Statistical Verification Framework for Platooning System of Systems with Uncertainty

Abstract

Platooning system is a well-known technology for alleviating traffic congestion and increasing fuel efficiency by grouping vehicles. It has the major characteristics of Systems of Systems (SoS), such as uncertainty. Several internal and external factors of uncertainty exist in the platooning system, such as car accidents, network disconnections, and simultaneous requests from other platoons. These factors make it difficult to guarantee that the system operates correctly in unpredictable scenarios and environments. The existing techniques used to verify the platooning system have two limitations: 1) the lack of consideration of uncertainty in scenarios and environments; 2) the application of exhaustive verification techniques which are vulnerable to the state-explosion problem. Thus, we suggest a statistical verification framework for a platooning SoS to address the above two limitations. The proposed framework automatically generates platooning configurations and scenarios with internal and external uncertain factors considered, and bypasses the state-explosion problem using a statistical verification technique. In this study, experimental results showed that the proposed approach generates 50% more valid scenarios than pure random strategy. In addition, we found two types of undiscovered failures and their causes in the VENTOS platooning system. These results indicate that our approaches enable the deep analysis of the platooning management system.