GitHub repository
An open-source digital twin simulator specifically optimized for Autoware, providing ROS2-native environments and sensor simulations.
What is GitHub repository?
AWSIM is an open-source digital twin simulator specifically designed for the Autoware autonomous driving platform. It provides a virtual environment where developers can test and validate autonomous driving systems using the same ROS2 communications and sensor simulations found in real vehicles. The simulator enables comprehensive testing of Autoware-based systems before real-world deployment.
Autonomous vehicle developers and researchers working with Autoware who need to test and validate their systems in simulated environments. Robotics engineers focusing on autonomous driving who require ROS2-native simulation tools.
AWSIM offers the most optimized simulation environment specifically tailored for Autoware, with native ROS2 integration and sensor simulations that match real vehicle behavior. Its focus on customizability and layered architecture allows developers to extend and adapt the simulator to their specific testing needs.
Overview
Open sourced digital twin simulator for Autoware
Use Cases
Best For
- Testing Autoware-based autonomous driving systems in virtual environments
- Developing and validating sensor fusion algorithms with simulated LiDAR and camera data
- Creating reproducible traffic scenarios for autonomous vehicle testing
- Integrating hardware-in-the-loop testing with steering wheel controllers
- Developing V2I (Vehicle-to-Infrastructure) communication systems
- Validating autonomous vehicle behavior using ASAM OpenSCENARIO scenarios
Not Ideal For
- Projects using autonomous driving platforms other than Autoware (e.g., Baidu Apollo, NVIDIA DriveWorks)
- Teams seeking a no-code simulation environment with extensive pre-built assets and minimal setup
- Organizations without existing Unity 3D or ROS2 expertise and infrastructure
Pros & Cons
Pros
Uses the same ROS2 topics and messages as actual Autoware vehicles, ensuring seamless communication and testing fidelity as highlighted in the README's feature list.
Implements ray tracing for LiDAR and OpenCV for cameras, along with IMU and GNSS, providing comprehensive and realistic sensor data for algorithm validation.
Features a simple architecture that allows controlling C# code execution order independent of Unity's script system, enabling deep customizations through coding as per the philosophy.
Supports random traffic simulation with fixed seeds and ASAM OpenSCENARIO compatibility, facilitating reproducible and standardized testing scenarios for validation.
Cons
Optimized exclusively for Autoware, making it difficult to adapt for other autonomous driving frameworks without significant modification, limiting broader use.
Requires proficiency in Unity, ROS2, and Autoware, which can be a barrier for teams new to these technologies, as implied by the focus on customizability through coding.
License prohibits public hosting of documents under /docs, potentially hindering community-driven documentation improvements and ease of access for external users.
Frequently Asked Questions
Related Projects
GitHub repositoryOpen source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
GitHub repositoryOpen-source simulator for autonomous driving research.
GitHub repositoryA ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles
GitHub repositoryGazebo classic. For the latest version, see https://github.com/gazebosim/gz-sim
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.