Skip to content

Installation#

Target platforms#

Autoware 2.0.0 officially supports Ubuntu 22.04 with ROS 2 Humble and Ubuntu 24.04 with ROS 2 Jazzy, on the hardware listed below. Support for additional platforms may be introduced in future releases.

  • amd64, arm64
    Architecture
  • 8 cores
    CPU
  • 16GB
    RAM
  • 4GB RAM, optional
    NVIDIA GPU

Minimum hardware requirements

Autoware is scalable and can be customized to work with distributed or less powerful hardware. The minimum hardware requirements given above are just a general recommendation. However, performance will be improved with more cores, RAM and a higher-spec graphics card or GPU core.

Although GPU is not required to run basic functionality, it is mandatory to enable the following neural network related functions:

  • LiDAR based object detection
  • Camera based object detection
  • Traffic light detection and classification

For details of how to enable object detection and traffic light detection/classification without a GPU, refer to the Running Autoware without CUDA.

Installing Autoware#

There are multiple ways to install Autoware depending on your use case and experience level. You may also choose to install Autoware Core which contains only the essential Autoware packages, or Autoware Universe which contains the full Autoware stack. For installation types, see the subsections below. If any issues occur during installation, refer to the Support page.

Full stack

Autoware Universe#

  • Contains full stack Autoware and 3rd party packages
  • ML-based perception/planning capabilities

Essentials

Autoware Core#

  • Contains only the essential Autoware packages
  • Basic functionality for lane driving and obstacle detection
  • No NVIDIA dependency
  • No neural networks for detecting objects (yet)

1. Docker installation#

Autoware publishes prebuilt Docker images on GHCR that let you run and develop Autoware easily on your host machine, ensuring the same environment for development and deployment without installing dependencies.

For containerized deployment patterns and integrations beyond local development, see Open AD Kit (the first SOAFEE Blueprint for autonomous driving) and the Open AD Kit Documentation.

Autoware Universe Autoware Core

2. Source installation#

Source installation is for the cases where more granular control of the installation environment is needed. It is recommended for experienced users or people who want to customize their environment. Note that some problems may occur depending on your local environment.

Autoware Universe Autoware Core

3. Debian package installation#

Autoware Core packages are available on the ROS build farm. If you have an environment where ROS is set up, Autoware packages can be easily installed and used with other packages in the ROS ecosystem.

Autoware Core

Extending Autoware with community packages#

The Autoware Index is a registry of community ROS 2 packages that extend Autoware. Once you have a source workspace set up, you can pull additional packages from the index with a generated .repos file.

Autoware Index (Community Packages)

  • Installing related tools

    Some other tools are required depending on the evaluation you want to do. For example, to run an end-to-end simulation you need to install an appropriate simulator.