A collection and interface for CommonRoad-based prediction algorithms.
Currently implemented and tested models:
- Constant Velocity Linear Predictor [1]
- Constant Velocity Curvilinear Predictor [1]
- Constant Acceleration Linear Predictor [1]
- Constant Acceleration Curvilinear Predictor [1]
In development:
- Intelligent Driver Model (IDM) Predictor [2]
- Lane-Changing Model MOBIL Predictor [3]
We highly welcome your contribution. If you want to contribute a prediction algorithm, please create an issue/pull request in our GitHub repository.
We recommend to use PyCharm (Professional) as IDE.
We provide an PyPI package which can be installed with the following command
pip install commonroad-predictionIt is recommended to use poetry as an environment manager. Clone the repository and install it with poetry.
git clone [email protected]:commonroad/commonroad-prediction.git
poetry shell
poetry installWe recommend to use PyCharm (Professional) as IDE. An example script for visualizing predictions is provided here.
You can generate the documentation within your activated Poetry environment using.
poetry shell
mkdocs buildThe documentation will be located under site, where you can open index.html in your browser to view it.
For updating the documentation you can also use the live preview:
poetry shell
mkdocs serveResponsible: Roland Stolz, Sebastian Maierhofer
The implemented algorithms are based on the subsequent publications:
[1] R. Schubert, E. Richter and G. Wanielik, "Comparison and evaluation of advanced motion models for vehicle tracking," Proc. of the IEEE Int. Conf. on Information Fusion, 2008, pp. 1-6.
[2] M. Treiber, A. Hennecke, and D. Helbing, "Congested traffic states in empirical observations and microscopic simulations," Physical Review E, vol. 62, no. 2, pp. 1805–1824, 2000.
[3] A. Kesting, M. Treiber, and D. Helbing, “General lane-changing model MOBIL for car-following models,” Transportation Research Record, vol. 1999, pp. 86–94, Jan. 2007