Simulating use cases for the UAH autonomous electric car

Abstract

This paper presents the simulation use cases for the UAH Autonomous Electric Car, related with typical driving scenarios in urban environments, focusing on the use of hierarchical interpreted binary Petri nets in order to implement the decision making framework of an autonomous electric vehicle. First, we describe our proposal of autonomous system architecture, which is based on the open source Robot Operating System (ROS) framework that allows the fusion of multiple sensors and the real-time processing and communication of multiple processes in different embedded processors. Then, the paper focuses on the study of some of the most interesting driving scenarios such as: stop, pedestrian crossing, Adaptive Cruise Control (ACC) and overtaking, illustrating both the executive module that carries out each behaviour based on Petri nets and the trajectory and linear velocity that allows to quantify the accuracy and robustness of the architecture proposal for environment perception, navigation and planning on a university Campus.