Hello,
I am using a Raspberry Pi 5 with Raspberry Pi OS 64-bit and an AI HAT+. And I have successfully installed ROS 2 Jazzy.
I am planning to use this Raspberry Pi on a robot for development with ROS 2 Jazzy.
Therefore, I would like to know if there is an official ROS 2 package from Hailo available for use.
Thank you for your time and assistance.
Hey @Jinhong_Park ,
Welcome to the Hailo Community!
No we currently do not have official ROS package but our community have developed some things to work with ROS ( we know its possibile there are a lot of projects using it specially in our last HAILO hackathon )
You can check them out :
I can also say from my experience in the hackathon that for detection data , we found that when i implemented a socket-based communication layer between Hailo and ROS2.
Thank you for your response.
I will follow your advice and proceed with development.
Thanks again for your help.
Hey I just released this package where Hailo tappas and ROS2 are combined together in a debian docker container with a working example in Python.
The ROS2 Node is super performant in RPi5 allowing for 3 models to run in parallel with low CPU usage in the host.
Hello Kyrikakis, thank you for sharing your ROS 2 package!
It looks very well-made.
I have already developed my ROS 2 package using the hailo-rpi5-examples.
However, I will definitely consider your package for adding more features in the future.
No worries. Keep an eye, I am planning to add more features
@Kyrikakis thanks;-) I took your repo and I’m running it natively on Ubuntu 24.04 on a Pi5;-) It works pretty well now;-)
I found one problem, where the RasiOS packages and the normal tappas install script leave out some libraries in the rpi5 case:-( But that’s fixed in my build now;-)
All the [source] packages are here:
https://launchpad.net/~marco-sonic/+archive/ubuntu/rasppios , just make sure, you get at least ‘hailo-tappas-core 3.31.0+2-1ubuntu1~marco5’, that has the missing libs.
Thanks,
– Marco
Hi @marco, thanks for your feedback! It’s good to know the repo works well on a native Ubuntu 24.04 installation.
While running directly on the OS can offer some performance gains,
Docker’s containerization provides a more robust and scalable solution. It allows for better dependency isolation, especially when you have multiple ROS2 packages with potentially conflicting requirements, and makes it much easier to reproduce consistent environments.
In the case of the Pi5, sticking with Raspbian ensures compatibility with optimized hardware drivers and features like fan speed control, which may not be fully supported in Ubuntu yet.