This work presents the validation of our fully-autonomous driving architecture in the CARLA open-source simulator, by using some challenging driving scenarios inspired on the CARLA Autonomous Driving Challenge (CADC), focusing on our decision-making layer, based on Hierarchical Interpreted Binary Petri Nets (HIBPN). First, our ROS (Robot Operating System) based autonomous driving architecture is introduced. Second, the CARLA simulator is described, outlining the steps conducted to merge our architecture with this simulator and the advantages to create ad-hoc driving scenarios for use cases validation. Finally, the paper validates the architecture by means of some challenging driving scenarios such as: Stop, Pedestrian Crossing, Adaptive Cruise Control (ACC) and Unexpected Pedestrian. Some qualitative (video files) and quantitative (trajectory and linear velocity segmented with its corresponding Petri Net states) results are presented for each use case, validating our architecture in simulation as a preliminary stage before implementing it in our real autonomous electric car.
Train Here, Drive There: Simulating Real-World Use Cases with Fully-Autonomous Driving Architecture in CARLA Simulator
Advs in Intelligent Syst., Computing
Workshop of Physical Agents ; 2020 ; Alcalá de Henares, Madrid, Spain November 19, 2020 - November 20, 2020
2020-11-03
16 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Quantitative Evaluation of Autonomous Driving in CARLA
IEEE | 2021
|TIBKAT | 2021
|