meta-repository for Autoware architecture proposal version

This is the source code of the feasibility study for Autoware architecture proposal.

WARNING: This source is solely for demonstrating an architecture proposal. It should not be used to drive cars.

NOTE: The features in autoware.iv.universe will be merged into Autoware.Auto.

Architecture overview is here.

• x86 CPU (8 or more cores)
• 16 GB or more of memory
• Nvidia GPU (4GB or more of memory)

If cuda or tensorRT is already installed, it is recommended to remove it.

• Ubuntu 18.04
• Nvidia driver

If cuda or tensorRT is already installed, it is recommended to remove it.

1. Set up the repository

If ROS hasn't been installed yet in PC, at first run commands of 1.2 ~ 1.4, described in ROS wiki.

sudo sh -c 'echo "deb http://packages.ros.org/ros/ubuntu $(lsb_release -sc) main" > /etc/apt/sources.list.d/ros-latest.list'
sudo apt-key adv --keyserver 'hkp://keyserver.ubuntu.com:80' --recv-key C1CF6E31E6BADE8868B172B4F42ED6FBAB17C654
sudo apt update

Set up the repository

sudo apt install -y python3-vcstool
git clone [email protected]:tier4/AutowareArchitectureProposal.git
cd AutowareArchitectureProposal
mkdir -p src
vcs import src < autoware.proj.repos

2. Run the setup script

./setup_ubuntu18.04.sh

In this step, the following software are installed.
Please confirm their licenses before using them.

• osqp
• ROS Melodic
• CUDA 10.2
• cuDNN 7
• TensorRT 7

3. Build the source

source ~/.bashrc
colcon build --cmake-args -DCMAKE_BUILD_TYPE=Release --catkin-skip-building-tests

Prepare launch files and vehicle_description according to the sensor configuration of your hardware.
The following are the samples.

• sensing.launch
• lexus_description

1. Download sample map from here.

2. Download sample rosbag from here.

3. Launch Autoware

cd AutowareArchitectureProposal
source install/setup.bash
roslaunch autoware_launch logging_simulator.launch map_path:=[path] vehicle_model:=lexus sensor_model:=aip_xx1 rosbag:=true

* Absolute path is required for map_path.

4. Play rosbag

rosbag play --clock [rosbag file] -r 0.2

• sample map : © 2020 TierIV inc.
• rosbag : © 2020 TierIV inc.
  • Image data are removed due to privacy concerns.
    • Cannot run traffic light recognition
    • Decreased accuracy of object detection

1. Download sample map from here.

2. Launch Autoware

cd AutowareArchitectureProposal
source install/setup.bash
roslaunch autoware_launch planning_simulator.launch map_path:=[path] vehicle_model:=lexus sensor_model:=aip_xx1

* Absolute path is required for map_path.

3. Set initial pose
4. Set goal pose
5. Push engage button. autoware_web_controller

• sample map : © 2020 TierIV inc.

We are planning propose the architecture and reference implementation to AutowareAuto. For the time being, use ros_bridge if you wish to use this repository with AutowareAuto modules. You would have to do the message type conversions in order to communicate between AutowareAuto and AutowareArchitectureProposal modules until the architecture is aligned.

For setting up AutowareAuto, please follow the instruction in: https://gitlab.com/autowarefoundation/autoware.auto/AutowareAuto

For setting up ros_bridge, please follow the instruction in: https://github.com/ros2/ros1_bridge

See here. for more information.

• Scenario demo
• Obstacle avoidance in the same lane
• Obstacle avoidance by lane change
• Object recognition
• Auto parking
• 360° FOV perception(Camera Lidar Fuison)
• Robustness of localization

• Neural Network Weight Files