OpenVINO™ Physical AI

OpenVINO™ Physical AI provides runtime components for working with exported robot policies. The documentation is organized around the main deployment tasks and the runtime concepts behind them.

Quick Links

I want to	Go to
Install the package	Installation
Run first inference	Quickstart
Run a policy on a robot	Run a Policy
Write runtime YAML	Runtime Config
Use the runtime CLI	CLI Run
Understand architecture	Architecture
Look up schemas	Config Schema

Documentation Structure

docs/
├── getting-started/  # tutorials
├── how-to/           # task guides
├── explanation/      # concepts and boundaries
└── reference/        # exact commands, schemas, APIs

Workflow

Most deployment workflows follow the same path from an exported package to a running robot loop.

exported policy package
    -> InferenceModel
    -> PolicyRuntime
    -> Robot

Python example:

from physicalai.inference import InferenceModel
from physicalai.runtime import PolicyRuntime, SyncExecution
from physicalai.robot import SO101
from physicalai.capture import UVCCamera

model = InferenceModel.load("./exports/act_policy")
robot = SO101(port="/dev/ttyACM0")
cameras = {"wrist": UVCCamera(device="/dev/video0", width=640, height=480)}

runtime = PolicyRuntime(
    fps=30,
    robot=robot,
    model=model,
    cameras=cameras,
    execution=SyncExecution(mode="chunk"),
)

runtime.run(duration_s=60)

CLI example:

physicalai run --config runtime.yaml --duration-s 60

Note: PolicyRuntime and the CLI are planned APIs. See #121 for status.