中文版本：
Back to Table of Contents:
To ensure codec performance, as well as inference performance, make sure that your onboard computer has the following minimum operating requirements:
| Components | Minimum Requirements | Used for | Reasoning |
|---|---|---|---|
| CPUs | 4 Cores | Video streaming for remote teleoperation and image compression of dataset creation | These operations use software codecs, and low CPU performance can result in encoding frame rates not keeping up with camera frame rates |
| RAM | 8 GB | Dataset creation cache | Camera images are cached in memory for a period of time before being written to disk |
| GPU | NVIDIA RTX2060 | Inference of VLA models | AhaRobot uses NVIDIA GPUs for inference acceleration |
The main part of AhaRobot runs on ROS2 Humble and employs Docker to isolate the main system. Make sure you have the following software components installed on your onboard computer:
| Components | Installation Instructions |
|---|---|
| Ubuntu 24.04.1 Desktop | https://ubuntu.com/download/desktop |
| Docker | https://docs.docker.com/engine/install/ubuntu/ |
| NVIDIA Container Toolkit | https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html |
| Sunshine (recommended) | https://docs.lizardbyte.dev/projects/sunshine/latest/md_docs_2getting__started.html |
Every time you reboot your system, you need to start the service in the terminal with this command: systemctl --user restart sunshine && DISPLAY=:0 xhost local: + |