Accident; analysis and prevention最新文献_第10页

Evaluating the safety impact of mid-block pedestrian signals (MPS) 评估街区中段行人信号灯（MPS）对安全的影响

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-11-25 DOI: 10.1016/j.aap.2024.107847

Md Jamil Ahsan, Mohamed Abdel-Aty, Ahmed S. Abdelrahman

The Florida Department of Transportation (FDOT) has recently started implementing a new signal system at mid-blocks called Mid-block Pedestrian Signals (MPS). This study aims to evaluate the effectiveness of these newly implemented MPSs. A total of 260 h of video data were collected from five locations across Florida, with 130 h recorded before MPS installation and 130 h after installation, including both weekdays and weekends. State-of-the-art computer vision technology was employed to detect and track various road users. A random parameters multinomial logit model with heterogeneity in the means was implemented to assess safety of vehicle–pedestrian interaction by three conflict categories: No Conflict, Moderate Conflict, and Serious Conflict. Relative-Time-to-Collision (RTTC) values were utilized to classify these level of conflicts. The analysis demonstrates that the presence of MPS significantly enhances safety outcomes by increasing the likelihood of avoiding conflicts and reducing the probabilities of both moderate and serious conflicts. Key factors influencing conflict probabilities were identified, including pedestrian and vehicle counts, average leading vehicle speed, standard deviation of leading vehicle speeds, and land-use mix, all of which increase the probability of serious conflicts. Interestingly, the analysis identified three significant interaction variables with MPS: average leading vehicle speed, standard deviation of leading vehicle speeds, and land-use mix. While these factors individually had a higher probability of leading to serious conflicts, the presence of MPS effectively mitigates these risks by moderating their adverse effects, increasing the likelihood of no conflicts. These results underscore the importance of MPS as an effective measure to improve safety at mid-block crossings.

佛罗里达州交通部（FDOT）最近开始在中段街区实施一种新的信号系统，称为中段街区行人信号系统（MPS）。本研究旨在评估这些新实施的 MPS 的有效性。在佛罗里达州的五个地点共收集了 260 小时的视频数据，其中 130 小时记录在 MPS 安装之前，130 小时记录在安装之后，包括工作日和周末。采用了最先进的计算机视觉技术来检测和跟踪各种道路使用者。采用具有均值异质性的随机参数多项式对数模型，按三个冲突类别评估车辆与行人互动的安全性：无冲突、中度冲突和严重冲突。采用相对碰撞时间（RTTC）值来划分这些冲突等级。分析表明，多点停车系统的存在提高了避免冲突的可能性，降低了中度和严重冲突的概率，从而显著增强了安全效果。分析确定了影响冲突概率的关键因素，包括行人和车辆数量、平均领先车速、领先车速标准偏差和土地使用组合，所有这些因素都会增加严重冲突的概率。有趣的是，分析发现了三个与 MPS 重要的交互变量：平均领先车速、领先车速标准偏差和土地使用组合。虽然这些因素单独导致严重冲突的概率较高，但 MPS 的存在通过缓和其不利影响而有效降低了这些风险，增加了不发生冲突的可能性。这些结果凸显了多点停车系统作为改善街区中间交叉口安全的有效措施的重要性。

{"title":"Evaluating the safety impact of mid-block pedestrian signals (MPS)","authors":"Md Jamil Ahsan, Mohamed Abdel-Aty, Ahmed S. Abdelrahman","doi":"10.1016/j.aap.2024.107847","DOIUrl":"10.1016/j.aap.2024.107847","url":null,"abstract":"<div><div>The Florida Department of Transportation (FDOT) has recently started implementing a new signal system at mid-blocks called Mid-block Pedestrian Signals (MPS). This study aims to evaluate the effectiveness of these newly implemented MPSs. A total of 260 h of video data were collected from five locations across Florida, with 130 h recorded before MPS installation and 130 h after installation, including both weekdays and weekends. State-of-the-art computer vision technology was employed to detect and track various road users. A random parameters multinomial logit model with heterogeneity in the means was implemented to assess safety of vehicle–pedestrian interaction by three conflict categories: No Conflict, Moderate Conflict, and Serious Conflict. Relative-Time-to-Collision (RTTC) values were utilized to classify these level of conflicts. The analysis demonstrates that the presence of MPS significantly enhances safety outcomes by increasing the likelihood of avoiding conflicts and reducing the probabilities of both moderate and serious conflicts. Key factors influencing conflict probabilities were identified, including pedestrian and vehicle counts, average leading vehicle speed, standard deviation of leading vehicle speeds, and land-use mix, all of which increase the probability of serious conflicts. Interestingly, the analysis identified three significant interaction variables with MPS: average leading vehicle speed, standard deviation of leading vehicle speeds, and land-use mix. While these factors individually had a higher probability of leading to serious conflicts, the presence of MPS effectively mitigates these risks by moderating their adverse effects, increasing the likelihood of no conflicts. These results underscore the importance of MPS as an effective measure to improve safety at mid-block crossings.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"210 ","pages":"Article 107847"},"PeriodicalIF":5.7,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723767","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

Investigating streetscape environmental characteristics associated with road traffic crashes using street view imagery and computer vision 利用街景图像和计算机视觉研究与道路交通事故相关的街景环境特征。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-11-23 DOI: 10.1016/j.aap.2024.107851

Han Yue

Examining the relationship between streetscape features and road traffic crashes is vital for enhancing roadway safety. Traditional field surveys are often inefficient and lack comprehensive spatial coverage. Leveraging street view images (SVIs) and deep learning techniques provides a cost-effective alternative for extracting streetscape features. However, prior studies often rely solely on semantic segmentation, overlooking distinctions in feature shapes and contours. This study addresses these limitations by combining semantic segmentation and object detection networks to comprehensively measure streetscape features from Baidu SVIs. Semantic segmentation identifies pixel-level proportions of features such as roads, sidewalks, buildings, fences, trees, and grass, while object detection captures discrete elements like vehicles, pedestrians, and traffic lights. Zero-inflated negative binomial regression models are employed to analyze the impact of these features on three crash types: vehicle-vehicle (VCV), vehicle–pedestrian (VCP), and single-vehicle crashes (SVC). Results show that incorporating streetscape features from combined deep learning methods significantly improves crash prediction. Vehicles have a significant impact on VCV and SVC crashes, whereas pedestrians predominantly affect VCP crashes. Road surfaces, sidewalks, and plants are associated with increased crash risks, while buildings and trees correlate with reduced vehicle crash frequencies. This study highlights the advantages of integrating semantic segmentation and object detection for streetscape analysis and underscores the critical role of environmental characteristics in road traffic crashes. The findings provide actionable insights for urban planning and traffic safety strategies.

研究街景特征与道路交通事故之间的关系对于提高道路安全至关重要。传统的实地调查往往效率低下，而且缺乏全面的空间覆盖。利用街景图像（SVI）和深度学习技术为提取街景特征提供了一种具有成本效益的替代方法。然而，之前的研究往往只依赖于语义分割，忽略了特征形状和轮廓的区别。本研究结合语义分割和物体检测网络，从百度 SVI 中全面测量街景特征，从而解决了这些局限性。语义分割可识别道路、人行道、建筑物、围栏、树木和草地等特征的像素级比例，而物体检测则可捕捉车辆、行人和交通灯等离散元素。采用零膨胀负二项回归模型来分析这些特征对三种碰撞类型的影响：车辆-车辆（VCV）、车辆-行人（VCP）和单车碰撞（SVC）。结果表明，结合深度学习方法的街景特征可显著改善碰撞预测。车辆对 VCV 和 SVC 碰撞事故有重大影响，而行人则主要影响 VCP 碰撞事故。路面、人行道和植物与碰撞风险增加有关，而建筑物和树木则与车辆碰撞频率降低有关。这项研究凸显了将语义分割和物体检测整合到街景分析中的优势，并强调了环境特征在道路交通事故中的关键作用。研究结果为城市规划和交通安全战略提供了可行的见解。

{"title":"Investigating streetscape environmental characteristics associated with road traffic crashes using street view imagery and computer vision","authors":"Han Yue","doi":"10.1016/j.aap.2024.107851","DOIUrl":"10.1016/j.aap.2024.107851","url":null,"abstract":"<div><div>Examining the relationship between streetscape features and road traffic crashes is vital for enhancing roadway safety. Traditional field surveys are often inefficient and lack comprehensive spatial coverage. Leveraging street view images (SVIs) and deep learning techniques provides a cost-effective alternative for extracting streetscape features. However, prior studies often rely solely on semantic segmentation, overlooking distinctions in feature shapes and contours. This study addresses these limitations by combining semantic segmentation and object detection networks to comprehensively measure streetscape features from Baidu SVIs. Semantic segmentation identifies pixel-level proportions of features such as roads, sidewalks, buildings, fences, trees, and grass, while object detection captures discrete elements like vehicles, pedestrians, and traffic lights. Zero-inflated negative binomial regression models are employed to analyze the impact of these features on three crash types: vehicle-vehicle (VCV), vehicle–pedestrian (VCP), and single-vehicle crashes (SVC). Results show that incorporating streetscape features from combined deep learning methods significantly improves crash prediction. Vehicles have a significant impact on VCV and SVC crashes, whereas pedestrians predominantly affect VCP crashes. Road surfaces, sidewalks, and plants are associated with increased crash risks, while buildings and trees correlate with reduced vehicle crash frequencies. This study highlights the advantages of integrating semantic segmentation and object detection for streetscape analysis and underscores the critical role of environmental characteristics in road traffic crashes. The findings provide actionable insights for urban planning and traffic safety strategies.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"210 ","pages":"Article 107851"},"PeriodicalIF":5.7,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142708947","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 emergency operation strategy and motion planning method for autonomous vehicle in emergency scenarios 紧急情况下自动驾驶汽车的应急运行策略和运动规划方法。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-11-23 DOI: 10.1016/j.aap.2024.107842

Tianyang Gong , Xiumin Yu , Qunli Zhang , Zilin Feng , Shichun Yang , Yaoguang Cao , Jingyun Xu , Xinjie Feng , Zhaowen Pang , Yu Wang , Peng Wang

Ensuring driving operational safety in emergency scenarios is paramount for autonomous vehicles to prevent accidents, particularly when vehicle motion completely depends on autonomous systems. Numerous factors must be evaluated when designing emergency collision avoidance strategies for critical situations, such as trajectory feasibility, vehicle motion stability, and driver comfort. Therefore, this study proposes a framework for emergency operation that uses collision-free area calculations to inform maneuver decisions and facilitate collision avoidance trajectory planning, preventing vehicle collisions. In case of danger, the emergency maneuver decision module evaluates the safety level and selects safety terminal state by considering a pre-specified cluster of candidate maneuvers before generating trajectories. This process avoids infeasible trajectories and selects maneuvers for greater driver comfort when available. Subsequently, the dynamic trajectory planning module converts the collision-free area into mixed-integer constraints, utilizing time-varying Nonlinear Model Predictive Control (NMPC) for trajectory planning and ensuring vehicle motion stability by integrating dynamic and collision-free constraints throughout the motion planning process. Eventually, simulations and field testing validate the framework’s effectiveness, mitigating collisions in emergency scenarios with prompt and safe operations. The framework is designed to function autonomously, independent of the intelligent driving system, engaging only during risk events and restoring control to the driver or the intelligent system after the event.

确保紧急情况下的驾驶操作安全是自动驾驶车辆防止事故发生的首要任务，尤其是当车辆运动完全依赖于自动驾驶系统时。在为危急情况设计紧急避撞策略时，必须评估众多因素，如轨迹可行性、车辆运动稳定性和驾驶员舒适度。因此，本研究提出了一种紧急操作框架，利用无碰撞区域计算为机动决策提供信息，促进避撞轨迹规划，防止车辆碰撞。在发生危险时，紧急机动决策模块会评估安全等级，并在生成轨迹之前通过考虑预先指定的候选机动集群来选择安全终端状态。这一过程可避免不可行的轨迹，并在可行的情况下选择能让驾驶员更舒适的操纵。随后，动态轨迹规划模块将无碰撞区域转换为混合整数约束，利用时变非线性模型预测控制（NMPC）进行轨迹规划，并通过在整个运动规划过程中整合动态和无碰撞约束来确保车辆运动的稳定性。最终，模拟和现场测试验证了该框架的有效性，在紧急情况下，该框架能够迅速、安全地减少碰撞。该框架可独立于智能驾驶系统自主运行，仅在风险事件发生时介入，并在事件发生后将控制权交还给驾驶员或智能系统。

{"title":"An emergency operation strategy and motion planning method for autonomous vehicle in emergency scenarios","authors":"Tianyang Gong , Xiumin Yu , Qunli Zhang , Zilin Feng , Shichun Yang , Yaoguang Cao , Jingyun Xu , Xinjie Feng , Zhaowen Pang , Yu Wang , Peng Wang","doi":"10.1016/j.aap.2024.107842","DOIUrl":"10.1016/j.aap.2024.107842","url":null,"abstract":"<div><div>Ensuring driving operational safety in emergency scenarios is paramount for autonomous vehicles to prevent accidents, particularly when vehicle motion completely depends on autonomous systems. Numerous factors must be evaluated when designing emergency collision avoidance strategies for critical situations, such as trajectory feasibility, vehicle motion stability, and driver comfort. Therefore, this study proposes a framework for emergency operation that uses collision-free area calculations to inform maneuver decisions and facilitate collision avoidance trajectory planning, preventing vehicle collisions. In case of danger, the emergency maneuver decision module evaluates the safety level and selects safety terminal state by considering a pre-specified cluster of candidate maneuvers before generating trajectories. This process avoids infeasible trajectories and selects maneuvers for greater driver comfort when available. Subsequently, the dynamic trajectory planning module converts the collision-free area into mixed-integer constraints, utilizing time-varying Nonlinear Model Predictive Control (NMPC) for trajectory planning and ensuring vehicle motion stability by integrating dynamic and collision-free constraints throughout the motion planning process. Eventually, simulations and field testing validate the framework’s effectiveness, mitigating collisions in emergency scenarios with prompt and safe operations. The framework is designed to function autonomously, independent of the intelligent driving system, engaging only during risk events and restoring control to the driver or the intelligent system after the event.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"210 ","pages":"Article 107842"},"PeriodicalIF":5.7,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142708936","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

Assessment of the collision risk on the road around schools during morning peak period 评估早高峰期间学校周边道路的碰撞风险。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-11-23 DOI: 10.1016/j.aap.2024.107854

Xiaojian Hu , Haoran Deng , Huasheng Liu , Jiayi Zhou , Hongyu Liang , Long Chen , Li Zhang

Road traffic injury is a leading cause of death among pupils worldwide, particularly around primary schools during rush hours, where heavy traffic, frequent parking, and unpredictable patterns increase accident risk. To mitigate these risks, this study employs the peak-over-threshold method with the generalized pareto distribution to evaluate the spatial–temporal collision risk near primary schools during rush hours. Specifically, the research quantifies collision risks spatially across different road segments (upstream, midstream, and downstream) and lanes (outside, middle, and inside). Temporally, it assesses risks during vehicle gathering, peak vehicle concentration, and vehicle dissipation phases. Results show that collision risk decreases from upstream to downstream but increases from the outside lane to the inside lane. Moreover, collision risks are highest in the middle and outside lanes during the gathering and peak periods in upstream and midstream sections, and in the middle lanes during the dissipation phase. These findings recommend adding parking spaces, minimizing lane changes, reducing speed limits in upstream and midstream, and increasing speed limits in downstream and inside lanes. These measures aim to improve road traffic management policies around schools.

道路交通伤害是全球小学生死亡的主要原因之一，尤其是在上下学高峰时段的小学周围，交通繁忙、停车频繁以及不可预测的交通模式都会增加事故风险。为了降低这些风险，本研究采用了峰值超过阈值法和广义帕累托分布来评估高峰时段小学附近的空间-时间碰撞风险。具体来说，研究从空间上量化了不同路段（上游、中游和下游）和车道（外侧、中间和内侧）的碰撞风险。在时间上，它评估了车辆聚集、车辆集中高峰和车辆消散阶段的风险。结果表明，碰撞风险从上游向下游递减，但从外侧车道向内侧车道递增。此外，在上游和中游路段的聚集期和高峰期，中间车道和外侧车道的碰撞风险最高，而在消散期，中间车道的碰撞风险最高。这些发现建议增加停车位，尽量减少变道，降低上游和中游的限速，提高下游和内侧车道的限速。这些措施旨在改善学校周边的道路交通管理政策。

{"title":"Assessment of the collision risk on the road around schools during morning peak period","authors":"Xiaojian Hu , Haoran Deng , Huasheng Liu , Jiayi Zhou , Hongyu Liang , Long Chen , Li Zhang","doi":"10.1016/j.aap.2024.107854","DOIUrl":"10.1016/j.aap.2024.107854","url":null,"abstract":"<div><div>Road traffic injury is a leading cause of death among pupils worldwide, particularly around primary schools during rush hours, where heavy traffic, frequent parking, and unpredictable patterns increase accident risk. To mitigate these risks, this study employs the peak-over-threshold method with the generalized pareto distribution to evaluate the spatial–temporal collision risk near primary schools during rush hours. Specifically, the research quantifies collision risks spatially across different road segments (upstream, midstream, and downstream) and lanes (outside, middle, and inside). Temporally, it assesses risks during vehicle gathering, peak vehicle concentration, and vehicle dissipation phases. Results show that collision risk decreases from upstream to downstream but increases from the outside lane to the inside lane. Moreover, collision risks are highest in the middle and outside lanes during the gathering and peak periods in upstream and midstream sections, and in the middle lanes during the dissipation phase. These findings recommend adding parking spaces, minimizing lane changes, reducing speed limits in upstream and midstream, and increasing speed limits in downstream and inside lanes. These measures aim to improve road traffic management policies around schools.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"210 ","pages":"Article 107854"},"PeriodicalIF":5.7,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142708941","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

Gender disparities in rural motorcycle accidents: A neural network analysis of travel behavior impact 农村摩托车事故中的性别差异：旅行行为影响的神经网络分析。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-11-22 DOI: 10.1016/j.aap.2024.107840

Ittirit Mohamad

Rural road accidents involving motorcycle riders present a formidable challenge to road safety globally. This study offers a comprehensive gender-based comparative analysis of rural road accidents among motorcycle riders, aimed at illuminating factors contributing to accidents and discerning potential gender disparities in accident rates and severity. Employing a sophisticated Neural Network approach, the research delves into the intricate relationship between various variables and accident outcomes, with a specific emphasis on identifying gender-specific patterns. For female riders, the ANN model demonstrates impressive overall accuracy (CA) of 92 %, indicating its capability to correctly classify accident outcomes. Precision, which measures the model’s ability to avoid false positives, stands at a commendable 90.8 %. Moreover, the model exhibits high recall (92 %) and F1 score (88.4 %), indicating its effectiveness in identifying both fatal and non-fatal accidents among female riders. Additionally, the Matthews Correlation Coefficient (MCC) of 0.132 suggests a moderate level of agreement between the predicted and actual outcomes. Upon further examination, it is evident that the model performs exceptionally well in predicting non-fatal accidents for female riders, achieving a precision, recall, and F1 score of 92 %, 99.9 %, and 95.8 %, respectively. However, its performance in predicting fatalities is relatively lower, with a precision of 75.6 % and recall of 2.6 %, resulting in a lower F1 score of 5.0 %. Despite this disparity, the MCC remains consistent at 0.132, indicating a balanced performance across both classes. The findings reveal valuable insights for policymakers and road safety practitioners, providing avenues for the development of targeted interventions and the enhancement of safety measures for motorcycle riders on rural roads. By addressing the gap in understanding gender-related differences in travel habits and accident risks, this research contributes to ongoing efforts to mitigate the impact of road accidents and promote safer travel environments for all road users.

涉及摩托车骑手的农村道路交通事故是全球道路安全面临的一项严峻挑战。本研究以性别为基础，对农村道路摩托车驾驶员交通事故进行了全面的比较分析，旨在揭示导致事故的因素，并发现事故发生率和严重程度方面潜在的性别差异。研究采用了复杂的神经网络方法，深入探讨了各种变量与事故结果之间错综复杂的关系，并特别强调了识别特定性别的模式。对于女性骑手，ANN 模型的总体准确率（CA）高达 92%，令人印象深刻，这表明该模型有能力对事故结果进行正确分类。精度（衡量模型避免误报的能力）为 90.8%，值得称赞。此外，该模型还表现出较高的召回率（92 %）和 F1 分数（88.4 %），表明其在识别女性骑手的致命和非致命事故方面都很有效。此外，马修斯相关系数（MCC）为 0.132，表明预测结果与实际结果之间具有中等程度的一致性。进一步研究表明，该模型在预测女性骑手的非致命事故方面表现优异，精确度、召回率和 F1 分数分别达到 92%、99.9% 和 95.8%。然而，该模型在预测死亡事故方面的表现相对较差，精确度为 75.6%，召回率为 2.6%，F1 分数较低，为 5.0%。尽管存在这种差异，但 MCC 仍保持在 0.132，表明两个类别的性能均衡。研究结果为政策制定者和道路安全从业人员提供了宝贵的见解，为制定有针对性的干预措施和加强农村道路摩托车驾驶员的安全措施提供了途径。这项研究弥补了人们对出行习惯和事故风险中与性别有关的差异认识上的不足，有助于减轻道路事故的影响，为所有道路使用者提供更安全的出行环境。

{"title":"Gender disparities in rural motorcycle accidents: A neural network analysis of travel behavior impact","authors":"Ittirit Mohamad","doi":"10.1016/j.aap.2024.107840","DOIUrl":"10.1016/j.aap.2024.107840","url":null,"abstract":"<div><div>Rural road accidents involving motorcycle riders present a formidable challenge to road safety globally. This study offers a comprehensive gender-based comparative analysis of rural road accidents among motorcycle riders, aimed at illuminating factors contributing to accidents and discerning potential gender disparities in accident rates and severity. Employing a sophisticated Neural Network approach, the research delves into the intricate relationship between various variables and accident outcomes, with a specific emphasis on identifying gender-specific patterns. For female riders, the ANN model demonstrates impressive overall accuracy (CA) of 92 %, indicating its capability to correctly classify accident outcomes. Precision, which measures the model’s ability to avoid false positives, stands at a commendable 90.8 %. Moreover, the model exhibits high recall (92 %) and F1 score (88.4 %), indicating its effectiveness in identifying both fatal and non-fatal accidents among female riders. Additionally, the Matthews Correlation Coefficient (MCC) of 0.132 suggests a moderate level of agreement between the predicted and actual outcomes. Upon further examination, it is evident that the model performs exceptionally well in predicting non-fatal accidents for female riders, achieving a precision, recall, and F1 score of 92 %, 99.9 %, and 95.8 %, respectively. However, its performance in predicting fatalities is relatively lower, with a precision of 75.6 % and recall of 2.6 %, resulting in a lower F1 score of 5.0 %. Despite this disparity, the MCC remains consistent at 0.132, indicating a balanced performance across both classes. The findings reveal valuable insights for policymakers and road safety practitioners, providing avenues for the development of targeted interventions and the enhancement of safety measures for motorcycle riders on rural roads. By addressing the gap in understanding gender-related differences in travel habits and accident risks, this research contributes to ongoing efforts to mitigate the impact of road accidents and promote safer travel environments for all road users.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"210 ","pages":"Article 107840"},"PeriodicalIF":5.7,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142695121","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

One-pedal or two-pedal: Does the regenerative braking system improve driving safety? 单踏板还是双踏板？再生制动系统能提高驾驶安全性吗？

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-11-21 DOI: 10.1016/j.aap.2024.107832

Jun Ma , Xu Zhang , Wenxia Xu , Jiateng Li , Zaiyan Gong , Jingyi Zhao

Electric vehicles equipped with regenerative braking systems provide drivers a new driving mode, the one-pedal mode, which enables drivers to accelerate and decelerate with the throttle alone. However, there is a lack of systematic research on driving behavior in one-pedal mode, and whether it actually enhances or reduces safety remains to be validated. A driving simulator was used to analyze driving behavior and safety in the one-pedal mode in situations with different urgency level, with the two-pedal mode (the traditional driving mode in internal combustion engine vehicles) serving as a comparative group. The driver’s perception times, initial and final throttle release times, throttle to brake transition times, maximum brake pedal forces, collision ratios, and time-to-collision (TTC) were measured under the lead vehicle decelerating at 0.1 g, 0.2 g, 0.5 g, 0.75 g, as well as uncertainty (decelerating at 0.2 g to 25 km/h, then decelerating at 0.75 g to 0), and under headways of 1.5 s and 2.5 s. Results showed: 1) The regenerative braking system did not affect driver perception and reaction of the lead vehicle braking event and drivers extended throttle release to avoid rapid speed drops when the lead vehicle braked slowly; 2) the one-pedal mode exhibited a longer throttle to brake transition time and increased uncertainty in timing of brake pedal application; 3) the one-pedal mode was safer than the two-pedal mode in low urgency situations but became unsafe in high urgency or uncertain situations due to delayed braking. The implications of this research include enhancing regenerative braking systems and developing forward collision warning systems.

配备再生制动系统的电动汽车为驾驶员提供了一种新的驾驶模式--单踏板模式，使驾驶员可以仅通过油门加速和减速。然而，目前还缺乏关于单踏板模式下驾驶行为的系统研究，这种模式究竟是提高了安全性还是降低了安全性，还有待验证。本研究使用驾驶模拟器分析了在不同紧急程度情况下单踏板模式下的驾驶行为和安全性，并将双踏板模式（内燃机汽车的传统驾驶模式）作为对比组。在主车减速 0.1 g、0.2 g、0.5 g、0.75 g 以及不确定情况（减速 0.2 g 至 25 km/h，然后减速 0.75 g 至 0）下，并在车头间距为 1.5 s 和 2.5 s 的情况下，测量了驾驶员的感知时间、油门初始和最终释放时间、油门到制动器的转换时间、最大制动踏板力、碰撞比率和碰撞时间（TTC）。结果显示1）再生制动系统不影响驾驶员对前导车辆制动事件的感知和反应，当前导车辆缓慢制动时，驾驶员会延长油门释放时间以避免车速急剧下降；2）单踏板模式表现出较长的油门到制动过渡时间，并且制动踏板踩下时间的不确定性增加；3）在低紧迫性情况下，单踏板模式比双踏板模式更安全，但在高紧迫性或不确定情况下，由于制动延迟，单踏板模式变得不安全。这项研究的意义包括增强再生制动系统和开发前撞预警系统。

{"title":"One-pedal or two-pedal: Does the regenerative braking system improve driving safety?","authors":"Jun Ma , Xu Zhang , Wenxia Xu , Jiateng Li , Zaiyan Gong , Jingyi Zhao","doi":"10.1016/j.aap.2024.107832","DOIUrl":"10.1016/j.aap.2024.107832","url":null,"abstract":"<div><div>Electric vehicles equipped with regenerative braking systems provide drivers a new driving mode, the one-pedal mode, which enables drivers to accelerate and decelerate with the throttle alone. However, there is a lack of systematic research on driving behavior in one-pedal mode, and whether it actually enhances or reduces safety remains to be validated. A driving simulator was used to analyze driving behavior and safety in the one-pedal mode in situations with different urgency level, with the two-pedal mode (the traditional driving mode in internal combustion engine vehicles) serving as a comparative group. The driver’s perception times, initial and final throttle release times, throttle to brake transition times, maximum brake pedal forces, collision ratios, and time-to-collision (TTC) were measured under the lead vehicle decelerating at 0.1 g, 0.2 g, 0.5 g, 0.75 g, as well as uncertainty (decelerating at 0.2 g to 25 km/h, then decelerating at 0.75 g to 0), and under headways of 1.5 s and 2.5 s. Results showed: 1) The regenerative braking system did not affect driver perception and reaction of the lead vehicle braking event and drivers extended throttle release to avoid rapid speed drops when the lead vehicle braked slowly; 2) the one-pedal mode exhibited a longer throttle to brake transition time and increased uncertainty in timing of brake pedal application; 3) the one-pedal mode was safer than the two-pedal mode in low urgency situations but became unsafe in high urgency or uncertain situations due to delayed braking. The implications of this research include enhancing regenerative braking systems and developing forward collision warning systems.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"210 ","pages":"Article 107832"},"PeriodicalIF":5.7,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142692537","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

Driving characteristics of static obstacle avoidance by drivers in mountain highway tunnels − A lateral safety distance judgement 山区公路隧道中驾驶员静态避障的驾驶特性--横向安全距离判断。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-11-20 DOI: 10.1016/j.aap.2024.107845

Ying Chen , Zhigang Du , Jin Xu , Shuang Luo

Static obstacles (tunnel sidewalls, barricades, etc.) on the side of mountainous highways change the spatial range of the road during driving, restricting the driver’s freedom of driving while possibly triggering the driver’s shy away effect, which poses a specific potential safety hazard. To understand the characteristics of driving behaviour in mountain highway tunnels with different tunnel lengths and lateral obstacles, nine tunnels in Chongqing were selected for real-vehicle tests, and data on driving trajectories, speeds and other metrics were collected from 40 drivers. Analyse the driver’s need for lateral safety distance in different scenarios, defines the conditions and scope of the shy away effect, and establishes a multi-scenario “distance-trajectory” offset prediction model to adjust the offset under varying lateral environments by setting different facilities. The results show that drivers exhibit some avoidance behavior towards lateral static obstacles, but the extent of the shy-away effect varies based on tunnel length. By widening the lateral clearance to 0.925 m on the left side and 1.450 m on the right side of the road to meet the driver’s requirements for lateral safety distances, unreasonable avoidance behaviour can be reduced. Combined with the trajectory fluctuation characteristics of drivers in different tunnels, it is proposed to set up the traffic safety facilities in a manner more aligned with driver behavioral habits, with a place set up 110 m before the entrance of the short tunnel, two places set up in the medium tunnel at L/2 − 200 m, L/2 + 100 m (where L is the length of the tunnel), and three places for long tunnels at L/2 − 400 m, L/2 m, and L/2 + 300 m. For extra-long tunnels, facilities are to be set up in cycles of 500 m, 1000 m, and 1500 m intervals. In the cross-section where different drivers are prone to apparent trajectory offsets, a driving behavior prompt sign is added to help correct the driving trajectory.

山区公路边的静态障碍物（隧道侧壁、路障等）改变了行车过程中的道路空间范围，限制了驾驶员的驾驶自由，同时可能引发驾驶员的退避效应，存在特定的安全隐患。为了解不同隧道长度和横向障碍物的山区公路隧道驾驶行为特征，我们在重庆选取了9个隧道进行实车测试，并收集了40名驾驶员的驾驶轨迹、速度等指标数据。分析不同场景下驾驶员对横向安全距离的需求，明确避让效应产生的条件和范围，建立多场景 "距离-轨迹 "偏移预测模型，通过设置不同设施调整不同横向环境下的偏移量。结果表明，驾驶员对横向静态障碍物表现出一定的回避行为，但回避效应的程度因隧道长度而异。为满足驾驶员对横向安全距离的要求，可将道路左侧的横向间隙加宽至 0.925 米，右侧加宽至 1.450 米，从而减少不合理的避让行为。结合不同隧道内驾驶员的轨迹波动特点，建议以更符合驾驶员行为习惯的方式设置交通安全设施，短隧道在入口前110米处设置一处，中隧道在L/2-200米、L/2+100米处（其中L为隧道长度）设置两处，长隧道在L/2-400米、L/2米、L/2+300米处设置三处。对于超长隧道，设施将以 500 米、1000 米和 1500 米的间隔循环设置。在不同驾驶员容易出现明显轨迹偏移的断面，增加驾驶行为提示标志，帮助纠正驾驶轨迹。

{"title":"Driving characteristics of static obstacle avoidance by drivers in mountain highway tunnels − A lateral safety distance judgement","authors":"Ying Chen , Zhigang Du , Jin Xu , Shuang Luo","doi":"10.1016/j.aap.2024.107845","DOIUrl":"10.1016/j.aap.2024.107845","url":null,"abstract":"<div><div>Static obstacles (tunnel sidewalls, barricades, etc.) on the side of mountainous highways change the spatial range of the road during driving, restricting the driver’s freedom of driving while possibly triggering the driver’s shy away effect, which poses a specific potential safety hazard. To understand the characteristics of driving behaviour in mountain highway tunnels with different tunnel lengths and lateral obstacles, nine tunnels in Chongqing were selected for real-vehicle tests, and data on driving trajectories, speeds and other metrics were collected from 40 drivers. Analyse the driver’s need for lateral safety distance in different scenarios, defines the conditions and scope of the shy away effect, and establishes a multi-scenario “distance-trajectory” offset prediction model to adjust the offset under varying lateral environments by setting different facilities. The results show that drivers exhibit some avoidance behavior towards lateral static obstacles, but the extent of the shy-away effect varies based on tunnel length. By widening the lateral clearance to 0.925 m on the left side and 1.450 m on the right side of the road to meet the driver’s requirements for lateral safety distances, unreasonable avoidance behaviour can be reduced. Combined with the trajectory fluctuation characteristics of drivers in different tunnels, it is proposed to set up the traffic safety facilities in a manner more aligned with driver behavioral habits, with a place set up 110 m before the entrance of the short tunnel, two places set up in the medium tunnel at <em>L</em>/2 − 200 m, <em>L</em>/2 + 100 m (where <em>L</em> is the length of the tunnel), and three places for long tunnels at <em>L</em>/2 − 400 m, <em>L</em>/2 m, and <em>L</em>/2 + 300 m. For extra-long tunnels, facilities are to be set up in cycles of 500 m, 1000 m, and 1500 m intervals. In the cross-section where different drivers are prone to apparent trajectory offsets, a driving behavior prompt sign is added to help correct the driving trajectory.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"210 ","pages":"Article 107845"},"PeriodicalIF":5.7,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142685734","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

Revisiting the correlation between simulated and field-observed conflicts using large-scale traffic reconstruction 利用大规模交通重建重新审视模拟冲突与实地观察冲突之间的相关性。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-11-20 DOI: 10.1016/j.aap.2024.107808

Ao Qu, Cathy Wu

Safety is a critical aspect of traffic systems. However, traditional crash data-based methods suffer from scalability and generalization issues. Although SSMs offer a proactive alternative for safety evaluation, their validation in simulated settings remains inconsistent, especially with emerging mobility technologies like autonomous driving. Our study critiques existing methodologies in SSM validation and introduces a novel framework integrating micro-level driver models with macro-level traffic states. This approach accounts for diverse external factors, including weather and geographical variations. Utilizing the Caltrans Performance Measurement System (PeMS) data, we conduct a large-scale analysis, merging traffic simulation with real-world data to extract SSMs and correlate them with crash statistics. Our results indicate a significant correlation between SSM counts and crash numbers but no clear trend with varying SSM thresholds. This suggests limitations in current public data for establishing robust links between simulated SSMs and real-world crashes. Our study highlights the need for improved data collection and simulation techniques, paving the way for more accurate and meaningful roadway safety analysis in the era of advanced mobility systems.

安全是交通系统的一个重要方面。然而，基于碰撞数据的传统方法存在可扩展性和通用性问题。虽然 SSM 为安全评估提供了一种积极的替代方法，但其在模拟环境中的验证仍不一致，尤其是在自动驾驶等新兴移动技术方面。我们的研究对现有的 SSM 验证方法进行了批判，并引入了一种将微观层面的驾驶员模型与宏观层面的交通状态相结合的新型框架。这种方法考虑了各种外部因素，包括天气和地理变化。利用加州交通局性能测量系统（PeMS）的数据，我们进行了大规模的分析，将交通模拟与真实世界的数据相结合，以提取 SSM 并将其与碰撞统计相关联。我们的结果表明，SSM 数量与碰撞次数之间存在明显的相关性，但随着 SSM 临界值的变化，两者之间并没有明显的趋势。这表明目前的公共数据在建立模拟 SSM 与实际碰撞事故之间的稳健联系方面存在局限性。我们的研究强调了改进数据收集和模拟技术的必要性，为在先进交通系统时代进行更准确、更有意义的道路安全分析铺平了道路。

{"title":"Revisiting the correlation between simulated and field-observed conflicts using large-scale traffic reconstruction","authors":"Ao Qu, Cathy Wu","doi":"10.1016/j.aap.2024.107808","DOIUrl":"10.1016/j.aap.2024.107808","url":null,"abstract":"<div><div>Safety is a critical aspect of traffic systems. However, traditional crash data-based methods suffer from scalability and generalization issues. Although SSMs offer a proactive alternative for safety evaluation, their validation in simulated settings remains inconsistent, especially with emerging mobility technologies like autonomous driving. Our study critiques existing methodologies in SSM validation and introduces a novel framework integrating micro-level driver models with macro-level traffic states. This approach accounts for diverse external factors, including weather and geographical variations. Utilizing the Caltrans Performance Measurement System (PeMS) data, we conduct a large-scale analysis, merging traffic simulation with real-world data to extract SSMs and correlate them with crash statistics. Our results indicate a significant correlation between SSM counts and crash numbers but no clear trend with varying SSM thresholds. This suggests limitations in current public data for establishing robust links between simulated SSMs and real-world crashes. Our study highlights the need for improved data collection and simulation techniques, paving the way for more accurate and meaningful roadway safety analysis in the era of advanced mobility systems.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"210 ","pages":"Article 107808"},"PeriodicalIF":5.7,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142685735","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

V-FCW: Vector-based forward collision warning algorithm for curved road conflicts using V2X networks V-FCW：利用 V2X 网络针对弯道冲突的基于向量的前向碰撞预警算法。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-11-20 DOI: 10.1016/j.aap.2024.107836

Xiangpeng Cai , Bowen Lv , Hanchen Yao , Ting Yang , Houde Dai

The implementation of advanced driver assistance systems (ADAS) has significantly impacted the prevention of traffic accidents, particularly through the forward collision warning (FCW) algorithm. Nevertheless, traffic conflicts on traffic routes remain a significant issue, since most FCW algorithms cannot accurately determine the distance between the host vehicle (HV) and remote vehicle (RV) on curved roads. Hence, this study proposes a vector-based FCW (V-FCW) algorithm to address the issue of false warnings on unconventional road sections. The V-FCW algorithm employs vector relationships to estimate the poses of HV and RV at the current and next moments, thereby effectively calculating the relative angles. Firstly, the HV and RV transmit their position vector, velocity vector, and heading angle in real time via the vehicle-to-vehicle (V2V) communication technique. Subsequently, the localization of lanes is conducted through the vehicle-to-infrastructure (V2I) communication technique, with the assistance of roadside unit (RSU)-based local maps. Finally, a V-FCW algorithm was implemented on the Simcenter Prescan simulation platform and a cellular vehicle-to-everything (C-V2X, i.e., the combination of V2V and V2I) communication platform. The simulation results demonstrate that the proposed V-FCW algorithm can accurately identify and warn dangerous vehicles on both straight and curved roads. Moreover, the experimental results obtained from the hardware-in-the-loop approach illustrate the efficacy of the proposed V-FCW algorithm in accurately forecasting four warning levels on both straight and curved roads. Consequently, this study yields a significant contribution to the field of vehicle-road cooperation in C-V2X-enable intelligent driving.

高级驾驶员辅助系统（ADAS）的实施对预防交通事故产生了重大影响，特别是通过前撞预警（FCW）算法。然而，交通路线上的交通冲突仍然是一个重要问题，因为大多数 FCW 算法无法在弯曲的道路上准确确定主机车辆（HV）和远程车辆（RV）之间的距离。因此，本研究提出了一种基于矢量的 FCW（V-FCW）算法，以解决非常规路段上的误报问题。V-FCW 算法利用矢量关系来估计 HV 和 RV 在当前和下一时刻的姿态，从而有效计算相对角度。首先，HV 和 RV 通过车对车（V2V）通信技术实时传输其位置矢量、速度矢量和航向角。随后，通过车对基础设施（V2I）通信技术，在基于路边装置（RSU）的本地地图的辅助下，进行车道定位。最后，在 Simcenter Prescan 仿真平台和蜂窝式车对物（C-V2X，即 V2V 和 V2I 的结合）通信平台上实现了 V-FCW 算法。仿真结果表明，所提出的 V-FCW 算法可以在直线和曲线道路上准确识别和警告危险车辆。此外，通过硬件在环方法获得的实验结果表明，所提出的 V-FCW 算法能在直线和曲线道路上准确预测四个警告级别。因此，本研究为 C-V2X 智能驾驶中的车路协同领域做出了重要贡献。

{"title":"V-FCW: Vector-based forward collision warning algorithm for curved road conflicts using V2X networks","authors":"Xiangpeng Cai , Bowen Lv , Hanchen Yao , Ting Yang , Houde Dai","doi":"10.1016/j.aap.2024.107836","DOIUrl":"10.1016/j.aap.2024.107836","url":null,"abstract":"<div><div>The implementation of advanced driver assistance systems (ADAS) has significantly impacted the prevention of traffic accidents, particularly through the forward collision warning (FCW) algorithm. Nevertheless, traffic conflicts on traffic routes remain a significant issue, since most FCW algorithms cannot accurately determine the distance between the host vehicle (HV) and remote vehicle (RV) on curved roads. Hence, this study proposes a vector-based FCW (V-FCW) algorithm to address the issue of false warnings on unconventional road sections. The V-FCW algorithm employs vector relationships to estimate the poses of HV and RV at the current and next moments, thereby effectively calculating the relative angles. Firstly, the HV and RV transmit their position vector, velocity vector, and heading angle in real time via the vehicle-to-vehicle (V2V) communication technique. Subsequently, the localization of lanes is conducted through the vehicle-to-infrastructure (V2I) communication technique, with the assistance of roadside unit (RSU)-based local maps. Finally, a V-FCW algorithm was implemented on the Simcenter Prescan simulation platform and a cellular vehicle-to-everything (C-V2X, i.e., the combination of V2V and V2I) communication platform. The simulation results demonstrate that the proposed V-FCW algorithm can accurately identify and warn dangerous vehicles on both straight and curved roads. Moreover, the experimental results obtained from the hardware-in-the-loop approach illustrate the efficacy of the proposed V-FCW algorithm in accurately forecasting four warning levels on both straight and curved roads. Consequently, this study yields a significant contribution to the field of vehicle-road cooperation in C-V2X-enable intelligent driving.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"210 ","pages":"Article 107836"},"PeriodicalIF":5.7,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142685736","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

Detection and analysis of corner case scenarios at a signalized urban intersection 检测和分析信号灯控制的城市十字路口的拐角情况。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-11-20 DOI: 10.1016/j.aap.2024.107838

Clemens Schicktanz , Kay Gimm

One of the major challenges in automated driving is ensuring that the system can handle all possible driving scenarios, including rare and critical ones, also referred to as corner case scenarios. For the validation of automated driving functions, it is necessary to test the corner cases in simulation environments. However, the effectiveness of simulation-based testing depends on the availability of realistic test data that accurately reflect real-world scenarios. This work aims to detect, cluster, and analyze rare and critical traffic scenarios based on real-world traffic data from an urban intersection and prepare the data for usage in simulation environments. The scenarios are detected by filtering hard braking maneuvers, red light violations, and near misses under adverse weather conditions. A long-term analysis of trajectory, weather, and traffic light data was conducted to find these rare scenarios. Our results show that 24 hard braking maneuvers are included in our dataset with a duration of half a year. They occur due to failure to yield, emergency vehicle operations, and a red light violation. Some of the scenarios include crashes, lateral evasive maneuvers, or are under adverse weather conditions like fog. Altogether, we provide methods to extract corner case scenarios based on multiple data sources and reveal diverse types of corner case scenarios at an urban intersection. In addition, we analyze the behavior of road users in critical scenarios and show influencing factors to avoid crashes. By combining and converting the data to an industry standard for simulation we provide realistic test cases for the validation of automated vehicles. Therefore, the results are relevant for both, traffic safety researchers to learn from road user behavior in these rare scenarios and developers of automated driving systems to test their functions.

自动驾驶面临的主要挑战之一是确保系统能够处理所有可能的驾驶场景，包括罕见和关键场景，也称为 "边角情况"。为了验证自动驾驶功能，有必要在模拟环境中测试角情况。然而，模拟测试的有效性取决于能否获得准确反映真实世界场景的真实测试数据。这项工作的目的是根据城市十字路口的真实交通数据，检测、聚类和分析罕见的关键交通场景，并为在模拟环境中使用这些数据做好准备。这些场景是通过过滤急刹车、闯红灯和恶劣天气条件下的险情而检测到的。为了找到这些罕见场景，我们对轨迹、天气和交通灯数据进行了长期分析。结果显示，我们的数据集中包含了 24 个持续时间为半年的急刹车动作。它们发生的原因包括未让行、紧急车辆操作和闯红灯。其中一些场景包括撞车、横向规避机动，或者是在大雾等恶劣天气条件下。总之，我们提供了基于多种数据源提取拐角情况的方法，并揭示了城市交叉口的各种拐角情况。此外，我们还分析了道路使用者在关键场景中的行为，并展示了避免碰撞的影响因素。通过将数据合并并转换为行业模拟标准，我们为自动驾驶汽车的验证提供了真实的测试案例。因此，研究结果对交通安全研究人员和自动驾驶系统开发人员都具有重要意义，前者可以从这些罕见场景中的道路使用者行为中汲取经验，后者可以测试自动驾驶系统的功能。

{"title":"Detection and analysis of corner case scenarios at a signalized urban intersection","authors":"Clemens Schicktanz , Kay Gimm","doi":"10.1016/j.aap.2024.107838","DOIUrl":"10.1016/j.aap.2024.107838","url":null,"abstract":"<div><div>One of the major challenges in automated driving is ensuring that the system can handle all possible driving scenarios, including rare and critical ones, also referred to as corner case scenarios. For the validation of automated driving functions, it is necessary to test the corner cases in simulation environments. However, the effectiveness of simulation-based testing depends on the availability of realistic test data that accurately reflect real-world scenarios. This work aims to detect, cluster, and analyze rare and critical traffic scenarios based on real-world traffic data from an urban intersection and prepare the data for usage in simulation environments. The scenarios are detected by filtering hard braking maneuvers, red light violations, and near misses under adverse weather conditions. A long-term analysis of trajectory, weather, and traffic light data was conducted to find these rare scenarios. Our results show that 24 hard braking maneuvers are included in our dataset with a duration of half a year. They occur due to failure to yield, emergency vehicle operations, and a red light violation. Some of the scenarios include crashes, lateral evasive maneuvers, or are under adverse weather conditions like fog. Altogether, we provide methods to extract corner case scenarios based on multiple data sources and reveal diverse types of corner case scenarios at an urban intersection. In addition, we analyze the behavior of road users in critical scenarios and show influencing factors to avoid crashes. By combining and converting the data to an industry standard for simulation we provide realistic test cases for the validation of automated vehicles. Therefore, the results are relevant for both, traffic safety researchers to learn from road user behavior in these rare scenarios and developers of automated driving systems to test their functions.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"210 ","pages":"Article 107838"},"PeriodicalIF":5.7,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142685733","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}

引用次数: 0