Driver driving style classification method based on fuzzy C-means clustering algorithm

Abstract

The invention discloses a driver driving style classification method based on a fuzzy C-means clustering algorithm. The method comprises the following steps: firstly collecting the real-time driving data of a driver through a driving simulator, carrying out the preliminary screening of experimental data, and removing invalid data; then performing preliminary clustering based on a fuzzy C-means clustering algorithm: taking the reaction time and the vehicle following time interval as input variables, and outputting a preliminary driving style; and finally, on the basis of the preliminary clustering, introducing a transient index speed fluctuation standard deviation for re-clustering, and outputting a re-clustered driving style by taking the reaction time, the vehicle following speed and thespeed fluctuation standard deviation as input variables. According to the method, the adopted characteristic indexes are large in significant difference, the classification algorithm is simple, the classification effect is good, the driving styles of different drivers are comprehensively considered, and the driving styles of most drivers can be covered.

Description

technical field [0001] The invention relates to the technical field of driving style classification, in particular to a driver's driving style classification method based on a fuzzy C-means clustering algorithm. Background technique [0002] There are obvious differences among drivers of different styles in the frequency of overtaking and changing lanes, rapid acceleration / deceleration, speed fluctuation, steering wheel angular velocity fluctuation, close-range car following and other behaviors, and affect the frequency of dangerous driving behaviors. Aggressive, the greater the possibility of traffic accidents, the frequency of rear-end collisions or conflicts of aggressive drivers is more than 4 times that of normal drivers, more research results have verified that there is a significant correlation between differences in driving style and driving risk . [0003] In recent years, with the vigorous development of intelligent driving vehicles, the research on driver charact...

AI Technical Summary

Problems solved by technology

[0006] First, the driving style is evaluated by means of self-filled questionnaires and expert scoring, which is too subjective and subject to interference from external factors. It requires high validity of the questionnaire and expert experience, and the result judgment is not accurate enough.

[0007] Second, the amount of data extracted based on real vehicle driving experiments is huge and complex, and the post-processing is difficult and dangerous, and the external environment has a great influence on the experimental results

[0008] Third, the classification of driving styles is relatively simple and cannot cover most drivers

[0009] Fourth, the evaluation indicators for the classification of driving styles are single, and the classification results are not convincing enough

Images