Platooning is highly tractable for enabling fuel savings for autonomous and semi-autonomous cars and trucks. Safety concerns are one of the main impediments that need to be overcome before vehicle platoons can be deployed on ordinary roads despite their readily available technical feasibility. Simulation studies remain vital for evaluating platoon safety applications primarily due to the high cost of field tests. To this end, we present PlatoonSAFE, an open-source simulation tool that promotes the simulation studies of fault tolerance in platooning by enabling the monitoring of transient communication outages during runtime and assigning an appropriate performance level as a function of the instantaneous communication quality. In addition, PlatoonSAFE facilitates the simulation of several emergency braking strategies to evaluate their efficacy in transitioning a platoon to a fail-safe state. Furthermore, two Machine Learning (ML) models are integrated into PlatoonSAFE that can be employed as an onboard prediction tool in the platooning vehicles to facilitate online training of ML models and real-time prediction of communication, network, and traffic parameters. In this paper, we present the PlatoonSAFE structure, its features and implementation details, configuration parameters, and evaluation metrics required to evaluate the fault tolerance of platoon safety applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.