Exploring road safety using alignment perspective features in real driving images: A case study on mountain freeways.

INTRODUCTION: While driving, drivers frequently adapt their driving behaviors according to their perception of the road's alignment features. However, traditional two-dimensional alignment methods lack the ability to capture these features from the driver's perspective. METHOD: This study introduces a novel method for road alignment recognition, employing image recognition technology to extract alignment perspective features, namely alignment perspective skewness (APS) and alignment perspective kurtosis (APK), from in-real driving images. Subsequently, the K-means clustering algorithm is utilized for road segment classification based on APS and APK indicators. Various sliding step length for clustering are employed, with step length ranging from 100m to 400m. Furthermore, the accident rates for different segment clusters are analyzed to explore the relationship between alignment perspective features and traffic safety. A 150 km mountain road section of the Erlianhaote-Guangzhou freewway from Huaiji to Sihui is selected as a case study. RESULTS: The results demonstrate that using alignment perspective features as classification criteria produces favorable clustering outcomes, with superior clustering performance achieved using shorter segment lengths and fewer cluster centers. The road segment classification based on alignment perspective features reveals notable differences in accident rates across categories; while traditional two-dimensional parameters-based classification methods fail to capture these differences. The most significant differences in accident rates across categories are observed with segment length of 100m, with the significance gradually diminishing as segment length increases and disappearing entirely when the length exceeds 300m. IMPLICATION: These findings validate the reliability of using alignment perspective features (APS and APK) for road alignment classification and road safety analysis, providing valuable insights for road safety management.

Influence of conventional driving habits on takeover performance in joystick-controlled autonomous vehicles: A low-speed field experiment.

Takeover is a critical factor in the safety of autonomous driving. Takeover refers to the action of a human driver assuming control of an autonomous vehicle from its automated driving system. This can occur when the vehicle encounters a situation it cannot handle, when the system requests the driver to take control, or when the driver chooses to intervene for safety or other reasons. This study explored how traditional steering-wheel driving habits affect takeover performance in joystick-controlled autonomous vehicles. We conducted an experiment using a joystick-controlled Dongfeng Sharing-VAN autonomous vehicle in a low-speed campus environment. The participants were divided into three groups based on their driving experience: the individuals who have no licence and no experience (NN Group), the drivers who have licence but not experienced (HN Group), and the drivers who have licence and have been experienced (HH Group), representing varying levels of driving habits. The experiment focused on two takeover tasks: passive takeover and active takeover. We evaluated takeover performance using takeover time and takeover quality as key metrics. The results from the passive takeover task indicated that traditional driving habits had a significant negative impact on takeover performance. The HH Group took 2.65 s longer to complete the task compared to the NN Group, while the HN Group took 3.78 s longer. When we analyzed takeover time in stages, the initial stage showed the most significant difference in takeover time among the three groups. In the active takeover task, driving habits did not significantly affect takeover braking in front of obstacles in a low-speed driving environment. These findings suggest that conventional driving habits can hinder passive takeover in joystick-controlled autonomous vehicles. This insight can be valuable for developing training programs and guidelines for drivers transitioning from conventional to autonomous driving.

A method for evaluating the safety of freeway tunnel sections based on driving comfort - a naturalistic driving study.

OBJECTIVE: Driving comfort is crucial for tunnel safety because tunnel sections on freeways often introduce significant environmental changes that can compromise comfort and increase the risk of traffic accidents. This study aimed to quantitatively evaluate the driving comfort in tunnel sections and its implications for safety management. METHODS: Four indicators were used to assess the driving comfort: heart rate growth rate (Hrgr), skin conductance response (SCR), speed, and acceleration. The CRITIC weighting method was employed to calculate a quantitative driving comfort score, and the presence and severity of discomfort were used to evaluate the safety of each tunnel area. In addition, the evaluation was based on a naturalistic test consisting of Hrgr, SCR, speed, and acceleration data. A total of 32 participants were recruited based on a web-based questionnaire screening process, after which they were tested while driving through 30 tunnel sections on the roadway. These 30 tunnels included 14 short (< 500 m), 12 medium (500-1,000 m), and 4 long (1,000-3,000 m) tunnels. RESULTS: The results revealed that the four selected indicators exhibited minimal multicollinearity and effectively captured the driving comfort. Among the indicators, SCR had the most significant contribution to the driving comfort score. Most drivers did not experience substantial discomfort while driving through tunnels. The area where drivers were most susceptible to discomfort was the middle zones of tunnels. However, drivers were more likely to experience strong discomfort in the outside exit, entrance, and middle zones of short, medium, and long tunnels, respectively. CONCLUSIONS: This study provides a comprehensive set of safety evaluation methods for tunnel sections on freeways, with a focus on quantifying the driving comfort. The findings provide theoretical support for freeway management personnel in implementing personalized controls in different tunnel areas with the aim of enhancing tunnel safety and mitigating the occurrence of traffic accidents.

Estimating mountainous freeway crash rate: Application of a spatial model with three-dimensional (3D) alignment parameters.

The road alignment is a three-dimensional (3D) curve in nature. In this study, we quantitatively examine the effect of 3D road alignment on traffic safety on mountainous freeways. Geometric parameters of 3D curvature and torsion in mathematics are derived to characterize the 3D road curve. Based on the coordination of different horizontal and vertical elements, 3D road alignment is divided into twelve types of combined alignment. For each alignment combination, the 3D curvature and torsion are calculated according to the differential geometry theory. Regarding crash statistical modeling, the Bayesian spatial Tobit (BST) model is developed to accommodate possible spatial correlation of traffic crashes among adjacent freeway segments. The Bayesian Tobit (BT) model is also built for comparison. A 118-km mountainous freeway associated road geometric features, traffic volume with three years of crash data is used as a case study. The result from the model comparison shows the BST model outperforms the BT model in terms of goodness-of-fit. Parameter estimation result for the BST model shows that the differences of average 3D curvature (and torsion) between adjacent segments have statistically significant effects on the crash rate of the segment, indicating it is necessary to consider three-dimensional alignment parameters in estimating mountainous freeway crash rate. Moreover, by comparing the predicted crash rate calculated by the BST model and the observed crash rate, the result shows the proposed BST model can provide a reliable prediction for freeway crash rates of different combined alignments. This study provides new insight on the effect of road geometric design on traffic safety but also deepens our understanding of spatial correlations in freeway crash modeling.