Control for Intelligent Connected Vehicles Platoon Based on Deep Convolutional Generative Adversarial Networks

With the help of the Internet of Vehicles (IoV), Intelligent Connected Vehicles Platoon can improve vehicles’ safety, reduce fuel consumption, and decrease air pollution. This paper proposes a control model for Intelligent Connected Vehicles Platoon (ICVP) based on Deep Convolutional Generative Adversarial Networks (ICV-DCGAN). On one hand, vehicles’ carbon emissions and fuel consumption are used as performance indicators for evaluating air pollution. Conversely, the time to collision (TTC) and the time to reach the current position of the vehicle ahead (TIV) are used as performance indicators to detect vehicle driving safety. Experimental results show that the model can adapt to the complex urban roads in China, and the ICVP controlled by the model can respond early to changes on the road and ensure the safety of the platooning. At the same time, the model also can avoid unnecessary braking and down to reduce the carbon emissions and fuel consumption of vehicles. Finally, the model realizes low-carbon intelligent travel.