Accident; analysis and prevention最新文献

{"title":"Recognizing autonomous driving disengagement scenarios using the transferable knowledge from human driver’s EEG cognitive data","authors":"Geqi Qi ,&nbsp;Shuo Zhao ,&nbsp;Jixiang Yu ,&nbsp;Peihao Li ,&nbsp;Wei Guan","doi":"10.1016/j.aap.2025.108102","DOIUrl":"10.1016/j.aap.2025.108102","url":null,"abstract":"<div><div>Without human participation in driving operations, the adoption of autonomous driving (AD) technology greatly enhances driving safety by reducing human errors. Even though AD can handle common scenarios properly, some exceptions still call for the human takeover with AD failing to engage due to the incomprehensible or intensely conflict situations that rarely occur. To help AD understand and recognize the disengagement scenarios effectively, this paper incorporates the human electroencephalogram (EEG) cognitive data into modeling and proposes a transfer learning framework to let AD absorb the integrative knowledge from the manual driving (MD). Several disengagement scenarios are designed using a driving simulator and EEG data are collected from both “drivers” in MD and “supervisors” in AD. A conditional maximum mean discrepancy (CMMD) function is introduced to identify the common brain activity characteristics, allowing the recognition model to be transferred from the cognitively demanding domain of MD to the less demanding domain of AD. The results indicate that the proposed model can achieve an 80 % recognition rate for typical disengagement scenarios, such as static obstacles, intersection conflict and vehicle cut-in, using only 30 % of AD training labels. The transferable common feature space from EEG data improves the recognition accuracy by 21.2 % compared with the model only using AD domain data. By accurately recognizing the type of disengagement scenarios, the AD system can activate appropriate safety mechanisms or provide more explicit takeover prompts, which could effectively reduce the risk of accidents due to delayed or incorrect takeovers.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"219 ","pages":"Article 108102"},"PeriodicalIF":5.7,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070995","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":"Context-dependent effects of built environment factors on pedestrian-injury severities with imbalanced and high dimensional crash data","authors":"Zehao Wang,&nbsp;Wei Fan","doi":"10.1016/j.aap.2025.108104","DOIUrl":"10.1016/j.aap.2025.108104","url":null,"abstract":"<div><div>Built environment is an important component that influences pedestrian injury severities in pedestrian-vehicle crashes. Previous studies indicated that the effects of various built environment factors on pedestrian injury severities are heterogeneous, meaning the direction of their effects varies under different conditions. This heterogeneity poses a challenge in developing effective countermeasures. Therefore, this study aims to explore the context-dependent effects of built environment factors and uncover the potential sources of this heterogeneity. Using North Carolina crash data (2017–2022) as a case study, an enhanced machine learning framework that incorporates a conditional tabular generative adversarial network and wrapper-based feature selection techniques is designed to investigate the context-dependent effects. The enhancements seek to mitigate the adverse impacts associated with imbalanced and high dimensional crash data. Model results show that 13 out of the top 19 important factors belong to built environment factors, with 11 of these factors (i.e., restaurants present and road class) being heterogeneous. The context-dependent effects analysis can help identify conditions for the positive effects of heterogeneous factors. For example, restaurants near the local routes or in urban areas, higher-grade roads (i.e., US, Interstate, and NC routes) in better economically developed counties, and signs or signals control roads under dark (with or without) roadway light conditions have clear positive effects on pedestrian injury severities. These findings can provide guidance for urban planning and policy development, thereby promoting the sustainable development of cities, regions, and transportation systems.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"218 ","pages":"Article 108104"},"PeriodicalIF":5.7,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143941988","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":"Can mid-block pedestrian signals (MPS) provide greater safety benefits than other mid-block pedestrian crossings?","authors":"Md Jamil Ahsan,&nbsp;Mohamed Abdel-Aty,&nbsp;Ahmed S. Abdelrahman","doi":"10.1016/j.aap.2025.108105","DOIUrl":"10.1016/j.aap.2025.108105","url":null,"abstract":"<div><div>The Florida Department of Transportation (FDOT) has recently implemented a new midblock signal system known as the Midblock Pedestrian Signal (MPS) to enhance pedestrian safety. This study evaluates the effectiveness of MPSs by comparing their safety performance with other existing midblock crossing treatments. Portable CCTV video data were collected from 14 MPS equipped locations, in addition to five reference sites, to calculate Conflict Modification Factors (CoMFs) using vehicle–pedestrian conflict data. Advanced computer vision techniques, specifically the RT-DETR model for object detection and the ByteTrack algorithm for tracking were utilized to process the video data. The study employed both Cross-Sectional (CS) and Before-After methods, incorporating the Comparison Group (CG) and Empirical Bayesian (EB) approaches to evaluate the safety impacts of MPSs. To address repeated observations at the same locations and minimize bias, Safety Performance Functions (SPFs) were developed using Generalized Estimating Equations (GEE) with a Negative Binomial distribution, which proved more robust than traditional Generalized Linear Models (GLMs). The results demonstrate that MPS systems outperform Rectangular Rapid Flashing Beacons (RRFBs) and Flashing Beacons in reducing pedestrian-vehicle conflicts. Furthermore, when compared to Pedestrian Hybrid Beacons (PHBs) which share similar functionalities but differ in signal phase management—MPS systems provided additional safety benefits. Compared to PHBs, MPS systems reduced serious and all conflicts by between 26–33% and 31–33%, respectively, using the EB, CG and the CS methods. These reductions highlight the superior safety performance of MPS systems compared to PHBs and other midblock crossing treatments. With their adaptability, cost-effectiveness, and enhanced safety benefits, MPS systems are a promising alternative for upgrading existing pedestrian crossings or installing new signal systems to improve pedestrian safety at midblock locations.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"218 ","pages":"Article 108105"},"PeriodicalIF":5.7,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143941987","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":"Do motorists select safe routes over efficient routes? An empirical study using travel trajectory data","authors":"Wei Hao ,&nbsp;Fang Liu ,&nbsp;Chunyang Han ,&nbsp;Amjad Pervez ,&nbsp;Kai Wang ,&nbsp;Jie Chen ,&nbsp;Jinjun Tang","doi":"10.1016/j.aap.2025.108090","DOIUrl":"10.1016/j.aap.2025.108090","url":null,"abstract":"<div><div>Studies have highlighted the importance of traffic safety concerns in travelers’ mode choices. However, little attention has been given to route choices between safety and efficiency. This study aims to investigate motorists’ safety route choice behavior using vehicle trajectory data collected by the Automatic License Plate Recognition (ALPR) system in Changsha, China. A paired scenario comparison (PSC) method is proposed to examine motorists’ safety route choice behaviors by contrasting the choices under two scenarios across a large-scale city area. Specifically, four scenarios are considered, including daytime/nighttime, work/non-work, livelihood/non-livelihood, and short-distance/long-distance travel. Motorists’ route choice preferences are hypothesized to differ between paired scenarios. Motorists’ route choices are depicted by the Group Random Parameters Logit (GRPL) model with a set of route safety and efficiency attributes. Hypotheses are tested through an overall model validation and a series of scenario-specific model validations. Results demonstrate the significance of motorists’ priority of the routes with safety attributes (e.g., fewer intersections, wider roads) during nighttime trips or for non-livelihood purposes. However, evidence for work/non-work and trip distance effects remains inconclusive. This study provides empirical support for safety-oriented route planning and navigation systems.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"218 ","pages":"Article 108090"},"PeriodicalIF":5.7,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143941989","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":"Why anticipatory sensing matters in commercial ACC systems under cut-in scenarios: A perspective from stochastic safety analysis","authors":"Hao Zhang,&nbsp;Sixu Li,&nbsp;Zihao Li,&nbsp;Mohammad Anis,&nbsp;Dominique Lord,&nbsp;Yang Zhou","doi":"10.1016/j.aap.2025.108064","DOIUrl":"10.1016/j.aap.2025.108064","url":null,"abstract":"<div><div>This study presents an analytical solution for the vehicle state evolution of Adaptive Cruise Control (ACC) systems under cut-in scenarios, incorporating sensing delays and anticipation using the Lambert W function. The theoretical analysis demonstrates that the vehicle state evolution and the corresponding safety of ACC in cut-in situations are influenced by multiple factors, including the original leading vehicle’s state, the initial conditions of the cut-in vehicle, subsequent cut-in maneuvers, sensing delays, and the ACC’s anticipation capabilities.</div><div>To quantitatively assess these influences, a series of numerical experiments were conducted to perform a stochastic safety analysis of ACC systems, accounting for embedded sensing delays and anticipation, using empirically calibrated control parameters from real-world data. The experiments revealed that the impact of sensing delays on ACC is multifaceted. Specifically, sensing delays negatively affect ACC stability, with the severity increasing as the delay lengthens. Furthermore, collision risk in cut-in scenarios becomes more significant with sensing delays, particularly when the cut-in vehicle is slower than the following vehicle and when cut-ins are aggressive.</div><div>However, anticipation plays a crucial role in mitigating these risks. Even with a 0.6-second anticipation, collision risk can be reduced by 91% in highly adverse scenarios. Both sensing delays and anticipation have effects that intensify with their duration. An anticipation period of 2 s effectively ensures safety in aggressive cut-in conditions, even in the presence of sensing delays.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"218 ","pages":"Article 108064"},"PeriodicalIF":5.7,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143932206","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":"Association between automatic emergency braking and pedestrian and cyclist injury severity in Japan","authors":"Haruhiko Inada ,&nbsp;Masao Ichikawa","doi":"10.1016/j.aap.2025.108091","DOIUrl":"10.1016/j.aap.2025.108091","url":null,"abstract":"<div><div>This cross-sectional study assessed whether automatic emergency braking (AEB) in colliding passenger cars is associated with reduced injury severity among pedestrians and cyclists in road traffic crashes. We used national police-reported data in Japan from 2016 to 2019 on vehicle versus pedestrian and vehicle versus cyclist injury crashes, focusing on six best-selling car models with optional AEB systems. We analyzed the association between AEB presence and injury severity, dichotomized as fatal/serious versus minor/no injury, using multivariable logistic regression, adjusting for potential confounders. Among 4131 pedestrians and 6659 cyclists involved in crashes, AEB was associated with a 20 % decrease in the odds of fatal or serious injuries among pedestrians (adjusted odds ratio: 0.80, 95 % confidence interval [CI]: 0.64–0.996). No significant association was observed for cyclists (adjusted odds ratio: 0.91, 95 % CI: 0.74–1.14). In conclusion, AEB systems may mitigate injury severity even when collisions cannot be avoided, at least for pedestrians in real-world conditions. Future studies should evaluate the effectiveness of newer AEB systems that detect cyclists and explore variations in effectiveness according to driver characteristics.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"218 ","pages":"Article 108091"},"PeriodicalIF":5.7,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928544","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 simulation study on traffic conflict risk under shockwave propagation at signalized intersections","authors":"Junqing Wang ,&nbsp;Hong Yang ,&nbsp;Yuan Zhu ,&nbsp;Kun Xie ,&nbsp;Zizheng Yan ,&nbsp;Qingwen Pu","doi":"10.1016/j.aap.2025.108081","DOIUrl":"10.1016/j.aap.2025.108081","url":null,"abstract":"<div><div>Traffic congestion and safety at signalized intersections are critical concerns in urban mobility management. The interaction between shockwaves caused by stop-and-go vehicles and the resultant conflict risk remains inadequately understood, necessitating detailed investigation. This study aims to explore the relationship between traffic conflict risk and shockwave propagation at signalized intersections through simulation, focusing on the dynamic conditions as vehicles queue and dissipate. The vehicle trajectory data extracted from the video captured by unmanned aerial vehicles (UAVs) is utilized in this study. The Simulation of Urban MObility (SUMO) software was selected as the simulation platform for building the simulation model. To ensure accuracy, the trajectories are refined with data smoothing and sampling, providing a reliable benchmark input for the simulation model development. Moreover, surrogate safety measures (SSMs) such as modified time to collision (MTTC) and deceleration rate to avoid a crash (DRAC), along with shockwave analysis (SA) were used to investigate the impact of driving risk when shockwave propagates in the queue. Then, the relationship between shockwaves and driving risk was explored under the calibrated model in a signalized intersection scenario. The study results show that conflicts occurred during the process of vehicles approaching until they stop and join the queue. Subsequently, the risk propagated at the tail of the growing queue. Additionally, the space–time diagram reveals that the risk propagation may be initiated before or along with the shockwave’s propagation. The findings provide insights for developing control strategies at signalized intersections through the uncovered correlation between the conflict risk and shockwave, contributing to the comprehensive understanding of traffic flow and safety at intersections.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"218 ","pages":"Article 108081"},"PeriodicalIF":5.7,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928545","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":"Generating risky and realistic scenarios for autonomous vehicle tests involving powered two-wheelers: A novel reinforcement learning framework","authors":"Zhiyuan Wei ,&nbsp;Jiang Bian ,&nbsp;Helai Huang ,&nbsp;Rui Zhou ,&nbsp;Hanchu Zhou","doi":"10.1016/j.aap.2025.108038","DOIUrl":"10.1016/j.aap.2025.108038","url":null,"abstract":"<div><div>Emerging technologies have the potential to revolutionize transportation, with Autonomous Vehicles (AVs) enhancing traffic safety, improving efficiency, and reducing emissions by optimizing driving patterns and minimizing idling time. However, despite their great potential, the actual utility and functionality of AVs have yet to be fully realized. Testing remains a critical method for advancing AVs adoption, and given that Powered Two-Wheelers (PTWs) is a major contributor to crashes, this paper proposes a novel scenario generation method for PTWs interactions with AVs. First, we extracted 314 car-to-PTWs crashes from the China In-depth Mobility Safety Study-Traffic Accident (CIMSS-TA) database as the initial state of the test scenarios. Subsequently, Reinforcement Learning (RL) was employed to control PTWs, using a reward function guided by a potential energy function that mirrors human driving characteristics to enhance the risk and realism of the generated scenarios. Finally, the effectiveness and scientific validity of the generated scenarios are verified by comparing and analyzing the risk, realism, and crash severity through multiple indicators. The results demonstrate that our proposed method increases riskiness while maintaining a high level of realism. It is hoped that this process will be applied in the future to not only test AV functions but also encourage AVs to be more mindful of crash severity.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"218 ","pages":"Article 108038"},"PeriodicalIF":5.7,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928543","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":"Ensuring SOTIF: Enhanced object detection techniques for autonomous driving","authors":"Sifen Wang ,&nbsp;Zhangyu Wang ,&nbsp;Sheng Hong ,&nbsp;Pengcheng Wang ,&nbsp;Shaowei Zhang","doi":"10.1016/j.aap.2025.108094","DOIUrl":"10.1016/j.aap.2025.108094","url":null,"abstract":"<div><div>Neural networks’ insufficient interpretability can lead to unguaranteed Safety of the Intended Functionality (SOTIF) issues when perceptual results are not always met in autonomous driving applications. To address the safety shortcomings in the current object detection process, this study proposes an object detection algorithm to enhance the accuracy of the perception system’s detection. We utilize the classical one-stage object detection algorithm YOLO v5 as the baseline in this study and evaluate our proposed model. A prediction extension box is added to the classical YOLO v5 model, which considers the coverage range and redundancy of real targets, guaranteeing the safety of image perception. The proposed object detection algorithm has been shown to increase the coverage range of detected targets, which significantly enhances perception safety in the autonomous driving process.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"218 ","pages":"Article 108094"},"PeriodicalIF":5.7,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928706","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":"Driving simulator analysis of the first time driving on a diverging diamond interchange","authors":"Didier M. Valdés,&nbsp;Alberto Figueroa-Medina,&nbsp;Carol A. Perelló","doi":"10.1016/j.aap.2025.108084","DOIUrl":"10.1016/j.aap.2025.108084","url":null,"abstract":"<div><div>The Diverging Diamond Interchange (DDI) is an innovative design alternative that enhances safety and operations, but its unconventional crossover maneuvers might confuse first-time drivers. The first DDI in Puerto Rico opened in 2023 at the interchange of highways PR-30 and PR-189 to improve the level of service of a conventional diamond interchange. Due to the lack of experience with a DDI in Puerto Rico, a driving simulation experiment was conducted in three phases to analyze future user behavior and performance. The simulation was conducted with 96 subjects who completed eight driving scenarios representing different maneuvers at the DDI and provided feedback about the effectiveness of the traffic control devices (TCDs) in assisting the driving task. Over 2,600 individuals also participated in training sessions with the simulator to experience the DDI. Speed profiles and vehicle trajectories were analyzed to reveal first-time drivers’ challenges at the DDI, such as confusion with the crossover maneuvers, speeding, wrong route selection, and incorrect maneuvers. The results from the simulation and the survey responses assisted in identifying recommendations for modifications to TCDs and the DDI characteristics. Subsequent simulation phases served to evaluate the impacts of the implemented changes, resulting in a 47% reduction in the number of critical driver errors and a 26% reduction in total driver errors at the DDI. This study demonstrates the significant role of a driving simulator during the design process of innovative facilities like a DDI, aiding in assessing proposed design features and identifying effective improvements to TCDs.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"218 ","pages":"Article 108084"},"PeriodicalIF":5.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143916711","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}