A Control Testing Framework for automated driving functionalities using modular architecture with ROS/CARLA environment

Interest in Automated Vehicles (AV) has increased in the last years due to the need of providing more efficient and safe transportation systems. However, the development of AV functionalities is a complex task, as multiple technologies have to be tested and integrated to fulfill the required automation level. Moreover, the number of different scenarios that have to be dealt with Cooperative and Connected Automated Mobility (CCAM) solutions makes traditional track testing a non-optimal approach. Due to this, in recent years interest in the development of simulation-based testing frameworks has arisen, with open-source and commercial solutions trying to fulfill the requirements of AV development. This work introduces an automated vehicle testing framework that combines the widely used open-source simulation environment CARLA with a self-developed modular control framework AUDRIC. The communication between both is made using the ROS environment. The proposed approach provides the advantages of both environments in terms of flexibility and modularity, allowing the development of automated functionalities for the different modules of AV architecture. The validity of the approach is demonstrated by presenting two use cases: a lane following application and an obstacle avoidance scenario.