Skip to content

Releases: RobotecAI/rai

RAI 2.0

04 Jun 20:00
650083e
Compare
Choose a tag to compare

RAI 2.0 is a major milestone. We have rewritten it almost from scratch to provide a simple yet efficient way to build embodied agents.

RAI 2.0 introduces a number of new packages, a cleaner architecture, and a more unified approach to agent development. The framework is now easier to extend, more modular, and better aligned with modern AI workflows. This release brings significant improvements in ROS 2 integration, a redesigned Connector API, new agent types including ReAct and ASR/TTS agents, Open set detection, and a simulation and benchmarking suite to support evaluation.

The updated documentation at robotecai.github.io/rai provides comprehensive guidance on getting started, API usage, tutorials, and demos. It covers topics such as speech-to-speech interactions, simulation and benchmarking tools, and available extensions. The documentation also includes detailed instructions for setting up RAI in various forms, tracing, and vendor configurations as well as answers questions on what is RAI and is it a good for me.

RAI 2.0 supports advanced human-robot interaction through text, speech, and multimodal interfaces. More importantly, it enables autonomous long-term reasoning, allowing robots to operate and make decisions independently over extended periods. Agents built with RAI can maintain context and adapt their behavior based on evolving goals and environmental changes. This is made possible by unified handling of perception, memory, and action streams, supporting both reactive and deliberative behavior.

Below is the full changelog of what has changed since the last release. Thanks to everyone who contributed.

What's Changed

Read more

1.1.0

23 Dec 11:22
9564f4f
Compare
Choose a tag to compare

Major Features

  • Added Configuration GUI using Streamlit for easier setup of vendor and settings
  • Implemented new Debugging Assistant for ROS 2 network inspection and troubleshooting
  • Added support for base_url configuration in OpenAI section to support compatible APIs
  • Integrated with rai_state_logs for improved system state monitoring

Improvements

  • Converted XML launchfiles to Python for better maintainability
  • Updated manipulation demo with Streamlit interface and synchronization improvements
  • Improved documentation structure and demo organization
  • Implemented second person perspective for identity building
  • Added default value for keep_speaker_busy parameter in TTS launchfiles

Bug Fixes

  • Fixed empty allowlist behavior in text_hmi (empty allowlist now allows all)
  • Fixed wrong argument name and type in priority of task demos
  • Fixed various documentation links and references
  • Reduced system prompt logging verbosity

Documentation

  • Added new debugging assistant documentation
  • Updated demo documentation and organization
  • Removed external demo repository links from readme
  • Added ROSCon 2024 talk reference

Other Changes

  • Updated Discord server link
  • Added CodeRabbit configuration
  • Updated poetry dependencies
  • Various code style and license notice formatting improvements

What's Changed

Full Changelog: 1.0.0...1.1.0

RAI 1.0.0 release

23 Oct 07:12
bfd3b03
Compare
Choose a tag to compare

What's Changed

New Features

  • Added tools for open-set detection, manipulation, taxi, and agriculture demos
  • Enhanced voice-based apps and ROS2 message tools
  • Integrated Langfuse for system-wide tracing
  • Introduced GenAI URDF parser

Fixes and Improvements

  • Various bug fixes in text_hmi, Ros2PubMessageTool, and Turtlebot configuration
  • Refactoring for better clarity and modularity (vendor separation, toolset updates)
  • Improved task handling, tracing, and documentation

Documentation Updates

  • New tutorials and improved docs for ROSbot XL and Turtlebot4
  • Added vendor table and demo documentation

Build and CI Updates

  • Updated CI setup with self-hosted runners and pre-commit configurations

Chores and Maintenance

  • Dependency updates and minor improvements to launch files and extensions

What's Changed

New Contributors

  • @skrobinho made their first contribution in #245

Full Changelog: 0.9.0-beta...1.0.0

0.9.0-beta

18 Sep 19:29
da5ac2e
Compare
Choose a tag to compare

Summary of changes

This release brings a considerable refactoring effort to the RAI's agent system. RAI architecture now consists of two separate agents:

  • HMI agent (for communication, both voice and text)
  • RAI agent (for solving tasks/missions)
    The default workflow now is to add a task to the RAI agent via HMI such as text_hmi (streamlit app). The RAI Agent will pick up the task, report feedback on every iteration and return task's report at the very end (success or no).

We have also added a new, refactored version of the voice interface with much better voice detection system. Our ASR now supports (possibly) any recording device (no matter the sampling rate), as well as wake word using OpenWakeWord.

Additionally, other enhancements were introduced:

  • RAI What I See (Node for intelligent image capture, based on heuristics (did anything change since the last time?))
  • Extended tests
  • CI license checking
  • NoMaD transformer based navigation system
  • Overall docs improvement
  • Global configuration file (config.toml) where one can set the default model that will be used across RAI's modules
  • Local ASR (Whisper)
  • CI has been extended to ROS 2 Humble
  • Pydantic V2 compatibility with latest Langchain version

What's Changed

New Contributors

Thank you for your contributions!

Full Changelog: 0.8.1-beta...0.9.0-beta

0.8.1-beta

28 Aug 11:49
a462790
Compare
Choose a tag to compare

Changelog

Highlights

  • Cleanup and refactors: Various improvements, including the general cleanup, as well as changes to make the project easier to navigate.
  • New ROSbot-XL Running Example: Documentation now includes a running example for the ROSbot-XL, enhancing the developer experience. It also describes the usage of simulation binary for faster startup.
  • Community and Developer Documentation: The project now features a developer guide, code of conduct, link to a discord server, and community section, improving accessibility and fostering community involvement.
  • Automatic Dependency Updates: A new CI workflow has been added to automatically update dependencies using Poetry, ensuring that the project stays up-to-date with the latest dependencies.

What's Changed

New Contributors

  • @pijaro made their first contribution in #155
  • @github-actions made their first contribution in #159

Full Changelog: 0.8.0-beta...0.8.1-beta

First beta release

14 Aug 17:12
ed722b0
Compare
Choose a tag to compare