An Aggregation Degree-Based Cooperative Model for Autonomous Vehicle Groups in a Closing Scene

Abstract

Maintaining stable and orderly intelligent autonomous driving behavior in a closing scene is an important challenge. Compared with traditional chaos caused by an individual autonomous vehicle based on central control, when it breaks down, an intelligent cooperative autonomous driving group may effectively mitigate or alleviate the issue. There is no method to formulate an autonomous vehicle group and analyze its cooperative behavior by taking the aggregation, leading node change rate, and algorithm complexity of a vehicle group into account. This work formulates an aggregation degree-based Cooperative Model for Autonomous Vehicle Groups in a closing scene (CMAVG). First, we construct multi-roles and hierarchical autonomous vehicle groups. Then, we analyze their evolution behavior and present a dynamic evolution method based on it. Finally, we formulate CMAVG and give its solving method. We conduct extensive simulations in a simulated closing scene and a real one. Experimental results show that our autonomous vehicle group formation method outperforms a VANET clustering method and an autonomous vehicle group formation method in terms of aggregation degree, running time, and leading node change rate. CMAVG outperforms two cooperation methods for Internet of vehicles and an autonomous vehicle group cooperation method in terms of aggregation degree, leading node change rate, and vehicle group survival time.