A Driver Intention Recognition Method Based on Fuzzy Neural Networks

Driving intention recognition is significant for intelligent driving and control strategies of electric vehicles. It still has a remarkable drawback to developing an accuracy model for recognition of the driver’s intention in real-time applications. In this paper, a neural network-based fuzzy model is established based on abundant actual driving data to generate driving intention fuzzy inference rules for accurate identification of the driver’s acceleration and the deceleration intention. The results demonstrate that driving intention recognition can be achieved exactly, and the fuzzy inference rules obtained by the proposed method can adequately identify the driver’s intention. Moreover, the control strategy of the electric vehicle can be efficiently optimized to further improve the economy.