No abstract

Driver hazard perception is highly related to involvement in traffic accidents, and vision is the most important sense with which we perceive risk. Therefore, it is of great significance to explore the characteristics of drivers’ eye movements to promote road safety. This study focuses on analyzing the changes of drivers’ eye-movement characteristics in anxiety. We used various materials to induce drivers’ anxiety, and then conducted the real driving experiments and driving simulations to collect drivers’ eye-movement data. Then, we compared the differences between calm and anxiety on drivers’ eye-movement characteristics, in order to extract the key eye-movement features. The least squares method of change point analysis was carried out to detect the time and locations of sudden changes in eye movement characteristics. The results show that the least squares method is effective for identifying eye-movement changes of female drivers in anxiety. It was also found that changes in road environments could cause a significant increase in fixation count and fixation duration for female drivers, such as in scenes with traffic accidents or sharp curves. The findings of this study can be used to recognize unexpected events in road environment and improve the geometric design of curved roads. This study can also be used to develop active driving warning systems and intelligent human–machine interactions in vehicles. This study would be of great theoretical significance and application value for improving road traffic safety.

Anxiety is a common emotion of driver, which always affects the safety of driving. Eye movement characteristics can be used to understand the true emotion state of human beings. It is of great significance to study the law of eye movement for realizing active vehicle safety warning and human-machine cooperation. In this article, anxiety-induction experiment, real-vehicle driving experiments, and virtual driving experiments were designed and used to obtain the eye movement data of female novice extroversion driver under calm and anxiety, and mathematical statistics analysis was made on the fixation count, fixation duration, and visit duration in the area of interest within the driver horizon. The results showed that there are significant differences in fixation count and fixation duration of drivers (p\0:05, p is the accompanying probability), and the main effect of emotion is significant (p\0:05).Compared with the situation of calm, fixation area, fixation count, and fixation duration of drivers under anxiety were more focused on the middle area, the fixation count and visit duration on the left area were relatively more, the fixation duration on the right area was relatively longer, and anxiety was more likely to cause driver's attention bias.

Purpose This study aims to analyze the differences of electrocardiograph (ECG) characteristics for female drivers in calm and anxious states during driving. Design/methodology/approach The authors used various materials (e.g. visual materials, auditory materials and olfactory materials) to induce drivers’ mood states (calm and anxious), and then conducted the real driving experiments and driving simulations to collect driver’s ECG signal dynamic data. Physiological changes in ECG during the stimulus process were recorded using PSYLAB software. The paired T-test analysis was conducted to determine if there is a significant difference in driver’s ECG characteristics between calm and anxious states during driving. Findings The results show significant differences in the characteristic parameters of female driver’s ECG signals, including (average heart rate), (atrioventricular interval), (percentage of NN intervals > 50ms), (R wave average peak), (Root mean square of successive), (Q wave average peak) and ( S wave average peak), in time domain, frequency domain and waveform in emotional states of calmness and anxiety. Practical implications Findings of this work show that ECG can be used to identify driver’s anxious and calm states during driving. It can be used for the development of personalized driver assistance system and driver warning system. Originality/value Only a few attempts have been made on the influence of human emotions on physiological signals in the transportation field. Hence, there is a need for transport scholars to begin to identify driver’s ECG characteristics under different emotional states. This study will analyze the differences of ECG characteristics for female drivers in calm and anxious states during driving to provide a theoretical basis for developing the intelligent and connected vehicles.

Accurate identification of driving intention and reasonable control of driver's behavior is seen as an important mean to reduce man-made traffic accidents for the intelligent vehicle. However, the intention identification processes associated with driving emotion-related impact have received very little attention. With the aim of uncovering the emotional impact on driving intention identification, the car-following condition was taken as an example, and multi-source and dynamic data of human-vehicle-environment under different driving emotional states were obtained through the experiments of emotions induction, actual driving, and virtual driving in this study. The feature extraction and dynamic identification models based on rough set theory and back-propagation artificial neural network were built to recognize driving intentions. The results showed that there were some differences in driving intention identification under different emotional modes. The differences were mainly manifested in the complexity and accuracy of intention feature vectors. The rationality and validity of the intentions feature extraction and identification models were verified by the actual driving experiments, virtual driving experiments, and interactive simulation experiments. The research results can provide theoretic basis for the emotional intelligence research of advanced vehicle, driving assist systems, and unmanned vehicles.