The study of driver’s driving intention is of great significance to improve vehicle safety warning technology, auxiliary driving technology and optimization of vehicle control strategy. By analyzing the driving environment data collected by the Internet of vehicles monitoring platform, the driving environment perception model based on the long-term memory network (LSTM) is established to judge the driving environment. After that, the symbolized environmental result combined with vehicle state parameters collected by the sensors are used as input to the driving intention identification model based on LSTM. Then the dynamic driving behavior and driving intention of the driver are analyzed. The results show that, based on the dynamic model LSTM, the driving intention identification model considering the driving environment produce a higher accuracy.
Driving Intention Identification Model Based on Long and Short-Term Memory Network
20th COTA International Conference of Transportation Professionals ; 2020 ; Xi’an, China (Conference Cancelled)
CICTP 2020 ; 2392-2402
2020-12-09
Conference paper
Electronic Resource
English
Driver driving behavior automatic analysis method based on long-term and short-term memory network
European Patent Office | 2020
|Long short‐term memory and convolutional neural network for abnormal driving behaviour recognition
Wiley | 2020
|