Driver support and infotainment systems can be adapted to the specific needs of individual drivers by assessing driver skill and state. In this paper, we present a machine learning approach to classifying the skill at...Driver support and infotainment systems can be adapted to the specific needs of individual drivers by assessing driver skill and state. In this paper, we present a machine learning approach to classifying the skill at maneuvering by drivers using both longitudinal and lateral controls in a vehicle. Conceptually, a model of drivers is constructed on the basis of sensor data related to the driving environment, the drivers＇ behaviors, and the vehi- cles＇ responses to the environment and behavior together. Once the model is built, the driving skills of an unknown driver can be classified automatically from the driving data. In this paper, we demonstrate the feasibility of using the proposed method to assess driving skill from the results of a driving simulator. We experiment with curve driving scenes, using both full curve and segmented curve sce- narios. Six curves with different radii and angular changes were set up for the experiment. In the full curve driving scene, principal component analysis and a support vector machine-based method accurately classified drivers in 95.7 % of cases when using driving data about high- and low/average-skilled driver groups. In the cases with seg- mented curves, classification accuracy was 89 %.展开更多
The previous research (Danno & Taniguchi, 2015) showed that near-miss incident experience was basically reduced by the Empathy Quotient (EQ) and was disturbed by the Systemizing Quotient (SQ) when the Empathy Quot...The previous research (Danno & Taniguchi, 2015) showed that near-miss incident experience was basically reduced by the Empathy Quotient (EQ) and was disturbed by the Systemizing Quotient (SQ) when the Empathy Quotient was low, based on the Empathizing and Systemizing (E-S) model using a web survey [1]. It means that drivers whose EQ was low and SQ was high had more near-miss incident experience. It suggested that drivers who have a stronger Empathizing function may have stronger hazard perception ability although the Systemizing function may weaken hazard perception ability when Empathizing is weak. And, then, it was revealed that the D score (standard SQ (T) score minus standard EQ (T) score) had a significant effect on the near-miss incident experience. Those results implied that a D score, which is used to classify “E-S types”, should have a relationship with near-miss incident experience, i.e. , hazard perception ability. The EQ and SQ scores were supposed to relate to the cognitive ability to estimate other road users’ mental situations and predict their behavior or to recognize stable laws in traffic situations. The aim of this research was to investigate the relationship between a driver’s visual attention ability (gaze movement) and hazard (near-miss incident) perception ability of different EQ and SQ scores. Drivers’ Real-time Useful Field of View (rUFOV) [2] was measured under normal and hasty driving conditions in a driving simulator which had six scenarios of traffic situation. The result from seven participants who had different EQ and SQ scores showed that a driver’s visual attention ability (gaze movement) corresponds to their scores. This pilot test research revealed a possibility that the individual difference in cognitive trait with E-S model could be a promising tool to understand the mechanism of hazard perception since a D score is used to classify “E-S types”.展开更多
文摘Driver support and infotainment systems can be adapted to the specific needs of individual drivers by assessing driver skill and state. In this paper, we present a machine learning approach to classifying the skill at maneuvering by drivers using both longitudinal and lateral controls in a vehicle. Conceptually, a model of drivers is constructed on the basis of sensor data related to the driving environment, the drivers＇ behaviors, and the vehi- cles＇ responses to the environment and behavior together. Once the model is built, the driving skills of an unknown driver can be classified automatically from the driving data. In this paper, we demonstrate the feasibility of using the proposed method to assess driving skill from the results of a driving simulator. We experiment with curve driving scenes, using both full curve and segmented curve sce- narios. Six curves with different radii and angular changes were set up for the experiment. In the full curve driving scene, principal component analysis and a support vector machine-based method accurately classified drivers in 95.7 % of cases when using driving data about high- and low/average-skilled driver groups. In the cases with seg- mented curves, classification accuracy was 89 %.
文摘The previous research (Danno & Taniguchi, 2015) showed that near-miss incident experience was basically reduced by the Empathy Quotient (EQ) and was disturbed by the Systemizing Quotient (SQ) when the Empathy Quotient was low, based on the Empathizing and Systemizing (E-S) model using a web survey [1]. It means that drivers whose EQ was low and SQ was high had more near-miss incident experience. It suggested that drivers who have a stronger Empathizing function may have stronger hazard perception ability although the Systemizing function may weaken hazard perception ability when Empathizing is weak. And, then, it was revealed that the D score (standard SQ (T) score minus standard EQ (T) score) had a significant effect on the near-miss incident experience. Those results implied that a D score, which is used to classify “E-S types”, should have a relationship with near-miss incident experience, i.e. , hazard perception ability. The EQ and SQ scores were supposed to relate to the cognitive ability to estimate other road users’ mental situations and predict their behavior or to recognize stable laws in traffic situations. The aim of this research was to investigate the relationship between a driver’s visual attention ability (gaze movement) and hazard (near-miss incident) perception ability of different EQ and SQ scores. Drivers’ Real-time Useful Field of View (rUFOV) [2] was measured under normal and hasty driving conditions in a driving simulator which had six scenarios of traffic situation. The result from seven participants who had different EQ and SQ scores showed that a driver’s visual attention ability (gaze movement) corresponds to their scores. This pilot test research revealed a possibility that the individual difference in cognitive trait with E-S model could be a promising tool to understand the mechanism of hazard perception since a D score is used to classify “E-S types”.
