Project FREISA, an acronym for "Four-legged Robot Ensuring Intelligent Sprinkler Automation", continues the storyline of the B-AROL-O Team's saga.
In the last few months FREISA evolved into FREISA-GPT, developed in response to the OpenAI Open Model Hackathon.
FREISA-GPT transforms the original FREISA robotic dog into an intelligent assistant powered by gpt-oss-20b open-weight Large Language Model released by OpenAI, thus implementing the following new features:
- Listens to voice commands using Whisper and transforms them into LLM prompts
- Generates structured responses in JSON
- Executes physical actions (for instance, to move or rotate the robot) thanks to ros-mcp-server and ROS2 Humble
- Displays expressions and sounds through an ad-hoc Puppy State Manager
To run FREISA-GPT with an emulated version of the pupper, check out the guide.
With FREISA-GPT, the project moved from smart irrigation to smart interaction, making the robotic puppy not only a gardener’s helper but also a conversational, reactive companion.
Project FREISA was the Grand Prize Winner 🥇 of the OpenCV AI Competition 2023 with OpenCV, Khadas and Seeed Studio.
In more recent times, FREISA was a Finalist of Backdrop Build v3 and repeated the same achievement with Build v4, Build v5 and Build v6:
We published multiple detailed writeups of FREISA:
- Hackster.io (Nov 2023)
- Electromaker.io
- Updated version on Hackster.io
FREISA was also:
featured in Issue 139 of The MagPi Magazine with a 4-page interview:
Described by Tom's Hardware
and presented live at DataBeers Torino in December 2023 (video, slides):
- 2023 🏆 – FREISA wins the Grand Prize at the OpenCV AI Competition
- 2023 🎤 – FREISA is presented at DataBeers Torino and featured in The MagPi Magazine #139
- 2023–2024 🔄 – FREISA is selected multiple times as a Backdrop Build Finalist
- 2024 🌱 – Collaboration with Seeed Studio and integration with SenseCAP Watcher
- 2025 🚀 – Launch of FREISA-GPT at the OpenAI Open Model Hackathon, continuing to evolve as a voice-enabled robotic assistant
| FirstName LastName | GitHub_ID | Telegram_ID |
|---|---|---|
| Alessio Chessa | @aleche28 | ale_che28 |
| Pietro d'Agostino | @pitdagosti | Pit836 |
| Davide Macario | @davmacario | DavideMacario |
| Gianpaolo Macario | @gmacario | gmacario |
| Eric Orso | @OrsoEric | x05032MendicantBias |
| Gianfranco Poncini | @Muwattalli | Togodumno |
| Gianluca Teti | @gteti | Giatet |
We express gratitude to the following people who actively contributed to the project but are no longer active in FREISA:
| FirstName LastName | Role | GitHub_ID | Telegram_ID |
|---|---|---|---|
| Francesca Petrocchi | Support and ideas | @francipetrocchi | stabilofuxia |
| Andrea Podo | Member | @AndreaPodo | andreapodo |
| Alessandro Varesi | Support and ideas | @alv67 | - |
Project Amarone reused some of the code and algorithms originally developed for FREISA. The project was created by Gianluca Teti together with a couple of members of the B-AROL-O team and is available on Hackster.
This was the first public project of the B-AROL-O Team. Some of the algorithms and code developed for ARNEIS have been reused and further refined by FREISA.
https://github.com/B-AROL-O/ARNEIS
Project FREISA is featured in the front page of Kickstarter "Project We Love" campaign "ChatGPT Robot Kit: Unlock your AI Dream Job" by Mangdang Ltd.
OpenSCAD library to draw LEGO® beams and plates with custom patterns. This GitHub repository contains most of the custom 3D-printed parts which are needed to build the FREISA Robot Dog.
https://github.com/B-AROL-O/OpenSCAD-lego-library
The B-AROL-O Team was selected by Seeed Studio to receive one of the 50 SenseCAP Watcher Alpha and delivered a comprehensive writeup on Hackster.io before its official launch.
Project FREISA has also been featured in the Kickstarter "Project We Love" campaign "SenseCAP Watcher - The Physical AI Agent for Smarter Spaces" by Seeed Studio, including the teaser video and a few photos on the front page.
You may follow @baroloteam on Instagram or @baroloteam on X to get notified about the progress of the FREISA project.
Please report bugs and feature requests on https://github.com/B-AROL-O/FREISA/issues, or DM B-AROL-O Team on X about security issues or other non-public topics.
Copyright (C) 2023-2025, B-AROL-O Team, all rights reserved.
The source code contained in this repository and the executable distributions are licensed under the terms of the MIT license as detailed in the LICENSE file.
Please note that your contribution to the project Documentation is licensed under a Creative Commons Attribution-Share Alike 4.0 License. see https://creativecommons.org/licenses/by-sa/4.0/