rai

RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface executi

What is rai?

RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.

Overview of rai

What it is

RAI is a vendor-agnostic agentic framework for Physical AI robotics. It uses ROS 2 tools to perform complex actions, execute defined scenarios, provide free interface execution, log summaries, and support voice interaction. The framework is designed to develop and deploy Embodied AI features for robots. It is an open-source project hosted on GitHub under the Apache-2.0 license.

Key features

  • Multi-agent systems that integrate generative AI capabilities into robots.
  • Robot intelligence features such as natural human-robot interaction and flexible problem-solving.
  • Multi-modal interaction supporting diverse data types, sensory integration, and multiple input/output modalities.
  • Includes components: rai core, rai whoami, rai_asr (speech-to-text), rai_tts (text-to-speech), rai_sim (simulation connection), rai_bench (benchmarking), rai_perception (object detection), and rai_nomad (navigation integration).
  • Provides simulation demos for various robots including autonomous tractors, robot arms, and mobile manipulators.

Use cases

RAI can be used for mission and obstacle reasoning in orchards with autonomous tractors, manipulation tasks using natural language with robot arms, autonomous mobile robot navigation and control, and agentic mobile manipulation with on-board execution. It is suitable for developers and researchers working on embodied AI, human-robot interaction, and multi-agent robotic systems.

Getting started

See the Quick setup guide in the repository documentation.

License and pricing

The project is licensed under Apache-2.0 and is open source. Pricing is not stated beyond the open-source nature.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/robotecairai.svg)](https://yunodb.com/tools/robotecairai?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/robotecairai?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/robotecairai.svg" alt="Featured on YunoDB" height="20"></a>