CARLA Real Traffic Scenarios -- novel training ground and benchmark for autonomous driving
This work provides a new, open-source training and testing environment for autonomous driving systems, specifically targeting challenging tactical tasks, which could benefit researchers and developers in the field.
This paper introduces CARLA Real Traffic Scenarios (CRTS), a new set of interactive traffic scenarios in the CARLA simulator derived from real-world traffic data, designed to train and test autonomous driving systems on tactical tasks. The authors demonstrate how to train competitive policies using reinforcement learning and analyze the impact of observation types and reward schemes on agent behavior.
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.