I. We propose 3CSim for control assessment of AD models
in controlled and deterministic environment.
II. We propose a taxonomy of advanced corner case scenarios implemented in our proposed simulation.
We present the CARLA corner case simulation (3CSim) for evaluating autonomous driving (AD) systems within the CARLA simulator. This framework is designed to address the limitations of traditional AD model training by focusing on non-standard, rare, and cognitively challenging scenarios. These corner cases are crucial for ensuring vehicle safety and reliability, as they test advanced control capabilities under unusual conditions. Our approach introduces a taxonomy of corner cases categorized into state anomalies, behavior anomalies, and evidence-based anomalies. We implement 32 unique corner cases with adjustable parameters, including 9 predefined weather conditions, timing, and traffic density. The framework enables repeatable and modifiable scenario evaluations, facilitating the creation of a comprehensive dataset for further analysis.
The dataset can be downloaded using the link.
If you use this code or ideas from the paper for your research, please cite our paper:
@INPROCEEDINGS{cavojsky20243csim,
author={Čavojsky, Matúš and Slapak, Eugen and Dopiriak, Matúš and Bugar, Gabriel and Gazda, Juraj},
booktitle={2024 IEEE 8th International Conference on Information and Communication Technology (CICT)},
title={3CSim: CARLA Corner Case Simulation for Control Assessment in Autonomous Driving},
year={2024},
volume={},
number={},
pages={1-6},
keywords={Training;Measurement;Taxonomy;Vehicle safety;Focusing;Timing;Information and communication technology;Reliability;Autonomous vehicles;Meteorology;autonomous driving;CARLA simulator;corner cases;reinforcement learning},
doi={10.1109/CICT64037.2024.10899666}}