Accident; analysis and prevention最新文献

筛选
英文 中文
Roadway safety during active wildfires: A machine-learning analysis of crash occurrence and injury severity. 活跃野火期间的道路安全:碰撞发生和伤害严重程度的机器学习分析。
IF 7.4 1区 工程技术
Accident; analysis and prevention Pub Date : 2026-11-14 DOI: 10.1016/j.aap.2026.108868
Fateme Gorzin, Omid Nayeri, Ramin Shabanpour
{"title":"Roadway safety during active wildfires: A machine-learning analysis of crash occurrence and injury severity.","authors":"Fateme Gorzin, Omid Nayeri, Ramin Shabanpour","doi":"10.1016/j.aap.2026.108868","DOIUrl":"https://doi.org/10.1016/j.aap.2026.108868","url":null,"abstract":"<p><p>Wildfires create rapidly changing conditions for roadway operations and safety, yet how wildfire-related conditions relate to crash occurrence and injury severity remains insufficiently understood. Using data from 10 California wildfires between 2020 and 2025, this study examines crash occurrence at the roadway segment-day level and injury severity at the crash level through two separate machine-learning analyses. Across the two analyses, predictors included fire advancement toward roadway segments, fire-risk context, smoke exposure, historical Public Safety Power Shutoff exposure, and distance to the active fire perimeter, alongside conventional roadway, land-use, weather, traffic-exposure, and temporal characteristics. The severity analysis additionally incorporated driver, vehicle, and collision attributes. Five tree-based classifiers were evaluated using cross-validation, and predictor contributions were examined using complementary feature-importance measures and SHAP. Fire advancement toward roadway segments emerged as the strongest crash-occurrence predictor across all importance measures, while fire-risk context and smoke exposure also contributed to model predictions. In contrast, injury severity was characterized primarily by collision, vehicle-safety, driver, roadway, and built-environment factors, with collision type and airbag deployment among the strongest contributors. Most wildfire-related variables ranked below the leading crash-specific predictors in the severity model. Together, these findings highlight distinct predictor structures for crash occurrence and conditional injury severity, supporting their separate assessment when examining roadway safety during active wildfires.</p>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"241 ","pages":"108868"},"PeriodicalIF":7.4,"publicationDate":"2026-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149400900","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}
引用次数: 0
Overdispersion parameter correction for safety performance Functions estimated using temporally aggregated crash data. 使用临时聚合的碰撞数据估计的安全性能函数的过分散参数校正。
IF 7.4 1区 工程技术
Accident; analysis and prevention Pub Date : 2026-11-14 DOI: 10.1016/j.aap.2026.108870
Vikash V Gayah, Hao Liu
{"title":"Overdispersion parameter correction for safety performance Functions estimated using temporally aggregated crash data.","authors":"Vikash V Gayah, Hao Liu","doi":"10.1016/j.aap.2026.108870","DOIUrl":"https://doi.org/10.1016/j.aap.2026.108870","url":null,"abstract":"<p><p>Safety Performance Functions (SPFs) are often developed using temporally aggregated crash data, where crash counts are combined across multiple years. However, temporal aggregation alters the negative binomial overdispersion parameter, affecting applications such as network screening, Empirical Bayes estimation, and crash modification factor development. This study develops and evaluates a modified overdispersion formulation that better captures the statistical effects of temporal aggregation. A two-component overdispersion formulation is derived by relating annual and aggregated crash-count variance under a negative binomial framework. The proposed model decomposes overdispersion into a persistent site-level component and a year-specific component that diminishes as more years are aggregated. The approach is evaluated using both synthetic data with known overdispersion properties and crash data from rural two-lane roadway segments in Pennsylvania, including sites with unequal observation periods. Conventional aggregate negative binomial models underestimated overdispersion relative to annual-data models due to the smoothing effect of temporal aggregation. The proposed formulation distinguished persistent site-level heterogeneity from year-specific variation, accurately reflecting the reduction in year-specific variability in the synthetic analysis. Empirical results suggest that both components contribute to aggregated crash data, indicating that some variation is smoothed over time while other variation remains correlated across years. The proposed formulation provides a practical framework for SPF development using temporally aggregated crash data, particularly when observation periods differ across sites. It improves interpretation of overdispersion estimates for applications including Empirical Bayes estimation, network screening, and crash modification factor development.</p>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"241 ","pages":"108870"},"PeriodicalIF":7.4,"publicationDate":"2026-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149400899","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}
引用次数: 0
An encounter-based exposure measure for crash risk analysis: Model development and evidence from the Netherlands. 碰撞风险分析的基于接触的暴露措施:模型开发和来自荷兰的证据。
IF 7.4 1区 工程技术
Accident; analysis and prevention Pub Date : 2026-11-13 DOI: 10.1016/j.aap.2026.108862
Dylan van Bezooijen, Jesse Voorhorst, Mehmet Baran Ulak, Joep Schyns, Karst Geurs
{"title":"An encounter-based exposure measure for crash risk analysis: Model development and evidence from the Netherlands.","authors":"Dylan van Bezooijen, Jesse Voorhorst, Mehmet Baran Ulak, Joep Schyns, Karst Geurs","doi":"10.1016/j.aap.2026.108862","DOIUrl":"https://doi.org/10.1016/j.aap.2026.108862","url":null,"abstract":"<p><p>In crash risk analysis, exposure is a key component used to account for the number of opportunities for a dangerous road event to occur. However, relatively little attention has been given in literature to quantifying exposure on roads where cyclists share space with motorized vehicles. Hence, this study aims to investigate how exposure can be measured on road segments with multiple types of road users and how this affects crash risk patterns. This study finds that exposure is best defined as a trial that has a probability of producing either a crash or a non-crash event and that encounters best fit this definition. The study proposes a model which uses traffic volumes, speeds and lane configurations as input to compute an estimate for the number of encounters on a road segment. Application of this model in a Dutch case study shows that encounter-based exposure can lead to significantly different crash risk estimates compared to activity-based exposure, particularly on mixed-use road segments, showing that encounters represent real-world exposure to risk significantly different compared to activity-based crash risk. By better accounting for interactions between cyclists and motorized vehicles, the approach in this study may provide a more meaningful basis for assessing crash risk on roads where these users share the same space.</p>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"241 ","pages":"108862"},"PeriodicalIF":7.4,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149400896","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}
引用次数: 0
Heterogeneous safety effects of right-turn protection and two-stage crossing treatments on non-motorized vehicle crashes at intersections. 右转保护和两段交叉口处理对非机动车碰撞的非均匀安全效应。
IF 7.4 1区 工程技术
Accident; analysis and prevention Pub Date : 2026-11-12 DOI: 10.1016/j.aap.2026.108874
Chunting Nie, Xuesong Wang, Bangyu Wang, Attila Borsos
{"title":"Heterogeneous safety effects of right-turn protection and two-stage crossing treatments on non-motorized vehicle crashes at intersections.","authors":"Chunting Nie, Xuesong Wang, Bangyu Wang, Attila Borsos","doi":"10.1016/j.aap.2026.108874","DOIUrl":"https://doi.org/10.1016/j.aap.2026.108874","url":null,"abstract":"<p><p>Non-motorized vehicle (NMV) crashes remain prevalent at intersections, posing a critical challenge for urban traffic safety. To address this issue, several cities in China have implemented intersection treatments, including right-turn protection measures (solid physical separation and right-turn warning zones) and two-stage crossing treatments for left-turning NMVs. However, the extent to which the safety effects of these treatments vary across different intersection contexts remains insufficiently understood. This study investigates the heterogeneous safety effects of these treatments and identifies intersection characteristics that moderate their effectiveness. A causal forest model, a machine learning-based causal inference approach, is employed to estimate treatment effects using NMV crash data. The results indicate that solid physical separation and right-turn warning zone treatments are associated with significant reductions in NMV crashes, whereas the two-stage crossing treatment does not exhibit a consistent overall safety benefit. Heterogeneity is observed in the effects of solid physical separation and two-stage crossing treatments across intersection characteristics, while the effects of right-turn warning zones remain relatively stable. Specifically, the safety benefits of solid physical separation are more pronounced at smaller intersections, at locations with shorter crossing distances, and where bicycle lane widths are at least 2.5 m. The two-stage crossing treatment shows safety benefits under specific conditions, including larger intersections, locations with longer crossing distances on major and minor roads, and the presence of medians on minor approaches. Across combinations of intersection characteristics, the estimated reductions in NMV crashes range from 0.86 % to 28.35 % for solid physical separation and from 7.05 % to 13.31 % for right-turn warning zones, while the estimated effects of two-stage crossing treatments range from a 4.04 % reduction to a 41.07 % increase in NMV crashes. Greater safety benefits of solid physical separation are observed at intersections with wide bicycle lanes (at least 2.5 m), limited median presence, and short crossing distances. This study highlights the importance of accounting for treatment effect heterogeneity in intersection safety analysis and provides empirical evidence that may inform the context-specific selection and implementation of NMV safety treatments.</p>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"241 ","pages":"108874"},"PeriodicalIF":7.4,"publicationDate":"2026-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149400898","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}
引用次数: 0
Estimating intersection crash risk with multi-type conflicts from trajectory data: A bivariate Bayesian hierarchical extreme value model. 基于轨迹数据的多类型冲突交叉口碰撞风险估计:一个二元贝叶斯层次极值模型。
IF 7.4 1区 工程技术
Accident; analysis and prevention Pub Date : 2026-11-12 DOI: 10.1016/j.aap.2026.108852
Guangzhu Luo, Xuesong Wang, Mohammed Quddus, Bingyou Dai, Lai Zheng, Yajie Zou, Qiming Guo
{"title":"Estimating intersection crash risk with multi-type conflicts from trajectory data: A bivariate Bayesian hierarchical extreme value model.","authors":"Guangzhu Luo, Xuesong Wang, Mohammed Quddus, Bingyou Dai, Lai Zheng, Yajie Zou, Qiming Guo","doi":"10.1016/j.aap.2026.108852","DOIUrl":"https://doi.org/10.1016/j.aap.2026.108852","url":null,"abstract":"<p><p>Unreasonable geometric designs and heterogeneous traffic flow patterns challenge vehicle safety at intersections. This study employs a Bivariate Bayesian Hierarchical Extreme Value model to investigate how different geometric features and traffic flow characteristics influence crash risk across multiple conflict scenarios. Highly disaggregated vehicle trajectory data covering a total of 9,428 min were collected from 20 intersections across seven cities in China, the United States, and Germany using Holographic Intersection technology and unmanned aerial vehicles. The AI Conflict Observer, based on an Ensemble Transformer model, automatically identified Crossing, Lane-changing, and Rear-end conflict scenarios, along with their severity and conflict point locations. To appropriately capture all conflict scenarios, the traditional Deceleration Rate to Avoid a Crash was generalized to account for vehicle orientation and size, together with the Generalized Time-to-Collision as bivariate surrogate safety measures. To ensure independence among extreme conflict events, a POT sampling method with spatiotemporal independence test was developed. A bivariate Generalized Pareto Distribution (GPD) with a logistic dependence structure was constructed for these two measures. A Bayesian Hierarchical structure was further introduced to relate the scale parameters of the marginal GPDs to intersection geometric design and traffic operation characteristics. Model parameters and intersection crash risks were estimated using a two-stage approach. The results indicate that: 1) for crossing conflicts, providing exclusive right-turn lanes and signal control reduces crash risk, whereas smaller skew angles and smaller right-turn radii increase crash risk; 2) for lane-changing conflicts, the presence of a median strip reduces crash risk, whereas excessive bicycle lanes and high traffic volumes increase crash risk; and 3) for rear-end conflicts, providing exclusive right-turn lanes and larger right-turn radii reduces crash risk, whereas smaller left-turn radii increase crash risk. The proposed model provides a practical framework for proactive crash risk assessment, and supports evidence-based intersection design and traffic management.</p>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"241 ","pages":"108852"},"PeriodicalIF":7.4,"publicationDate":"2026-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149400897","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}
引用次数: 0
Long-term effects of driver feedback on harsh braking behavior: insights from survival models. 驾驶员反馈对急刹车行为的长期影响:来自生存模型的见解。
IF 7.4 1区 工程技术
Accident; analysis and prevention Pub Date : 2026-11-09 DOI: 10.1016/j.aap.2026.108865
Armira Kontaxi, Athanasios Theofilatos, Apostolos Ziakopoulos, George Yannis
{"title":"Long-term effects of driver feedback on harsh braking behavior: insights from survival models.","authors":"Armira Kontaxi, Athanasios Theofilatos, Apostolos Ziakopoulos, George Yannis","doi":"10.1016/j.aap.2026.108865","DOIUrl":"https://doi.org/10.1016/j.aap.2026.108865","url":null,"abstract":"<p><p>This study investigates the long-term effects of smartphone-based driver feedback on harsh braking behavior using a large-scale naturalistic driving dataset. The overall naturalistic driving dataset comprised 24,904 trips from 31 drivers across all experimental phases, of which 2220 post-feedback trips were used to investigate relapse after feedback withdrawal. The analysis compares behavior across baseline, feedback and post-feedback periods to assess both immediate and sustained effects of feedback interventions. Descriptive statistics and non-parametric tests indicate a significant reduction in harsh braking events during the feedback phase, confirming the short-term effectiveness of feedback in improving driving behavior. However, a noticeable relapse is observed following the removal of feedback, suggesting challenges in maintaining behavioral improvements over time. To further explore the persistence of these effects, survival analysis techniques were applied, including Kaplan-Meier estimators, Cox Proportional Hazards models with frailty, Weibull Accelerated Failure Time (AFT) models with clustered heterogeneity and Random Survival Forests (RSF). The Kaplan-Meier analysis demonstrates a gradual decline in the probability of remaining free from a first relapse during the post-feedback phase, reaching approximately 40.3 % by the 150-trip mark. Key predictors of relapse include driver age, vehicle engine capacity and trip duration, with older drivers exhibiting more stable behavior over time. In terms of model performance, the Weibull AFT model provided the most suitable balance between interpretability and predictive accuracy, while the RSF model provided a flexible, non-parametric, data-driven approach capable of accommodating complex non-linear relationships and interactions among predictors. Overall, the findings highlight the importance of continuous or reinforced feedback mechanisms to sustain safer driving behavior and provide a methodological framework for assessing long-term behavioral dynamics using survival analysis.</p>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"240 ","pages":"108865"},"PeriodicalIF":7.4,"publicationDate":"2026-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149376664","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}
引用次数: 0
Extending safety performance functions with connected vehicle data using a random-parameter negative binomial Lindley model with spatial effect. 利用具有空间效应的随机参数负二项Lindley模型扩展车联网数据下的安全性能函数。
IF 7.4 1区 工程技术
Accident; analysis and prevention Pub Date : 2026-11-09 DOI: 10.1016/j.aap.2026.108848
Abu Saif Md Nasim Uddin, Mohamed Abdel-Aty, Zubayer Islam, Chenzhu Wang
{"title":"Extending safety performance functions with connected vehicle data using a random-parameter negative binomial Lindley model with spatial effect.","authors":"Abu Saif Md Nasim Uddin, Mohamed Abdel-Aty, Zubayer Islam, Chenzhu Wang","doi":"10.1016/j.aap.2026.108848","DOIUrl":"https://doi.org/10.1016/j.aap.2026.108848","url":null,"abstract":"<p><p>Severe crashes remain a critical roadway safety concern, yet traditional Safety Performance Functions (SPFs) primarily rely on traffic exposure and roadway characteristics, often overlooking driving behavior. Leveraging high-resolution connected vehicle (CV) trajectory data, this study derives behavioral measures, including hard braking, hard acceleration, radial acceleration, lane changes, operating speeds, and speed variability, and integrates them into an extended SPF framework for segment-level crash frequency modeling. Using data from the Lake-Sumter Metropolitan Planning Organization region in Florida, Bayesian random parameter negative binomial-Lindley models with spatial effects are estimated separately for two-lane and multilane segments for both severe (KA) and total (KABCO) crashes. Six alternative spatial weight structures, accounting for segment adjacency, length, and distance decay, are compared, with the second-order adjacency structure providing the best overall performance. Results indicate that CV-based behavioral variables improve model fit and predictive performance compared to traditional SPFs. Among the behavioral variables, radial acceleration on two-lane segments and lane changes on multilane segments are positively associated with KA and KABCO crash frequencies, respectively. Elasticity analysis identifies traffic volume (AADT) as the most influential factor across facilities, while over-speeding proportion (0-10%) and speed standard deviation show strong effects for two-lane KA and KABCO crashes, respectively, and speed standard deviation remains particularly influential for multilane KABCO crashes. By integrating CV data into SPF modeling, the proposed framework advances behavior-informed roadway safety analysis and offers practical insights for proactive safety management and prioritization.</p>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"240 ","pages":"108848"},"PeriodicalIF":7.4,"publicationDate":"2026-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149376744","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}
引用次数: 0
GeoShapley-based interpretation of older adult pedestrian fatal vs injury crash frequency in dense urban environments 基于geoshaples的稠密城市环境中老年行人致命与伤害碰撞频率分析
IF 6.2 1区 工程技术
Accident; analysis and prevention Pub Date : 2026-06-01 Epub Date: 2026-02-11 DOI: 10.1016/j.aap.2026.108450
I Gede Brawiswa Putra , Pei-Fen Kuo , Febrian Fitryanik Susanta , Bimo Harya Tedjo , Dominique Lord
{"title":"GeoShapley-based interpretation of older adult pedestrian fatal vs injury crash frequency in dense urban environments","authors":"I Gede Brawiswa Putra ,&nbsp;Pei-Fen Kuo ,&nbsp;Febrian Fitryanik Susanta ,&nbsp;Bimo Harya Tedjo ,&nbsp;Dominique Lord","doi":"10.1016/j.aap.2026.108450","DOIUrl":"10.1016/j.aap.2026.108450","url":null,"abstract":"<div><div>As the world’s population ages, ensuring the safety of older adult pedestrians has become an urgent priority in transportation planning. However, most existing studies rely on global models that overlook spatial heterogeneity and fail to capture nonlinear, location-specific interactions between the environmental factors and crash outcomes. Moreover, subjective perceptions (e.g., how safe or walkable an area feels) may influence pedestrian behavior and crash exposure but are underexplored in traffic safety research.</div><div>This study addresses these gaps by integrating subjective perception indicators extracted from Street View Images (SVI) with machine learning models to examine the severity of older adult pedestrian crashes at intersections in Taipei City. Three modeling frameworks are evaluated and compared: global Negative Binomial Regression (NBR), Geographically Weighted Negative Binomial Regression (GWNBR), and GeoShapley, a spatially interpretable extension of the SHAP framework for XGBoost. A total of 36 environmental and perceptual variables are evaluated in relation to injury and fatal crash frequencies.</div><div>Among these models, GeoShapley achieved the best performance and revealed that spatial location (GEO) and its interactions with environmental factors and subjective perceptions were among the most influential predictors. In some areas, higher walkability was associated with reduced injury crash frequencies, especially in older and urban districts. In addition, the effect of convenience stores and nursing homes on the frequency of fatal crashes varied significantly across locations, reflecting the spatial clustering of pedestrian activity and older adults. Overall, the findings demonstrate the value of spatially explicit machine learning tools and subjective perceptions in understanding localized crash dynamics in aging urban populations.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"230 ","pages":"Article 108450"},"PeriodicalIF":6.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146177362","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}
引用次数: 0
Study on a multi-factor lane-changing risk resilience assessment model based on genetic algorithm and fault tree analysis 基于遗传算法和故障树分析的多因素变道风险恢复力评估模型研究
IF 6.2 1区 工程技术
Accident; analysis and prevention Pub Date : 2026-06-01 Epub Date: 2026-02-13 DOI: 10.1016/j.aap.2026.108443
Qiang Luo , Haihui Wang , Junheng Yang , Xiaodong Zang , Xinqiang Chen , Octavian Postolache
{"title":"Study on a multi-factor lane-changing risk resilience assessment model based on genetic algorithm and fault tree analysis","authors":"Qiang Luo ,&nbsp;Haihui Wang ,&nbsp;Junheng Yang ,&nbsp;Xiaodong Zang ,&nbsp;Xinqiang Chen ,&nbsp;Octavian Postolache","doi":"10.1016/j.aap.2026.108443","DOIUrl":"10.1016/j.aap.2026.108443","url":null,"abstract":"<div><div>Current lane-change risk assessment models often lack dynamic adaptation to adverse weather and validation against real-world outcomes. To bridge this gap, this study re-frames the problem through a resilience engineering lens, defining risk resilience as the lane-changing system’s capacity to absorb weather disturbances and maintain safety through adaptation. To operationalize this concept, we introduce two complementary metrics: the Risk Exposure Level (REL) and the Risk Severity Level (RSL). We propose a weather-aware, resilience-oriented assessment framework that integrates a Genetic Algorithm (GA)-calibrated Stopping Sight Distance (SSD) model with Fault Tree Analysis (FTA). Using the CitySim naturalistic driving dataset, a dual-threshold identification algorithm was applied to extract 310 lane-change events (218 sunny, 92 rainy). Key influencing factors, including weather, surrounding vehicle distribution, lane-change direction, and location, were identified through statistical testing. The GA was employed to optimize critical braking parameters (deceleration, reaction time) in the SSD/SDI model, enabling self-adaptive risk thresholds under different weather conditions. REL and RSL quantify the probability (exposure) and severity (consequence) of conflicts from multiple vehicle groups, which are systematically integrated via FTA to assess overall system robustness. Model calibration and testing using trajectory data showed a 42.38% improvement in fitness over the baseline model. A PyQt5-based visualization platform was developed to support practical application. The results confirm that the model effectively captures real-time lane-changing risk, providing a reliable tool for proactive safety management and resilience-oriented decision support in intelligent transportation systems.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"230 ","pages":"Article 108443"},"PeriodicalIF":6.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146187583","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}
引用次数: 0
Enhancing legal driving for autonomous vehicles through law-compliance potential fields 通过潜在的守法领域,加强自动驾驶汽车的合法驾驶
IF 6.2 1区 工程技术
Accident; analysis and prevention Pub Date : 2026-06-01 Epub Date: 2026-02-14 DOI: 10.1016/j.aap.2026.108441
Chengxiang Zhao , Zichun Xiong , Lei Song , Xiaohan Ma , Zhengxian Chen , Siyu Wu , Jun Li , Wenhao Yu , Hong Wang
{"title":"Enhancing legal driving for autonomous vehicles through law-compliance potential fields","authors":"Chengxiang Zhao ,&nbsp;Zichun Xiong ,&nbsp;Lei Song ,&nbsp;Xiaohan Ma ,&nbsp;Zhengxian Chen ,&nbsp;Siyu Wu ,&nbsp;Jun Li ,&nbsp;Wenhao Yu ,&nbsp;Hong Wang","doi":"10.1016/j.aap.2026.108441","DOIUrl":"10.1016/j.aap.2026.108441","url":null,"abstract":"<div><div>With the advent of the mixed traffic era, ensuring autonomous vehicles’ compliance with traffic laws alongside human drivers has become increasingly critical. Existing decision-making methods predominantly emphasize safety, inadequately addressing systematic compliance with traffic laws, leading to potential legal violations in complex driving scenarios. To bridge this gap, this paper proposes a comprehensive Law-Compliance Potential Fields-based method. Traffic law constraints are systematically categorized into four potential fields, which explicitly encode vehicle states, static and dynamic elements, and compliance thresholds. A novel fusion strategy is further designed to effectively resolve field-overlap distortions. Finally, the constructed law-compliance potential fields are integrated into a model predictive control-based decision-making framework, and five representative scenarios are designed for experimental validation, including a critical scenario of safety-compliance conflict. The evaluated results of scenario tests demonstrate that the proposed method markedly enhances autonomous vehicles’ compliance capabilities, effectively balancing safety considerations even under challenging driving conditions.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"230 ","pages":"Article 108441"},"PeriodicalIF":6.2,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146187588","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}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书