A Real-time Prediction Algorithm for Driver Torque Demand based on Vehicle-Vehicle Communication

In our country, with the continuous growth of car ownership and the rapid development of new energy vehicles and hybrid electric vehicles, people’s demand for reducing pollution gas emissions and energy consumption is increasing day by day. Driver demand torque prediction is widely used in energy management optimization strategy, vehicle safety assistant driving and other fields. Therefore, accurate prediction of driver demand torque can not only effectively reduce energy consumption, but also improve the safety of driving process, which has important practical significance. In this paper, an autoregressive real-time torque prediction algorithm based on V2V information is proposed. On the basis of single input real-time autoregressive prediction model, the input of other influencing factors are added, the comprehensive information of torque including torque, front vehicle speed, distance and so on. The simulation results show that the real-time autoregressive torque prediction algorithm based on vehicle-to-vehicle (V2V) information can take into account the information of vehicles around the traffic environment and the information between vehicles, and provide a more comprehensive reference for the torque prediction, and can effectively improve the prediction accuracy.