Accident; analysis and prevention最新文献

{"title":"Cyclist safety assessment using autonomous vehicles","authors":"Tarek Ghoul,&nbsp;Tarek Sayed","doi":"10.1016/j.aap.2025.107923","DOIUrl":"10.1016/j.aap.2025.107923","url":null,"abstract":"<div><div>Proactive and holistic safety management approaches should consider multi-modal crash risk. Cyclist crash risk should be prioritized given the high-severity of vehicle-cyclist crashes. Cyclist crash risk is difficult to quantify given the sparse nature of cyclist collisions and collisions in general. There is thus a need to develop a more proactive approach for multi-modal road-safety management by leveraging new technologies. This study proposes a conflict-based methodology to estimate cyclist crash risk using autonomous vehicle data, extrapolating from observed conflicts to real-time dynamic crash risk. Using 87 hours of data from an autonomous vehicle dataset from downtown Boston (nuPlan), traffic conflicts were identified. A Bayesian Hierarchical Extreme Value model was created representing driver and cyclist crash risk over short time intervals. This allows for identifying the real-time crash risk of various intersections and mid-blocks, enabling route-level safety metrics. The spatiotemporal characteristics of crash risk were examined in this study. Routes with cyclist facilities were found to be safer for cyclists, on average, than those with shared facilities. However, substantial fluctuations in crash risk were observed at different time intervals, with the shared facilities sometimes being safer than those with painted or buffered bicycle lanes. This highlights the need for real-time safety monitoring. At the user-level, a safest route application was also proposed, allowing for an impedance function to be developed based on real-time crash risk and the comparison of any number of nodes and links along a particular route.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"212 ","pages":"Article 107923"},"PeriodicalIF":5.7,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142996683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of eHMI-equipped automated vehicles on pedestrian crossing behavior and safety: A focus on blind spot scenarios","authors":"Xu Chen ,&nbsp;Xiaomeng Li ,&nbsp;Yuxuan Hou ,&nbsp;Wenzhang Yang ,&nbsp;Changyin Dong ,&nbsp;Hao Wang","doi":"10.1016/j.aap.2025.107915","DOIUrl":"10.1016/j.aap.2025.107915","url":null,"abstract":"<div><div>Blind spot collisions are a critical and often overlooked threat to pedestrian safety, frequently resulting in severe injuries. This study investigates the impact of automated vehicles equipped with external human–machine interfaces (eHMIs) on pedestrian crossing behavior and safety, focusing on scenarios where AVs create mutual blind spots between pedestrians and adjacent traffic. A virtual reality experiment with 51 participants simulated crossing situations in front of yielding trucks with obstructed pedestrian visibility, featuring three eHMIs: ‘Walk,’ ‘Don’t Walk,’ and ‘Caution! Blind Spots’. Vehicles within the truck’s blind spot exhibited proactive and reactive braking behaviors toward pedestrians. The results indicate that eHMI designs based on color, text, and symbols enhance pedestrian understanding. However, the ‘Walk’ eHMI, which ignores blind spot risks, may lead to dangerous crossing behaviors. In contrast, the ‘Don’t Walk’ eHMI effectively reduced unsafe crossing behaviors, though yielding trucks sometimes caused pedestrian confusion. The ‘Caution! Blind Spots’ eHMI increased alertness but was not significantly more effective than the direct ‘Don’t Walk’ instruction. This study provides empirical evidence for integrating dynamic environmental perception and hazard warnings into eHMI designs to raise road users’ awareness of blind spots. The findings emphasize the importance of comprehensive strategies, including policy-making, education, and VR-based training, to ensure the effective deployment and public understanding of eHMIs in blind spot environments.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"212 ","pages":"Article 107915"},"PeriodicalIF":5.7,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142997730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the impact of built environment on traffic risk perception of school-aged children: A case study of old residential neighborhoods in Changsha City, Hunan Province, China","authors":"Fan Yang ,&nbsp;Jiale Li ,&nbsp;Chengzhi Zhang ,&nbsp;Fangrong Chang ,&nbsp;Suwen Xiong","doi":"10.1016/j.aap.2025.107920","DOIUrl":"10.1016/j.aap.2025.107920","url":null,"abstract":"<div><div>The built environment of old residential neighborhoods poses heightened perceived traffic risks for school-aged children due to their limited cognitive ability to assess hazards, underdeveloped understanding of traffic patterns, and inadequate infrastructure in these areas. However, studies on the impacts of neighborhood environments on children’s traffic risk perceptions remain limited. This study aims to reveal the influence of individual attributes, as well as macro- and micro-level environmental factors, on children’s risk perception using a hierarchical ordered logit model with random effects. Data were collected through a questionnaire survey of 404 school-aged children across fifty old residential neighborhoods in Changsha, China. The results indicated that girls generally perceive higher levels of traffic risk than boys. At the macro-level, low population density and high activity facilities coverage were associated with reduced risk perceptions among children. At the micro-level, obstructed views of intersections, curbside parking, and road damage were found to increase risk perceptions among children. Additionally, random effects related to gender, intersection type, intersection visibility, curbside parking, and sidewalk availability suggested the influence of unobserved factors. The findings underscore the need for targeted interventions, such as improving intersection visibility, managing curbside parking, and repairing road damage, to mitigate traffic risks. Policymakers and urban designers should focus on these aspects to enhance safety and create child-friendly residential environments.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"212 ","pages":"Article 107920"},"PeriodicalIF":5.7,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142997824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Innovative prediction and causal analysis of accident vehicle towing probability using advanced gradient boosting techniques on extensive road traffic scene data","authors":"Ronghui Zhang ,&nbsp;Yang Liu ,&nbsp;Zihan Wang ,&nbsp;Junzhou Chen ,&nbsp;Qiang Zeng ,&nbsp;Lai Zheng ,&nbsp;Hui Zhang ,&nbsp;Yulong Pei","doi":"10.1016/j.aap.2024.107909","DOIUrl":"10.1016/j.aap.2024.107909","url":null,"abstract":"<div><div>Accurate prediction and causal analysis of road crashes are crucial for improving road safety. One critical indicator of road crash severity is whether the involved vehicles require towing. Despite its importance, limited research has utilized this factor for predicting vehicle towing probability and analyzing its causal factors. This study addresses this gap by predicting the probability of vehicle towing in road crashes based on road scene features and identifying key causal factors. Utilizing the Transportation Injury Mapping System (TIMS) dataset from California, USA, encompassing 12 years, 14 relevant features, and over 2 million road crash records, research team developed a prediction model using advanced gradient boosting techniques. Our model outperforms Random Forest, GBDT, and XGBoost in predictive accuracy. Employing the Shapley Additive Explanation (SHAP) method, researchers elucidate seven key factors influencing towing necessity. These findings introduce a novel predictive approach and offer valuable insights for road crash risk assessment and road safety planning.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"211 ","pages":"Article 107909"},"PeriodicalIF":5.7,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142982484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An integrative approach to generating explainable safety assessment scenarios for autonomous vehicles based on Vision Transformer and SHAP","authors":"Minhee Kang ,&nbsp;Keeyeon Hwang ,&nbsp;Young Yoon","doi":"10.1016/j.aap.2024.107902","DOIUrl":"10.1016/j.aap.2024.107902","url":null,"abstract":"<div><div>Automated Vehicles (AVs) are on the cusp of commercialization, prompting global governments to organize the forthcoming mobility phase. However, the advancement of technology alone cannot guarantee the successful commercialization of AVs without insights into the accidents on the read roads where Human-driven Vehicles (HV) coexist. To address such an issue, The New Car Assessment Program (NCAP) is currently in progress, and scenario-based approaches have been spotlighted. Scenario approaches offer a unique advantage by evaluating AV driving safety through carefully designed scenarios that reflect various real-world situations. While most scenario studies favor the data-driven approach, the studies have several shortcomings, including perspectives of data, AI models, and scenario standards. Hence, we propose a holistic framework for generating functional, logical, and concrete scenarios. The framework composes explainable scenarios (X-Scenarios) based on real-driving LiDAR data, and visual trend interpretation using eXplainable AI (XAI). The framework consists of four components as follows: (1) voxelization of LiDAR PCD and extraction of kinematic features; (2) classification of critical situations and generation of attention maps using visual XAI and Vision Transformer (ViT) to generate range values of elements in logical scenarios; (3) analysis of the importance and correlations among input data features using SHapley Additive exPlanations (SHAP) for selecting scenarios based on the most relevant criteria; and (4) composition of AV safety assessment scenarios. X-scenarios generated from our framework involve the parameters of ego vehicles and surrounding objects on the highways and urban roads. With our framework highly trustworthy AV safety assessment scenarios can be created. This novel work provides an integrated solution to generate trustworthy scenarios for AV safety assessment by explaining the scenario selection process.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"211 ","pages":"Article 107902"},"PeriodicalIF":5.7,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142982483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Partially temporally constrained modeling of speeding crash-injury severities on freeways and non-freeways before, during, and after the stay-at-home order","authors":"Li Song ,&nbsp;Shijie Li ,&nbsp;Qiming Yang ,&nbsp;Bing Liu ,&nbsp;Nengchao Lyu ,&nbsp;Wei David Fan","doi":"10.1016/j.aap.2025.107917","DOIUrl":"10.1016/j.aap.2025.107917","url":null,"abstract":"<div><div>Speeding crashes remain high injury severities after the stay-at-home order in California, highlighting a need for further investigation into the fundamental cause of this increment. To systematically explore the temporal impacts of the stay-at-home order on speeding behaviors and the corresponding crash-injury outcomes, this study utilizes California-reported single-vehicle speeding crashes on freeways (access-controlled) and non-freeways (non-access-controlled) before, during, and after the order. Significant injury factors and in-depth heterogeneity across observations are identified by random parameter logit models with heterogeneity in means and variances. Without segmenting the data by periods, the partially temporally constrained approach is employed to statistically determine varying and stabilized parameters over time through the whole dataset. Different likelihood ratio tests reveal significant temporal instabilities and stabilities of factors between two roadways and three periods. The potential impacts of observation selection issues on the marginal effect calculations of the partially constrained models are also systematically investigated. Significant variations in the probability of severe injury rate per week after the order are also found based on the Mann-Whitney U tests. The hysteretic effects of the order on the crash frequency and severity are observed on both freeways and non-freeways. Overall, seven variables are found to have stable effects, while fifteen variables exhibit unstable effects over time. Significant temporal variations in driver behaviors, including driving under the influence, cell phone usage, hit-and-run, failure to use seat belt, entering or leaving the ramp, and reaction to previous collisions, are observed before, during, or after the order. Specific countermeasures and effects of heterogeneity in means and variances are also discussed. These findings provide insights into understanding the temporal impacts of the stay-at-home order on injury severities, which are valuable to decision-makers and researchers for future order practice, restriction improvement, and complementary policy development.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"211 ","pages":"Article 107917"},"PeriodicalIF":5.7,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142963538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating crash severity at highway-rail grade crossings using an analytic hierarchy process-based hazard index model","authors":"Amin Keramati ,&nbsp;Pan Lu ,&nbsp;Afrooz Moatari-Kazerouni","doi":"10.1016/j.aap.2025.107918","DOIUrl":"10.1016/j.aap.2025.107918","url":null,"abstract":"<div><div>Due to the substantial mass disparity between trains and highway vehicles, crashes at Highway-Rail Grade Crossings (HRGCs) are often severe. Therefore, it is essential to develop systematic frameworks for allocating federal and state funds to improve safety at the highest-risk grade crossings. Common techniques for hazard prioritization at HRGCs include the hazard index and the collision prediction formula. A few research projects and state departments of transportation (DOTs) have employed hybrid models that integrate crash hazard indices with prediction models to create comprehensive safety decision-making frameworks. In addition, ranking grade crossings based on their forecasted crash severity likelihood remains largely unexplored, partly due to the complexity of integrating crash severity outputs with hazard indices. This research introduces a new mixed hazard ranking model, the Analytic Hierarchy Process Hazard Index (AHP-HI), which serves as a decision-making tool for ranking grade crossings based on their potential for crash severity. The AHP-HI model combines the analytic hierarchy process (AHP) and the competing risk model (CRM), a prediction model that estimates the likelihood of crash severity for crossings. Risk analysis using the AHP-HI model categorizes public grade crossings in North Dakota into four risk levels, with 4.73% of the crossings identified as high risk.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"211 ","pages":"Article 107918"},"PeriodicalIF":5.7,"publicationDate":"2025-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142963537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the Mechanism for Increased Risk in Freeway Tunnel Approach Zones: A Perspective on Temporal-spatial Evolution of Driving Predictions, Tasks, and Behaviors","authors":"Runzhao Bei ,&nbsp;Zhigang Du ,&nbsp;Nengchao Lyu ,&nbsp;Liang Yu ,&nbsp;Yongzheng Yang","doi":"10.1016/j.aap.2024.107914","DOIUrl":"10.1016/j.aap.2024.107914","url":null,"abstract":"<div><div>Freeway tunnel approach zones, situated outside the tunnel, do not undergo the same sudden changes in luminous environment and visual references that entrance zones experience. Despite this, accident data indicates that approach zones present similar safety risks to entrance zones, both of which are significantly higher than other tunnel sections. The reasons for the heightened risks in approach zones remain unclear in existing research. To address this knowledge gap, this study conducted real vehicle tests and subjective perception experiments. The Task Analysis of Driving Scenarios (TADS) was employed to analyze driving behavior patterns and develop a set of evaluation metrics, including four key driving behavior nodes (<em>P1_SGD, P2_EF, P3_FF, P4_SAD</em>), safety and efficacy indices for active deceleration behaviors (<em>I1_ADS, I2_ADE</em>), and two indicators for understanding anomalous behaviors (<em>SR, AOI_PFN</em>). By skillfully selecting scenarios to control variables, this research examined how limited visibility in tunnel approach zones and spatial intervisibility tunnels contribute to safety risks in these zones. Additionally, the Predictive Processing Model (PPM) was used to elucidate the temporal and spatial evolution of driving predictions, tasks, and behaviors under normal conditions. The findings reveal that, although heavy driving tasks cannot be avoided, under normal conditions, predictions develop gradually with minimal prediction errors, enabling effective navigation. However, limited visibility in tunnel approach zones and spatially intervisible tunnels lead to inaccuracies and deviations in predictions, resulting in significant prediction errors as drivers approach the tunnel. This causes more aggressive driving behaviors, disrupting the delicate balance of predictions and tasks.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"211 ","pages":"Article 107914"},"PeriodicalIF":5.7,"publicationDate":"2025-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142942452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A cognitive digital twin approach to improving driver compliance and accident prevention","authors":"Yi Gu ,&nbsp;Shuhang Li ,&nbsp;Ji Qi ,&nbsp;Bangzheng Fu ,&nbsp;Renzhi Tang ,&nbsp;Lifeng Yang ,&nbsp;Sen Tian ,&nbsp;Zhihao Jiang","doi":"10.1016/j.aap.2024.107913","DOIUrl":"10.1016/j.aap.2024.107913","url":null,"abstract":"<div><div>Advanced Driver Assistance Systems (ADAS) are crucial for enhancing driving safety by alerting drivers to unrecognized risks. However, traditional ADAS often fail to account for individual decision-making processes, including drivers’ perceptions of the environment and personal driving styles, which can lead to non-compliance with the provided assistance. This paper introduces a novel Cognitive-Digital-Twin-based Driving Assistance System (CDAS), leveraging a personalized driving decision model that dynamically updates based on the driver’s control and observation actions. By incorporating these individual behaviors, CDAS can tailor its assistance options to predict and adapt to the driver’s responses across various scenarios, ensuring both the necessity and safety of its interventions. Through two comprehensive experimental validations, we demonstrate that the cognitive digital twin (CDT) closely aligns with actual driver observation behaviors. By incorporating additional driver observation actions – an input not readily leveraged by data-driven methods without large annotated datasets – the CDT also achieves superior lane-changing predictions compared to deep learning classifiers relying solely on environmental states. Furthermore, CDAS significantly outperforms traditional ADAS in terms of risk reduction and user acceptance, showcasing its potential to enhance driving safety and adaptability effectively. These findings suggest that CDAS represents a substantial advancement towards more personalized and effective driving assistance.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"211 ","pages":"Article 107913"},"PeriodicalIF":5.7,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142942450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantifying spatial inequities in traffic injury rates through the integration of urban road network measures and social vulnerability","authors":"Pengfei Cui ,&nbsp;Mohamed Abdel-Aty ,&nbsp;Xiaobao Yang ,&nbsp;Chenzhu Wang ,&nbsp;Yali Yuan","doi":"10.1016/j.aap.2025.107916","DOIUrl":"10.1016/j.aap.2025.107916","url":null,"abstract":"<div><div>Mitigating traffic injury rate plays an essential role in sustainable urban development and is closely related to public health and human well-being. The inequity of traffic injury rate undermines equitable access to transportation infrastructure and poses a significant threat to the safety of residents during their commutes. Although previous studies have examined the association between socio-demographic characteristics and regional traffic crash risk, they seldom consider the spatial heterogeneity of the traffic injury rate inequity especially for the vulnerable groups. This study tackles three main challenges in quantifying spatial inequity in traffic injury rate, including identifying appropriate spatial units for macro-level crash modelling, integrating network topology measures, and examining the inequities suffered by vulnerable group. The global-scale spatial lag model (SLM) and local-scale geographically weighted regression (GWR) were employed at the census tract, Voronoi diagram and grid cell levels in New York City. The results highlight significant spatial variations in social vulnerability, showing that vulnerable indicators of housing cost burden, older age, minority, and those living in mobile homes are linked to increased traffic injury rate, especially in urban core regions. Furthermore, network topology measures indicates that increased network complexity and the buildings density would increase traffic injury rate. The traffic injury rate inequity level of each region was evaluated to identify areas with significant inequities for prioritization in future traffic planning. Recommendations like subsidized traffic insurance rates, enhanced public transportation services, and educational campaigns tailored for vulnerable groups are proposed. By prioritizing the needs of vulnerable groups and addressing the structural factors contributing to traffic injuries, policymakers can create safer and more equitable urban environment.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"211 ","pages":"Article 107916"},"PeriodicalIF":5.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}