AutoSDV project provides a recommended build for a small-scale autonomous vehicle, equipped with practical, industry-standard sensors and running Autoware, the leading open-source autonomous driving platform. Designed for research, development, and education, the platform offers an affordable, modular solution that enables realistic experimentation and rapid prototyping in autonomous driving technologies.
|
|
|
| Robin-W Solid-State LiDAR Kit | Velodyne 32C LiDAR Kit | Cube1 LiDAR + MOXA 5G Kit |
AutoSDV uses Semantic Versioning. All version dependencies are defined in versions.yaml.
| Version | Autoware | CUDA (x86) | JetPack | Status |
|---|---|---|---|---|
| v0.1.0 | 2025.02 | 12.3 | 6.0 | Stable |
| develop | 2025.02 | 12.3 | 6.0 | Development |
Stable release:
git clone -b v0.1.0 --recurse-submodules git@github.com:NEWSLabNTU/AutoSDV.gitDevelopment version:
git clone -b develop --recurse-submodules git@github.com:NEWSLabNTU/AutoSDV.gitPrevious releases based on Autoware version naming:
This project is distributed under Apache 2.0 license in the license file. If you use this project in your work, please cite it as follows:
@misc{autosdv2025,
author = {Hsiang-Jui Lin, Chi-Sheng Shih},
title = {AutoSDV: A Software-Defined Vehicle Platform for Research and Education},
year = {2025},
institution = {National Taiwan University},
url = {https://github.com/NEWSLabNTU/AutoSDV},
note = {Accessed: 2025-04-28}
}