z` tags, or verify GitHub Releases…

Quellsprache: Englisch

2026-10-15

pai-benchmark-policy

nicht klassifiziert

Benchmarks a trained Physical AI Studio policy in a simulation gym and reports success metrics. Use when running physicalai benchmark, selecting a benchmark config for a checkpoint or export, tuning episode/env settings, recording videos, or interpreting…

Quellsprache: Englisch

2026-10-15

pai-export-policy

nicht klassifiziert

Exports and validates a trained Physical AI Studio policy for Runtime deployment. Use when calling policy.export or physicalai export with an existing checkpoint, choosing ONNX/OpenVINO/Torch/ExecuTorch, checking numerical parity and export metadata, or…

Quellsprache: Englisch

2026-10-15

pai-train-policy

nicht klassifiziert

Trains, validates, tests, and predicts with Physical AI Studio policies. Use when running physicalai fit/validate/test/predict, wiring a Policy, LeRobotDataModule and Trainer in a project config or Python script, resuming a checkpoint, or debugging an…

Quellsprache: Englisch

2026-10-15

pai-work-with-datasets

nicht klassifiziert

Works with Physical AI Studio datasets and Lightning datamodules using the LeRobot format. Use when wiring LeRobotDataModule into a project training config, choosing a repo_id, inspecting batch shapes, converting between physicalai and lerobot layouts with…

Quellsprache: Englisch

2026-10-15

Es werden 8 von 8 gesammelten Skills angezeigt.