This paper presents a novel identification method of driver steering characteristics based on backpropagation neural network. First, a driving simulator is built to collect required driving data. After careful analysis, three feature parameters that reflect driver steering characteristics are determined, including the average steering wheel angular speed, the standard deviation of the steering wheel angle, and the average vehicle longitudinal speed. Then, steering feature parameter vectors are extracted from raw data and clustered by the K-means algorithm. According to the clustering result, driver steering characteristics are divided into three types: cautious, average, and aggressive. Subsequently, a backpropagation neural network with two hidden layers is designed and trained to identify the types of feature parameter vectors. Verification results show that the established backpropagation neural network has high identification accuracy and good generalization ability for the identification of driver steering characteristics.
An identification algorithm of driver steering characteristics based on backpropagation neural network
2019-08-01
10 pages
Article (Journal)
Electronic Resource
English
Adaptive Neural Control with Backpropagation Algorithm
British Library Conference Proceedings | 1994
|Mapping with a Backpropagation Neural Network
British Library Conference Proceedings | 1994
|Study on Thermal Comfort Model Based on Genetic Algorithm with Backpropagation Neural Network
Springer Verlag | 2019
|Performance of Neural Network Models Without Backpropagation
Springer Verlag | 2025
|