Physical AI SIG

OSRA TGC Special Interest Group for Physical AI

This project is maintained by ros-physical-ai

Working Groups

The Physical AI SIG is organized into five working groups, each focused on a critical layer of the stack.

Standardized Interfaces & Messages

Coordinator: Michel Hidalgo (Ekumen)

Defines the common language and contracts for the ecosystem, ensuring all components are interoperable and reusable.

Data Collection Pipeline

Coordinator: Anh Vu Vu (Huawei)

Builds the workflow of collecting data, logging under constraints, and inspecting and visualizing logged data for curation.

Training & Execution Pipeline

Coordinator: Michael Gentner (BMW)

Builds the end-to-end software workflow, enabling developers to take a trained policy and run it efficiently and robustly on a robot.

Reference Platform & Applications

Coordinator: Yadunund Vijay (Intrinsic)

Makes the initiative’s work tangible by integrating all technologies into a physical platform with accessible examples and community-facing activities.

Embodied Agentic AI

Coordinator: Adam Dabrowski (Robotec.ai)

Develops standards, best practices and reference applications for flexible skill composition, where reasoning models orchestrate state-of-the-art packages and learned policies through tool use.