For the personification of automotive vehicle function performance under common traffic scenarios, analysis of human driver behavior is necessary. Based on China Field Operational Test (China-FOT) database of China Natural Driving Study project, this paper studies the driver's response in the common cut-in scenario. A total of 266 cut-in cases are selected by manual interception of driving recorder video. The relevant traffic environment characteristics are also extracted from video, including light conditions, road conditions, scale and lateral position of cut-in vehicle, etc. Dynamic information is decoded form CAN, such as speed, acceleration and so on. Then image processing results, such as relative speed and distance of cut-in and subject vehicles, are calculated. Statistical results based on above information show the response type and distribution of human driver: the behavior of keeping lane is 96.24%, in which the ratio of braking response is 51.13%. According to this, we choose to further research the behavior of keeping lane, and analyze the influencing factors of braking response. Statistical methods, such as Chi-square test, Spearman correlation test, are used to verify the relativity between the factor introduced above and braking. And test results indicated traffic flow, cut-in vehicle type, relative speed and distance of two vehicles are significantly correlated with the driver's braking response. Finally, a logistic regression model of the braking response probability is established with the relevant parameter. The model shows the braking probability of human drivers, when faced with cut-in vehicle.
Analysis of the Driver’s Breaking Response in the Safety Cut-in Scenario Based on Naturalistic Driving
Sae Technical Papers
New Energy & Intelligent Connected Vehicle Technology Conference ; 2019
2019-11-04
Aufsatz (Konferenz)
Englisch
Driver's Response Prediction Using Naturalistic Data Set
British Library Conference Proceedings | 2019
|Driver’s Response Prediction Using Naturalistic Data Set
SAE Technical Papers | 2019
|SceNDD: A Scenario-based Naturalistic Driving Dataset
IEEE | 2022
|