This work introduces interactive traffic scenarios in the CARLA simulator, which are based on real-world traffic. We concentrate on tactical tasks lasting several seconds, which are especially challenging for current control methods. The CARLA Real Traffic Scenarios (CRTS) is intended to be a training and testing ground for autonomous driving systems. To this end, we open-source the code under a permissive license and present a set of baseline policies. CRTS combines the realism of traffic scenarios and the flexibility of simulation. We use it to train agents using a reinforcement learning algorithm. We show how to obtain competitive polices and evaluate experimentally how observation types and reward schemes affect the training process and the resulting agent's behavior.
@article{arxiv.2012.11329,
title = {CARLA Real Traffic Scenarios -- novel training ground and benchmark for autonomous driving},
author = {Błażej Osiński and Piotr Miłoś and Adam Jakubowski and Paweł Zięcina and Michał Martyniak and Christopher Galias and Antonia Breuer and Silviu Homoceanu and Henryk Michalewski},
journal= {arXiv preprint arXiv:2012.11329},
year = {2021}
}