Research on personalized driving behavior characteristics has an important impact on the development and progress of intelligent driving technology. In order to explore the traffic characteristics of drivers driving through unsignalized intersections, test data of 95 road transport drivers driving through intersections was collected by using a driving simulator. K-means clustering was used to achieve the clustering of different driving risk, and the optimal clustering index and number were selected with the help of silhouette coefficient. Finally, the single factor analysis of variance (ANOVA) was used to verify the effectiveness of the clustering results. The research shows that the clustering effect is the best when using the average driving speed and maximum pedal travel change rate as clustering indexes, and clustering into three categories. The ANOVA test shows that there are significant differences among the three types of driving risk. Low driving risk is to travel at a lower speed through intersection and at the same time to maintain slow down operation. High driving risk is to travel at a higher speed through intersection and prone to sharp deceleration.
Study on Driving Risk Through Unsignalized Intersection
Lect. Notes Electrical Eng.
International Conference on Artificial Intelligence and Autonomous Transportation ; 2024 ; Beijing, China December 06, 2024 - December 08, 2024
The Proceedings of 2024 International Conference on Artificial Intelligence and Autonomous Transportation ; Chapter : 4 ; 43-51
2025-04-19
9 pages
Article/Chapter (Book)
Electronic Resource
English
Unsignalized Intersection Simulation Model InterSim
British Library Conference Proceedings | 1997
|Interim materials on unsignalized intersection capacity
TIBKAT | 1991
|ITE TO HOST THE UNSIGNALIZED INTERSECTION IMPROVEMENT GUIDE
Online Contents | 2015