Autoware is the world's first "all-in-one" open-source software for self-driving vehicles hosted under the Autoware Foundation. Autoware first began with the Autoware.AI project, based on ROS 1.

Autoware.Auto, another project from the Autoware Foundation, is a clean slate rewrite of Autoware.AI based on ROS 2. Compared to Autoware.AI, Autoware.Auto has the best possible software engineering practices which includes PR reviews, PR builds through CI, 100% documentation, 100% code coverage, style guide, development, and release process.

Autoware.Auto has two other major differentiators when it's compared to Autoware.AI:

  1. Crisply defined interfaces for different modules (messages and APIs)
  2. An architecture designed for determinism, such that it is possible to reproduce behaviors on live machines and development machines
Autoware.Auto testing vehicle

Use Cases

Autoware.Auto initially targets the following 2 use cases:

  1. Autonomous Valet Parking
  2. Autonomous Depot Maneuvering

After the initial set of milestones are completed, Autoware.Auto will allow you to easily map a parking lot, create a map for autonomous driving, and drive over this parking lot entirely autonomously; all in less than 2 weeks.

Autonomous valet parking

Supported Hardware

  1. Vehicle: Lexus 450 LH with the Pacmod 3.0 DBW interface
  2. Sensors:
    1. 4 VLP-16 (or comparable sensors, e.g. VLP-32C)
    2. 16 Sonar sensors
    3. 4 cameras (180 degree FOV)
    4. Novatel GPS
  3. ECUs:
    1. Nvidia AGX Xavier aarch64 computer
    2. Nuvo rugged x86-64 desktop computer


The latest documentation corresponding to the master branch of AutowareAuto is located here:


Functional features in Autoware.Auto are developed according to the roadmap below. More granular feature planning is being handled via GitLab milestones.

Functional feature roadmap

Installation and development

Install Autoware.Auto and learn how to develop applications.

Development process guide

Guidelines for contributing to Autoware.Auto.

Links to other resources