This repository provides a sample ROS 2 environment working on a Jetson-based ECU and GMSL2-compatible cameras.
As a sample application, the following images show object detection results using the contents of this repository. Various perception applications will be added in the future and you can develop them in this provided environment.
Edge.Auto sensor fusion system can be realized by using this with edge-auto repository.
This repository is based on a natively built ROS 2 environment. The system overview is shown below.
- Camera: v4l2 compatible cameras, including TIER IV Automotive HDR Camera C1
- ECU: Jetson AGX Xavier based ECU, including RQX-58G from ADLINK Technology Inc. and Developer Kit from NVIDIA Corp.
- NVIDIA L4T: R32.6.1 (including Ubuntu 18.04)
- ROS: ROS 2 Humble (native build)
Please see Tutorials.
- tier4/edge-auto
- Meta-repository containing
autoware.repos
to construct ROS-based workspace on x86-based ECU.
- Meta-repository containing
- tier4/edge-auto-jetson
- Meta-repository containing
autoware.repos
file to construct ROS-based workspace on Jetson-based ECU.
- Meta-repository containing
- tier4/edge_auto_launch
- Launch configuration repository containing node configurations and their parameters for x86-based ECU.
- tier4/edge_auto_jetson_launch
- Launch configuration repository containing node configurations and their parameters for Jetson-based ECU.
- tier4/edge_auto_individual_params
- Repository for managing system parameters including camera parameters, driver parameters, etc.
- tier4/nebula
- ROS 2 package for unified ethernet-based LiDAR driver.
- tier4/tier4_automotive_hdr_camera
- Kernel driver for using TIER IV cameras with Video4Linux2 interface.
- tier4/ros2_v4l2_camera
- ROS 2 package for camera driver using Video4Linux2.
- tier4/sensor_trigger
- ROS 2 package for generating sensor trigger signals.
- tier4/calibration_tools
- Repository for calibration tools to estimate parameters on autonomous driving systems.
- autowarefoundation/autoware.universe
- Repository for experimental, cutting-edge ROS packages for autonomous driving.