STEB-Planner is a spatio-temporal elastic bands-based trajectory planner for autonomous vehicles using semantic graph optimization
The paper of this method is submitted to the IEEE Robotics and Automation Letters (RA-L)
Scenario 1: Static Obstacle Avoidance |
Scenario 2: Static Obstacle Avoidance |
GIF playback speed is 1.6 times. More scenes will be uploaded later.
Scenario 3: Overtaking a slow car ahead |
|
Scenario 4: Unprotected Left Turn |
Scenario 5: Merge Into the Traffic |
Scenario 4: Unprotected Left Turn |
Our software is developed and tested in Ubuntu20.04 with ROS2 galactic. Follow this link to install galactic.
- Eigen3
- PCL
- OpenCV
We use Carla-0.9.15 as the simulator (download via this link).
To use the Carla PythonAPI, you need to export the path or install it
export CARLA_ROOT=<path-to-carla>
export PYTHONPATH=$PYTHONPATH:/carla_directory/PythonAPI/carla/dist/carla-0.9.15-py3.7-linux-x86_64.egg
# Download
cd ~/your_workspace/src
git clone https://github.com/heshanchuan/STEB-Planner.git
# Compile
cd ../
source /opt/ros/galactic/setup.bash
colcon build --symlink-install --cmake-args -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DCMAKE_BUILD_TYPE=Release
source install/setup.bash
ros2 launch steb_planner steb_planner_test.launch.xml
Notes: 1.0.0 will be our first elegant version.
- 0.1
- CHANGE: First upload readme and some multimedia files
- Fork it (https://github.com/heshanchuan/STEB-Planner/fork)
- Create your feature branch (
git checkout -b feature/fooBar
) - Commit your changes (
git commit -am 'Add some fooBar'
) - Push to the branch (
git push origin feature/fooBar
) - Create a new Pull Request
The source code is released under MIT license.
This is research code, it is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of merchantability or fitness for a particular purpose.