<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Research in Progress (RIP)</title>
    <link>https://rip.trb.org/</link>
    <atom:link href="https://rip.trb.org/Record/RSS?s=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" rel="self" type="application/rss+xml" />
    <description></description>
    <language>en-us</language>
    <copyright>Copyright © 2026. National Academy of Sciences. All rights reserved.</copyright>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <managingEditor>tris-trb@nas.edu (Bill McLeod)</managingEditor>
    <webMaster>tris-trb@nas.edu (Bill McLeod)</webMaster>
    <image>
      <title>Research in Progress (RIP)</title>
      <url>https://rip.trb.org/Images/PageHeader-wTitle-RIP.jpg</url>
      <link>https://rip.trb.org/</link>
    </image>
    <item>
      <title>Large Language Model-Driven Crash Risk Analysis System for Rural and Tribal Roadways</title>
      <link>https://rip.trb.org/View/2731923</link>
      <description><![CDATA[Rural and tribal roadways in the United States experience disproportionately high crash incidents due to a combination of infrastructure challenges, limited resources, and incomplete crash reporting. Traditional statistical, machine learning (ML), and deep learning (DL) models have struggled to address these issues because they rely heavily on structured data, perform poorly with incomplete or imbalanced datasets, and often fail to leverage the rich information contained in crash narratives. Large language models (LLMs) offer an alternative by reframing crash risk analysis as a text reasoning problem, enabling the extraction of contextual insights from narratives, the imputation of missing or inconsistent fields, and the integration of structured and unstructured data into unified predictive frameworks. This proposal aims to develop an LLM-based crash risk analysis system utilizing North Carolina’s statewide police-reported crash data as a foundation, with the goal of enhancing the accuracy, interpretability, and robustness of rural crash risk assessment. The project will proceed through four main tasks: crash data enhancement and model adaptation, predictive model development, model validation, and the design of an implementation plan for real-time crash risk warnings in connected vehicle (CV) environments. ]]></description>
      <pubDate>Fri, 17 Jul 2026 16:08:51 GMT</pubDate>
      <guid>https://rip.trb.org/View/2731923</guid>
    </item>
    <item>
      <title>Leveraging Telematics Data for Enhanced Traffic Safety: Unveiling Crash-Prone Hotspots and Mitigating Incidents - Phase 2</title>
      <link>https://rip.trb.org/View/2727388</link>
      <description><![CDATA[Cutting-edge connected-vehicle (CV) telematics now stream billions of instantaneous speed, heading, and hard- maneuver records across Texas roadways—an untapped resource for proactive safety management. Phase I of Project 0-7200 capitalized on this opportunity by (1) surveying and vetting statewide CV data sources, (2) building rigorous preprocessing pipelines and a strategic data-archiving scheme with the Receiving Agency, (3) defining data-driven “near-crash” events, and (4) creating proof-of-concept analytics that locate and rank high-risk corridors. Two single-user prototype web tools—TTI’s near-crash explorer and UTA’s multi-criteria hotspot-ranking dashboard—proved the approach valid, with results aligning closely with the Crash Records Information System (CRIS). Phase II will transform those prototypes into a secure, cloud-based, multi-user platform capable of statewide, high-volume ingestion and real-time analytics—advancing the solution to TRL 8 (actual system completed and “TxDOT-pilot ready”). The research teams will, optimize the data-processing engine for scalability, integrate interactive visualizations with enterprise authentication, automate continuous data refresh and long-term archiving, and embed crash- prediction models that fuse telematics with CRIS and roadway inventory. The research teams will develop a decision-support tool that lets TxDOT’s districts quickly pinpoint emerging crash-prone hotspots and deploy targeted countermeasures.]]></description>
      <pubDate>Fri, 10 Jul 2026 17:07:46 GMT</pubDate>
      <guid>https://rip.trb.org/View/2727388</guid>
    </item>
    <item>
      <title>Systemic Safety Analysis and Assessment of Bicycle and Pedestrian Crash Risk: Developing Risk Factors using the Multimodal Inventory Project Data</title>
      <link>https://rip.trb.org/View/2725665</link>
      <description><![CDATA[Inconsistent and incomplete data on multimodal infrastructure and operations limits 
Oregon Department of Transportation's (ODOT’s) ability to develop data-driven risk factors. Accurate and up-to-date bicycle and pedestrian risk factors are necessary inputs for ODOT programs aiming to proactively address active transportation safety, as they can help identify locations with geometric and operational characteristics that lead to increased crash risk for active transportation users. The Multimodal Inventory Project offers new data and a unique opportunity to develop more rigorous, data-driven bicycle and pedestrian risk factors. Leveraging these new data and methodologies, in addition to crash data and exposure data, will enable analysis that can identify roadway and operational characteristics most strongly associated with bicycle and pedestrian crash risk.
OBJECTIVES: This research will provide ODOT with up-to-date, high-quality bicycle and pedestrian risk factors to be used for proactive safety analysis. The anticipated outcome of this research is to develop these new bicycle and pedestrian risk factors by leveraging new multimodal data from the Multimodal Inventory Project and by applying more rigorous risk factor methodologies. The latter will be accomplished by developing a Risk Factor Tool that relies on data inputs and analysis results to provide site-specific bicycle and pedestrian risk assessments. Objectives of this research include: (1) A comprehensive review of studies that develop bicycle and pedestrian risk factors and/or apply them, methods used to derive bicycle and pedestrian risk factors, and current policies and practices implemented through Active Transportation Safety Plans and Vulnerable Road User Safety Assessments; (2) A data collection and fusion process that combines existing and new Multimodal Inventory Project data; and (3) Development of bicycle and pedestrian risk factors using an integrated approach that leverages descriptive statistics and safety modeling techniques, resulting in a Risk Factor Tool to conduct site-specific risk assessments.
This research will provide ODOT with up-to-date data and risk factors to improve bicycle and pedestrian safety, addressing Transportation Plan Safety Objectives, Social Equity Objectives, and Mobility Objectives.]]></description>
      <pubDate>Wed, 08 Jul 2026 16:52:17 GMT</pubDate>
      <guid>https://rip.trb.org/View/2725665</guid>
    </item>
    <item>
      <title>Safety Performance of Safe System Treatments for Corridors and Intersections that May Impact Capacity</title>
      <link>https://rip.trb.org/View/2712178</link>
      <description><![CDATA[Transportation agencies are increasingly adopting the Safe System Approach (SSA), which emphasizes a holistic approach to eliminating all fatal and serious traffic injuries on road segments and at intersections. Historically, efforts to reduce congestion often led to the addition of through lanes, implementation of short auxiliary lanes at intersections to facilitate right turns and through movements, and other treatments. However, agencies are now exploring lane reductions—commonly referred to as right-of-way reallocation, road diets, or reconfigurations—to improve safety. In some cases, roads previously widened to accommodate peak-hour traffic are being reevaluated through the lens of the SSA.

Implementing these changes requires a comprehensive understanding of the associated safety impacts and the ability to predict crash outcomes resulting from modifications to roadway capacity. Safety outcomes associated with capacity modifications carry substantial weight in routine planning and operational decisions. Current evidence, however, is limited, and context-specific effects, especially for vulnerable road users, are not well quantified. Additional research is therefore needed to quantify how short auxiliary lanes and cross-section changes affect exposure, likelihood, and severity.

The objectives of this research are to (1) quantify the safety impacts of SSA treatments that may affect roadway capacity and (2) develop analysis methodologies, such as crash modification factors (CMFs) and crash prediction models, to evaluate how these treatments affect crash exposure, likelihood, and severity across all road users and crash types, including pedestrian and bicyclist crashes. The research results can enable planners, designers, traffic engineers, and other decision-makers to make evidence-based choices that balance safety with operational and capacity needs.]]></description>
      <pubDate>Tue, 09 Jun 2026 15:00:53 GMT</pubDate>
      <guid>https://rip.trb.org/View/2712178</guid>
    </item>
    <item>
      <title>Highway Safety Manual Crash Prediction Models of Arterial Weaving Segments</title>
      <link>https://rip.trb.org/View/2712176</link>
      <description><![CDATA[More than half of U.S. roadway deaths and nearly two-thirds of pedestrian fatalities occur on non-freeway arterials. Arterial sections with weaving maneuvers are complex for all road users to navigate and traverse without incidents or collisions.

The Code of Federal Regulations requires determination of whether the location, configuration, geometric design, and signing related to a proposed change in access may be reasonably expected to serve the anticipated traffic of the Interstate system in a manner that is conducive to safety, durability, and economy of maintenance. For many existing and proposed alternative designs, the safety of the weave is not quantified between ramps. Examples include cloverleaf designs with adjacent intersections and crossing weaves from ramps to downstream left turns. A better understanding of crash outcomes is needed for a variety of rural and urban speeds and contexts.

As part of NCHRP Project 15-66, “Operational Performance and Safety Effects of Arterial Weaving Sections,” crash data and conflict data obtained in the field and a driving simulator were analyzed to assess the safety performance of several types of arterial weaving sections. The results of the safety analysis did not provide a definitive relationship between the length and vehicle maneuvers of arterial weaving sections and crashes or conflicts; however, sufficient information was found to suggest additional research in this area would yield promising results toward developing a methodology for predicting the safety performance of arterial weaving sections suitable for inclusion in the AASHTO Highway Safety Manual (HSM).

The objective of this research is to develop a crash prediction methodology, safety performance functions (SPFs), to assess different types of arterial weaving sections, suitable for inclusion in the HSM.]]></description>
      <pubDate>Tue, 09 Jun 2026 14:53:30 GMT</pubDate>
      <guid>https://rip.trb.org/View/2712176</guid>
    </item>
    <item>
      <title>Unraveling the Causes of Fatal Crashes in the U.S.: A Machine Learning Approach to Safer Roads</title>
      <link>https://rip.trb.org/View/2694440</link>
      <description><![CDATA[This project investigates the underlying causes of fatal traffic crashes in the United States using advanced machine learning (ML) techniques to enhance road safety. Each year, traffic crashes claim over 42,000 lives nationwide, inflicting significant social, economic, and health burdens. Traditional analytical methods have struggled to capture the complex, nonlinear interactions among factors such as driver behavior, vehicle characteristics, roadway design, and environmental conditions. To address this limitation, this project employs data-driven ML models to identify key determinants of fatal crashes and generate actionable insights for evidence-based safety interventions.

The research activities will proceed in four phases. First, comprehensive crash data will be collected from the National Highway Traffic Safety Administration (NHTSA) and integrated across multiple datasets to ensure completeness and consistency. Next, statistical analysis and visualization will be used to identify spatial and temporal trends in crash patterns, revealing geographic disparities and risk concentrations. In the modeling phase, several machine learning algorithms—Balanced Bagging, Balanced Random Forest, and RUSBoost—will be developed and compared against traditional logistic regression models to enhance prediction accuracy in imbalanced datasets. Finally, the top-performing model will be used to assess variable importance and generate policy-relevant recommendations.

OBJECTIVE: The objective of this project is to develop predictive models that accurately identify risk factors associated with fatal crashes and support data-informed decision-making by transportation agencies. The findings will guide targeted interventions such as improved traffic regulations, safer roadway designs, and enhanced vehicle technologies. This research will provide a scalable analytical framework for improving transportation safety and sustainability nationwide.
]]></description>
      <pubDate>Tue, 21 Apr 2026 13:45:15 GMT</pubDate>
      <guid>https://rip.trb.org/View/2694440</guid>
    </item>
    <item>
      <title>Enhancing Heavy Vehicle Crash Prevention in North Dakota through Machine Learning and Weather Data Integration</title>
      <link>https://rip.trb.org/View/2683255</link>
      <description><![CDATA[Heavy vehicle crashes continue to be a persistent safety concern across the Midwest, with several states reporting disproportionately high rates of incidents involving large trucks. According to the National Safety Council, in 2023, North Dakota recorded 18% of its fatal crashes involving large trucks, placing it among the highest in the nation. Neighboring states, such as Nebraska (16%) and Iowa, also face elevated risks. Illinois reported 7,509 truck accidents in 2022, ranking among the top five states nationwide. In North Dakota, the risks are especially pronounced during the winter months. In 2023, 64% of heavy vehicle crashes occurred between October and March, with 81% of these crashes taking place in rural areas. These figures highlight how weather conditions and geography amplify the risk associated with large-truck travel in the region. Further, crashes in rural areas in challenging weather conditions poses immense issues for first responders and their ability to provide timely medical care to crash victims.   

Traditional safety strategies have struggled to account for the dynamic, real-time factors that contribute to crash risk. Static approaches often fall short when adverse weather, road conditions, and traffic volume interact in unpredictable ways. This gap highlights the urgent need for predictive, data-driven solutions.  

This proposal aims to investigate the application of machine learning (ML) models, combined with weather and crash data, to predict high-risk scenarios before accidents occur, to support planning for safety and emergency response needs. By leveraging predictive analytics, North Dakota could enhance resource allocation, deploy preventive interventions, and reduce the frequency and severity of heavy vehicle crashes. The high incidence of winter crashes and the limitations of conventional methods make North Dakota an ideal proving ground for an innovative, ML-driven approach to roadway safety.  

The study will utilize historical crash records for heavy vehicles in North Dakota, including crash type, severity, date, and time, combined with corresponding weather data such as temperature, precipitation, snowfall, and visibility. Feature engineering will create representations of temporal and weather conditions relevant to crash severity. Machine learning models, including Random Forest, XGBoost, and Neural Networks, will be trained to predict crash severity. To ensure interpretability, SHAP (SHapley Additive exPlanations) will be applied to quantify the contribution of each feature to individual predictions and overall model behavior. This analysis will reveal which weather or temporal factors most strongly influence severe crashes, both globally across the dataset and locally for specific incidents. High-risk periods and conditions identified by the model, along with explanations provided via SHAP, will be visualized both temporally and geographically, offering actionable insights to support targeted preventive measures and inform DOT decision-making.  ]]></description>
      <pubDate>Tue, 24 Mar 2026 14:09:40 GMT</pubDate>
      <guid>https://rip.trb.org/View/2683255</guid>
    </item>
    <item>
      <title>Developing a Data Fusion Tool for Improved Traffic Crash Exposure
Analysis and Modeling</title>
      <link>https://rip.trb.org/View/2663603</link>
      <description><![CDATA[Accurate measurement of exposure is critical for understanding and preventing traffic crashes, as crash frequency is directly related to how much road users are exposed to risk. However, current exposure estimates rely on data sources with complementary but individually insufficient characteristics. Traditional traffic counts and Annual Average Daily Traffic (AADT) offer high accuracy but limited spatial and temporal coverage, while emerging Location-Based Services (LBS) data provide high-resolution mobility patterns but are often biased and less reliable. This fundamental mismatch between accuracy and coverage prevents agencies from developing the complete and reliable exposure estimates needed for effective safety analysis and planning.
This project develops a data fusion tool that integrates traffic counts and AADT, LBS data, and socio-demographically representative survey data from the National Household Travel Survey (NHTS) into a unified measure of exposure. Unlike previous efforts that focused on a single travel mode or low temporal resolution, the proposed framework generates exposure estimates for motor vehicles, pedestrians, bicyclists, and scooters at fine spatial scales (intersection and mid-block) and temporal scales (daily and monthly). The tool is evaluated in Washington, D.C., using three alternative fusion paradigms: Bayesian fusion through hierarchical or state-space modeling, Dempster–Shafer theory for explicit uncertainty representation and accommodation of LBS coverage gaps, and model-based fusion employing structured error modeling with NHTS socio-demographics to correct LBS data bias.
The fusion methods are compared through crash prediction models estimated with fused exposure measures against models using individual data sources, evaluated via pseudo-R², AIC, BIC, and out-of-sample prediction error, with a target improvement of at least 10% in predictive performance. Fused exposure patterns are further validated against Washington, D.C.’s High Injury Network and independent ground-truth count data where available. The final tool is delivered as an open-source Python package with documentation and secure coding practices. Agency outreach, including engagement with D.C. stakeholders managing the High Injury Network, informs tool refinement and supports preparation for future pilot deployment. This research supports USDOT’s Safety priority by generating more accurate and complete multimodal exposure measures that enable better identification of high-risk locations, improved crash prediction, and targeted safety interventions
]]></description>
      <pubDate>Tue, 03 Feb 2026 15:31:17 GMT</pubDate>
      <guid>https://rip.trb.org/View/2663603</guid>
    </item>
    <item>
      <title>Role of emerging transportation technologies and safety initiatives in mitigating crashes in coastal communities</title>
      <link>https://rip.trb.org/View/2661744</link>
      <description><![CDATA[Coastal communities face heightened crash risks due to hazards such as hurricanes, flooding, and roadway degradation. Traditional safety countermeasures often fail to address these compounded risks, especially where evacuation routes are limited. This project will investigate how emerging transportation technologies (e.g., connected vehicle systems, advanced driver assistance systems, smart corridors) and safety initiatives (e.g., hazard-responsive traffic management, roadway design measures) can mitigate crash risks in coastal regions. Using literature review, geospatial screening of coastal corridors, and expert validation, the team will develop a prototype decision-support tool linking crash scenarios common in coastal environments with candidate technologies and initiatives. The outcome will provide agencies with a concise, practical framework to assess and prioritize safety solutions that improve infrastructure durability and resilience under coastal hazards.]]></description>
      <pubDate>Thu, 29 Jan 2026 16:13:26 GMT</pubDate>
      <guid>https://rip.trb.org/View/2661744</guid>
    </item>
    <item>
      <title>Calibration and Implementation of Highway Safety Manual Bicyclist and Pedestrian Intersection Crash Prediction Models</title>
      <link>https://rip.trb.org/View/2635921</link>
      <description><![CDATA[The forthcoming 2nd Edition of the AASHTO Highway Safety Manual (HSM2) will introduce dedicated crash prediction models (CPMs) for pedestrian and bicyclist crashes at intersections, midblock crossings, and roadway segments.  The goal of this research is to calibrate the HSM2 pedestrian and bicyclist intersection CPMs using Virginia-specific data. The research outcomes will enhance the accuracy of nonmotorized crash predictions and support Virginia Department of Transportation's (VDOT’s) broader goals of data-driven planning, design decision-making, and funding prioritization for safety improvements. To achieve this goal, the research will (1) assemble a comprehensive dataset for selected representative intersections in Virginia, including crash history, exposure data, and roadway and roadside design features required by the HSM2 CPMs, (2) develop appropriate methods for estimating pedestrian and bicyclist exposure at intersections, considering available data sources, (3) develop a robust calibration methodology that accounts for the variability of contextual settings, exposure ranges, facility types and jurisdictions, etc., and (4) design a practical tool and accompanying guidance to help VDOT implement and maintain the calibrated pedestrian and bicyclist CPMs.]]></description>
      <pubDate>Thu, 04 Dec 2025 08:52:41 GMT</pubDate>
      <guid>https://rip.trb.org/View/2635921</guid>
    </item>
    <item>
      <title>Validation of HSM Crash Prediction Methods for Specific Intersection Types in Oregon</title>
      <link>https://rip.trb.org/View/2593954</link>
      <description><![CDATA[The Highway Safety Manual (HSM) is the national guidance of quantitative safety analysis used in highway transportation planning, alternatives development, highway design, operations, and maintenance. However, some crash prediction models and crash modification factors in the Highway Safety Manual were developed using data from other states, not Oregon. Therefore, it is necessary to validate these models and crash modification factors for the implementation in Oregon.
Recently the National Cooperative Highway Research Program (NCHRP) project 17-68 “Intersection Crash Prediction Methods for the Highway Safety Manual” has developed crash prediction models of more intersection types for inclusion in the HSM. The types of intersections include all-way stop control, three-leg intersections with signal control on rural highways, intersections on high-speed urban and suburban arterials, five-leg intersections, etc. Currently, there is no guideline for how to use these new crash prediction models particularly in Oregon. It is necessary to validate these models and crash modification factors in Oregon to guide the statewide implementation.
This research proposes to focus on intersections on urban and suburban arterials, which are common intersection types.]]></description>
      <pubDate>Thu, 28 Aug 2025 12:53:55 GMT</pubDate>
      <guid>https://rip.trb.org/View/2593954</guid>
    </item>
    <item>
      <title>Non-Motorist Safety at Highway-Rail Grade Crossings: Developing a Crash Prediction Model with Integrated Non-Motorist Exposure – Year 3</title>
      <link>https://rip.trb.org/View/2573721</link>
      <description><![CDATA[The proposed research objective is to address the safety of non-motorists at highway-rail grade crossings (HRGCs). In Phase III (Year 3), the research team will focus on a survey of pedestrians and bicyclists in Federal Region VII (NE, IA, KS, and MO) to investigate their characteristics, perceptions of safety at crossings, understanding and comprehension of traffic signs/signals at crossings, and their self-reported unsafe movements at HRGCs. The focus on this region ensures a representation of the Midwest, where the extensive rail network creates safety issues for non-motorists. Incidents involving non-motorist users at HRGCs are often underreported or overlooked, yet statistics reveal that they significantly contribute to overall fatalities and injuries at these locations. Pedestrians and bicyclists at HRGCs are particularly vulnerable due to the lack of adequate protective barriers or warning devices. In 2022, the Federal Railroad Administration (FRA) recorded 2,202 crashes at HRGCs, leading to 269 fatalities and 827 injuries nationwide. Furthermore, during the same year, there were 1,157 reported incidents of pedestrian rail trespassing, resulting in 606 fatalities and 551 injuries. These numbers emphasize the need for a comprehensive understanding of the risks associated with non-motorized users at HRGCs and identification of crossings where non-motorized users may be susceptible to crashes. This research will contribute to a deeper understanding of safety hazards associated with HRGCs and lead to the development of autonomous mitigation technologies for rail crossings. ]]></description>
      <pubDate>Mon, 14 Jul 2025 19:22:06 GMT</pubDate>
      <guid>https://rip.trb.org/View/2573721</guid>
    </item>
    <item>
      <title>Artificial Intelligence (AI) Applications to Enhance Transportation Safety</title>
      <link>https://rip.trb.org/View/2563983</link>
      <description><![CDATA[This research effort aims to explore the applications of artificial intelligence (AI) in improving transportation safety from a regional standpoint. The specific objectives include: 1. Identify, explore, and document the existing and upcoming applications of AI in improving safety at both macro- and micro-levels. 2. Identify the opportunities and risks of AI applications in traffic safety. 3. Identify the existing traditional and non-traditional datasets that could be used to develop AI applications to enhance traffic safety. 4. Develop several diverse use cases to demonstrate the feasibility of AI applications in mitigating traffic crashes and improving safety]]></description>
      <pubDate>Mon, 16 Jun 2025 09:54:17 GMT</pubDate>
      <guid>https://rip.trb.org/View/2563983</guid>
    </item>
    <item>
      <title>Applying Crash Prediction Models Across Traffic Control and Facility Types



</title>
      <link>https://rip.trb.org/View/2558381</link>
      <description><![CDATA[The Highway Safety Manual (HSM) is used by transportation agencies for decisions on planning, design, and operational safety. The manual includes crash prediction models to estimate the expected safety performance of various functional classifications of roadway segments and intersections. However, crash prediction models for intersections in the HSM can sometimes produce unexpected and difficult-to-interpret results when comparing crash outcomes across different traffic control types. For example, signalization at intersections may not consistently yield the expected crash reductions, particularly for high-severity crashes.

While the HSM is under revision to enhance these models and provide broader guidance in their application, there is a need for clear direction on how to apply the models to conduct comparative safety evaluations across traffic control and facility types. Research is needed to establish and quantify differences in predictive crash outcomes derived from the HSM crash prediction models when comparing the safety performance of different traffic control types. The findings will support improving safety in project concepts proposed by transportation planners and designs by engineers.

OBJECTIVE: The objective of this research is to develop a framework and guide, including application recommendations and tools, to support the use of HSM crash prediction models when analyzing traffic control types for a given location or facility type.]]></description>
      <pubDate>Wed, 28 May 2025 14:12:45 GMT</pubDate>
      <guid>https://rip.trb.org/View/2558381</guid>
    </item>
    <item>
      <title>Understand Vehicle-Driver Complex Behaviors under Cyberattacks and Model the Consequences to the Urban Traffic System
</title>
      <link>https://rip.trb.org/View/2548666</link>
      <description><![CDATA[Vehicle-to-infrastructure communication improves traffic safety and efficiency, but increasing connectivity also raises cybersecurity
risks. Cyberattacks on intelligent transportation systems can manipulate data, leading to unsafe driving behaviors. This project
investigates how cyberattacks impact driver behavior and safety using a driving simulator experiment with 32 participants of
different ages, experiences, and genders. Participants drove through connected intersections under both benchmark and
cyberattack conditions. Safety was assessed using the Surrogate Safety Assessment Model (SSAM), focusing on Proportion of
Stopping Distance (PSD) and Time to Collision (TTC). Findings show that cyberattacks significantly threaten traffic safety,
influencing speed, deceleration, and collision risks. Higher speeds at the end of a signal countdown increase the likelihood of
pedestrian and right-angle collisions but reduce rear-end collision risk. Experienced drivers respond better to cyberattacks, with
lower pedestrian and right-angle collision hazards than inexperienced drivers. No major differences were observed between male
and female drivers under cyberattacks, though mixed effects of males and cyberattacks brings a higher rear-end collision risks
than female in benchmark conditions. Speed mediates these effects, as experienced drivers decelerate more quickly, reducing
frontal collision risks. This study highlights the dangers of cyberattacks in transportation and how human factors influence safety.
The findings can help improve traffic management, driver education, and predictive safety models to reduce risks in connected
vehicle environments.]]></description>
      <pubDate>Wed, 30 Apr 2025 16:04:19 GMT</pubDate>
      <guid>https://rip.trb.org/View/2548666</guid>
    </item>
  </channel>
</rss>