Model for the cooperative obstacle-avoidance of the automated vehicle swarm in a connected vehicles environment

Abstract

The obstacle-avoidance problem of automated vehicles is a hot topic in the community of autonomous driving. The majority of the existing studies focused on the obstacle-avoidance of a single automated vehicle. The connected vehicles technology provides the possibility of controlling a vehicle swarm to avoid the obstacle cooperatively. Through cooperation, the vehicle swarm not only can avoid an obstacle safely but also can minimize traffic delays. Therefore, this paper proposes a cooperative obstacle-avoidance model for the automated vehicle swarm driving on the freeway based on the A2C reinforcement learning. The proposed model considers the efficiencies of both the individual and swarm in the learning, and a cooperative lane-changing execution model is proposed to ensure that the optimal decision made by the A2C algorithm can be performed by the vehicles. Furthermore, simulations are conducted to verify the proposed model. The results indicate that the proposed model can significantly improve the overall traffic efficiency compared with the existing models. In a congested state, when the proposed model is applied to control vehicles, an optimal control range can be found (i.e. 700 m here), and within this optimal range, the traffic efficiency increases with the increment of the number of the vehicles controlled by the proposed model.