CommonRoad-CriMe
Automotive manufacturers must ensure that autonomous vehicles can recognize and effectively handle unexpected situations. To effortlessly measure and compare the criticality of an autonomous vehicle, we present the novel CommonRoad CriMe (Criticality Measures) toolbox, which:
provides a framework in Python with unified notations, vehicle models, and coordinate systems for criticality measures;
adopts and supplements the categorization of criticality measures defined in this collection;
is open-source and allows users to easily modify, add, and compare criticality measures;
offers efficient and reliable computation by bridging to powerful scenario evaluation tools.
Installation
commonroad-crime can be installed with:
pip install commonroad-crime
For adding new measures, we recommend using Anaconda to manage your environment so that even if you mess something up, you can always have a safe and clean restart. A guide for managing python environments with Anaconda can be found here.
After installing Anaconda, create a new environment with:
conda create -n commonroad-py38 python=3.8 -y
Here the name of the environment is called commonroad-py38. You may also change this name as you wish. In such case, don’t forget to change it in the following commands as well. Always activate this environment before you do anything related:
conda activate commonroad-py38
or
source activate commonroad-py38
Then, install the dependencies with:
cd <path-to-this-repo>
pip install -e .
conda develop .
To test the installation, run unittest:
cd tests
python -m unittest -v
Overview
Citation
@InProceedings{lin2023crime,
title = {{CommonRoad-CriMe}: {A} Toolbox for Criticality Measures of Autonomous Vehicles},
author = {Yuanfei Lin and Matthias Althoff},
booktitle = {Proc. of the IEEE Intell. Veh. Symp.},
pages = {1-8},
year = {2023},
}
Contact information
- Release:
0.4.0
- Date:
May 10, 2024
- Website:
- Forum:
- Email: