<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>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>Perform Assessment of TxDOT Safety Scoring Tools to Determine Effectiveness and Calibration</title>
      <link>https://rip.trb.org/View/2636039</link>
      <description><![CDATA[The research team will conduct a comprehensive assessment of the Texas Department of Transportation's (TxDOT) safety scoring tools by analyzing evaluation performance, identifying potential biases or limitations, and recommending improvements and adjustments to enhance their effectiveness. The research team will develop a guidance documentation that recommends refinement to existing tool methodologies and strengthen its ability to reduce roadway fatalities and serious injuries through more informed decision-making and targeted safety interventions.]]></description>
      <pubDate>Fri, 05 Dec 2025 14:14:27 GMT</pubDate>
      <guid>https://rip.trb.org/View/2636039</guid>
    </item>
    <item>
      <title>Evaluate Emerging Transportation Technologies and Advancements in Engineering and Roadway Safety Efforts Impact on Crashes</title>
      <link>https://rip.trb.org/View/2606397</link>
      <description><![CDATA[Emerging technologies and advancements in transportation and engineering are becoming increasingly prevalent across the transportation spectrum. From advanced driving systems to the development of innovative corridors, and the use of 3D modeling for engineering, new technologies and tools are being implemented by the public and private sector with the goal of reducing crashes and saving lives. No analysis has been conducted to determine their safety effectiveness and what practical impact they may have in the future. The research team will develop a safety and policy framework to explore the correlations between the emerging technologies and engineering tools and purported reductions in fatalities and serious injuries. The research team will demonstrate how public agencies, like the Texas Department of Transportation (TxDOT), can objectively assess the extent to which emerging technologies and tools will achieve desired safety outcomes.]]></description>
      <pubDate>Thu, 02 Oct 2025 09:41:56 GMT</pubDate>
      <guid>https://rip.trb.org/View/2606397</guid>
    </item>
    <item>
      <title>Development of Crash Modification Factors/Functions for Bus Stops</title>
      <link>https://rip.trb.org/View/2601434</link>
      <description><![CDATA[​Public transit, including bus services, plays a crucial role in the United States by enhancing economic productivity and community livability. Deciding where to place a bus stop involves several key considerations to ensure safety, accessibility, and efficiency. Planners typically evaluate factors such as passenger safety, proximity to major trip generators, and accessibility for people with disabilities. They also consider traffic patterns, the availability of adequate curb space, and the potential impact on nearby
properties.

Historically, bus stops were easy to install and relocate due to minimal infrastructure requirements. However, as bus stops and systems (e.g., bus rapid transit or BRT) become more complex incorporating elements like shelters, seating, and Americans with Disabilities Act (ADA) compliant features they have become more expensive and difficult to locate. This complexity increases the importance of understanding the safety, operational, accessibility, and other impacts of bus stop locations on a roadway network before installation. Despite this, there is relatively little information on how bus stops affect roadway safety performance. There is no established equation or set of factors to determine whether perceptions of safety impacts are supported by numerical data, nor how these factors interact. Additional elements contributing to increased crash rates at bus stops may often be overlooked during placement decisions.

In light of the above, the overall objective of this project is to develop a suite of Crash Modification Factors (CMFs) that quantify the impact of adding a bus stop on crash frequency in North Carolina. These CMFs will be derived from crash prediction models (CPMs) designed to predict the safety performance (i.e., annual crash frequency) at a given location as a function of roadway-specific and bus stop-specific features. The models will specifically focus on all crashes (and all fatal + injury crashes) that occur at
these locations, not only crashes involving a bus. The CPMs will be  developed using cross-sectional models in which the safety performance of sites with bus stops will be compared to sites without bus stops. The research team proposes to use the propensity scores-potential outcomes (PSPO) approach for this cross-sectional analysis. The PSPO approach mimics a randomized experiment when the placement of the treatment being studied (in this case, bus stops) is not random. This helps to balance between features in the treatment and non-treatment groups and results in more reliable estimates of the safety impact of the treatment. The team plans to include as many bus stop locations as possible, given the anticipated low average crash frequencies at these sites. It is anticipated that the CPMs will yield CMFs in the form of Crash Modification Functions that provide an estimate of the safety impacts of bus stop locations as a function of several design variables. Candidate variables that the research team intends to explore include: bus stop location relative to the intersection (i.e., far-side vs. near-side), distance from nearest major intersection, number of travel lanes, traffic volume, speed limit, functional classification,
presence of on-street parking, and presence of nearby pedestrian/bicycle facilities.

Anticipated research products include a final report documenting the process of developing the bus stop CMFs, the CMFs themselves, and accompanying interpretations. Additionally, the research will produce an implementation plan for the CMFs, describing their applicability, use, and potential limitations. The Page 3 of 31 research team will provide the North Carolina Department of Transportation (NCDOT) with a final implementation plan detailing how to use and apply the research results. This plan will also address the level of confidence in the findings and identify data gaps and quality issues encountered during data collection. The research team will collaborate with NCDOT to identify necessary training resources, policies, and guidelines that need updating to incorporate the research results. Specific recommendations for updating these documents will be documented.​]]></description>
      <pubDate>Thu, 18 Sep 2025 01:01:24 GMT</pubDate>
      <guid>https://rip.trb.org/View/2601434</guid>
    </item>
    <item>
      <title>Implementation Requirements for Work Zone Intrusion Technologies to Reduce Fatalities</title>
      <link>https://rip.trb.org/View/2596487</link>
      <description><![CDATA[The latest information published by the Oregon Department of Transportation (ODOT) on fatal crashes shows alarming trends. In 2022, there were 605 fatalities, in 2021, 599, and in 2020, 460. These values represent three consecutive years of ODOT’s highest recorded values, as reported over a 10 year period (Oregon DOT Crash Analysis Unit, 2020). Across the United States, roadway workers on foot being struck by vehicles (both construction equipment and travellng public) was the most prevalent cause of highway worker fatalities (2017-2019) and accounted for 53% of worker fatalities in 2020 (American Road and Transportation Builders Association (ARTBA), 2022). Preventing intrusions, and protecting workers, is a high priority for both ODOT and contractors. ODOT has an immediate need to address this safety aspect, as identified by near misses in the month of February 2023 from Administrator Lynde’s recent all-ODOT email (Lynde, 2023). This research will focus on work zone intrusion technologies, which may also have application in other areas of roadway safety.]]></description>
      <pubDate>Mon, 08 Sep 2025 11:58:54 GMT</pubDate>
      <guid>https://rip.trb.org/View/2596487</guid>
    </item>
    <item>
      <title>Covid and Traffic Crashes/Impact on Safety Targets</title>
      <link>https://rip.trb.org/View/2562323</link>
      <description><![CDATA[The public health emergency due to COVID-19 in March of 2020 significantly changed driving patterns and behaviors.
Research is needed to assess how the pandemic has affected mobility patterns and impacted the number of road
fatalities. Travel was decreased for a period of time but speeds and fatalities increased. Determining the potential
explanations for these differences and understanding the characteristics of the drivers, the engagement in high risk
behaviors, and the continued impacts (current fatality estimates are still increasing) needed to be researched to better
understand these safety impacts and how Michigan Department of Transportation (MDOT) and other safety stakeholders may be able to address these underlying
issues with proactive countermeasures, policies, programs and future target setting.]]></description>
      <pubDate>Mon, 09 Jun 2025 07:59:41 GMT</pubDate>
      <guid>https://rip.trb.org/View/2562323</guid>
    </item>
    <item>
      <title>Examination of Light-Based Directed Vehicle to Everything Communications Systems for Bridge Strike Detection</title>
      <link>https://rip.trb.org/View/2562268</link>
      <description><![CDATA[With the emergence of advanced driver assistance systems (ADAS) in most modern passenger vehicles, the need for reliable
transmission of data from vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) has become apparent. However, many
commercial vehicles such as buses and semi-trucks are technologically behind when it comes to sensing potential safety hazards,
while having the potential to cause catastrophic damage due to their increased size and weight. One of the most common safety
incidents involving large commercial vehicles are bridge strikes and tunnel strikes, where the driver of a tall-load vehicle attempts to
pass under a bridge or tunnel and the top of the load collides with the bottom of the overpass. According to the National Highway
Safety Administration, there are approximately 15,000 bridge strikes in the USA annually, with potentially more going unreported.
These bridge strikes cause a serious threat to the safety of all road users, as well as a substantial financial cost in the form of
infrastructure repair, road closures, and traffic disruption.]]></description>
      <pubDate>Fri, 06 Jun 2025 14:57:35 GMT</pubDate>
      <guid>https://rip.trb.org/View/2562268</guid>
    </item>
    <item>
      <title>Updated Calibration Factors for Highway Safety Manual Crash Prediction Models (2020-2023)</title>
      <link>https://rip.trb.org/View/2536232</link>
      <description><![CDATA[Traffic safety is the primary objective for transportation professionals. However, according to the traffic crash data released by the U.S. Department of Transportation’s National Highway Traffic Safety Administration, 39,007 lives were taken in traffic crashes in 2020, which represents a 6.8% increase in fatal crashes and a 21% increase in the fatality rate per 100 million vehicle miles traveled, respectively, over the previous year. The Highway Safety Manual (HSM), published by the American Association of State Highway and Transportation Officials (AASHTO) in 2010, provides a set of quantitative tools that help transportation practitioners make more informed decisions regarding highway safety performance. One of the most critical tools are Safety Performance Functions (SPFs), models that relate expected safety performance of individual facilities (measured in terms of expected annual crash frequency) with its specific features, such as traffic volume or geometric characteristics. 

The design-level SPFs included in the HSM were developed using data from a limited number of states. Since a variety of features, including traffic flow characteristics, crash reporting system, and climate vary significantly across different states, using the HSM SPFs or other national-level SPFs directly for any state will likely lead to biased predictions. For this reason, jurisdictions need to calibrate these SPFs before they can be applied for meaningful predictive analysis. This calibration is typically done using a calibration factor. The purpose of this study is to develop updated calibration factors and accompanying crash proportion tables for the SPFs in the HSM using the most recent data and develop calibration factors for newer SPFs that are now available via other national-level projects. 

The segment facility types that calibration factors will be generated for include the following:
two-lane rural roads (Chapter 10 of HSM); rural multilane roads (Chapter 11 of HSM);  urban and suburban arterials (2-5 lanes from Chapter 12 of HSM); urban and suburban arterials (6-8 lanes and one-way from the results of NCHRP (5) 17-58); and urban and rural freeways, and ramps (Chapters 18 and 19 of HSM). The intersection types that calibration factors will be generated for include the following: intersections on rural two-lane highways; intersections on rural multilane highways; intersections on urban and suburban arterials and one-way streets; ramp terminals (Chapter 19 of HSM); and roundabouts (results of NCHRP 17-70).

SPF calibration factors will be generated by following the calibration procedure in the HSM using 2020 through 2023 data. The research team will identify study sites for inclusion in this effort by beginning with sites used in previous North Carolina SPF calibration efforts and then supplementing those locations to build a robust database meeting sample size requirements suggested by the HSM. Then, the research team will collect roadway geometric and operational data and gather and assemble crash data for each site. Finally, the research team will use the SPFs to predict crash frequency for each site and calculate statewide calibration factors and crash proportion tables, as well as regional calibrations for the Mountain, Piedmont, and Coastal regions. The outcomes of this project are anticipated to: (1) provide North Carolina Department of Transportation (NCDOT) the ability to generate North Carolina-specific predictions for all facility types; (2) incorporate economic analysis into decision-making by determining expected changes in safety performance among alternatives; (3) increased reliability in decision-making by using state-of-the-practice methods for evaluating expected safety performance; and (4) develop a broader dataset for North Carolina to serve as a base for future applications in calibration efforts.]]></description>
      <pubDate>Fri, 11 Apr 2025 01:36:13 GMT</pubDate>
      <guid>https://rip.trb.org/View/2536232</guid>
    </item>
    <item>
      <title>Analyzing Railroad Grade Crossing Crashes in Kentucky and Creating New KYTC Railroad Safety Initiatives</title>
      <link>https://rip.trb.org/View/2417079</link>
      <description><![CDATA[The Kentucky Transportation Cabinet (KYTC) is concerned with the safety of highway-railroad grade crossings because vehicle crashes at these locations are typically fatal. Between 2015 and 2019, 14 railroad-related crashes occurred in Kentucky — 13 were fatal. KYTC is moving forward with its Vision Zero initiative, and it is essential to assess safety at highway-railroad grade crossings and identify appropriate countermeasures (e.g., install/update warning signs, signals, and bells) to reduce injury and fatal crashes. KYTC can use research findings to implement countermeasures, design improvements, or safety programs that will reduce crashes at highway-railroad grade crossings.]]></description>
      <pubDate>Mon, 12 Aug 2024 13:26:36 GMT</pubDate>
      <guid>https://rip.trb.org/View/2417079</guid>
    </item>
    <item>
      <title>Develop Methods to Reduce Crashes and Increase Driver Compliance in Work Zones</title>
      <link>https://rip.trb.org/View/2377868</link>
      <description><![CDATA[Each summer the South Dakota Department of Transportation (SDDOT) has numerous work zones in operation for maintaining and upgrading the highway system. Speed reductions and traffic control measures are put in place to create a safer work zone environment for construction workers and the traveling public. The SDDOT uses the Manual on Uniform Traffic Control Devices (MUTCD) which defines standards and guidelines for work zones.  SDDOT regularly exceeds the minimum guidelines established in the MUTCD yet crashes in work zones still occur. The SDDOT would like to investigate opportunities to increase driver’s compliance with the traffic control signing and devices in the work zone.  The study team believes that the lack of driver compliance could be a leading contributing factor to the crashes that occur in SDDOT work zones. 
The SDDOT would like to examine work zone types and crashes to identify contributing factors with an overrepresentation of crashes using past work zone crash data. The SDDOT wants to find new strategies to increase driver compliance within work zones, reduce work zone crashes, and improve worker safety. The SDDOT wants to examine how work zone ITS devices, temporary speed reduction devices, and other traffic control methods and devices can be used to increase driver compliance. The findings from this work will aid in future work zone design and operations.
Research needs to be conducted that is specific to South Dakota work zones to determine strategies the SDDOT can implement to improve driver compliance within work zones, reduce work zone crashes, and improve worker safety.
]]></description>
      <pubDate>Mon, 06 May 2024 16:54:25 GMT</pubDate>
      <guid>https://rip.trb.org/View/2377868</guid>
    </item>
    <item>
      <title>Attribution Theory and Collisions at Intersections</title>
      <link>https://rip.trb.org/View/2353430</link>
      <description><![CDATA[Description: An automobile driver (D) is seldom alone on the road. Whenever there is another vehicle – even only one – on or approaching the road on which D is travelling, the future behaviors of the driver of the other car (O) must be guessed, and the probabilities of the possible maneuvers estimated. Understanding driver expectations of other drivers is essential in understanding how and why accidents happen which in-turn leads to better counter measures.

Intellectual Merit: This research will provide an outline for a range of driver expectations at intersections including, driver indications, stop or go decisions, performance and design of intersection traffic control devices, and turn maneuvers.

Broader Impacts: The research findings will help improve driver behavior models in traffic simulation software and in the design of mental behavior of automated vehicles.

Technology Transfer Plan: The research team will share research findings through participation in regional, national and international conferences.]]></description>
      <pubDate>Mon, 25 Mar 2024 15:36:53 GMT</pubDate>
      <guid>https://rip.trb.org/View/2353430</guid>
    </item>
    <item>
      <title>Improving Crash Prediction Using GRIDSMART Infrastructure</title>
      <link>https://rip.trb.org/View/2325689</link>
      <description><![CDATA["Improving Crash Prediction Using GRIDSMART Infrastructure" is a collaborative research project between the University of Connecticut and the University of Maine, in partnership with the Connecticut Department of Transportation (CTDOT). The study addresses the critical issue of intersection safety, noting that over 50% of all fatal and injury crashes occur at or near intersections, with left turn maneuvers accounting for a significant proportion of these crashes. The research aims to enhance Safety Performance Functions (SPFs) by integrating temporally varying data, such as continuous turning movement counts, into their development. This approach overcomes the limitations of traditional SPFs that mainly consider static measures like the two-way annual average daily traffic (AADT).

The project will utilize GRIDSMART technology, a system implemented for traffic signal management, to collect detailed turning and through movements of various road users at intersections. This data will be used to develop more precise and dynamic SPFs, considering factors like bicycle and pedestrian counts, road geometry, and surrounding land development intensity. The dependent variables in the study will include annual crash counts by manner of collision, categorized by the direction of travel of the involved vehicles.

The methodology involves collecting raw data using GRIDSMART, identifying relevant variables, and selecting intersections based on data quality for analysis. The team will perform temporal aggregation of data and classify crashes by manner of collision. The resulting analysis aims to determine whether turning movements are significant predictors of crashes and how improvements to GRIDSMART infrastructure could enhance intersection safety.]]></description>
      <pubDate>Mon, 22 Jan 2024 09:44:56 GMT</pubDate>
      <guid>https://rip.trb.org/View/2325689</guid>
    </item>
    <item>
      <title>Holistically Identifying Road Complexity and Relating it to Fatal Crashes</title>
      <link>https://rip.trb.org/View/2325387</link>
      <description><![CDATA[Understanding the context of crash occurrence in complex driving environments is essential for improving traffic safety and advancing automated driving. Previous studies have used statistical models and deep learning to predict crashes based on semantic, contextual, or vehicle kinematic features, but none have examined the combined influence of these factors. In this study, we term the integration of these features ``roadway complexity''. This paper introduces a two-stage framework that integrates roadway complexity features for crash prediction. In the first stage, an encoder extracts hidden contextual information from these features, generating latent complexity features. The second stage uses both original and latent complexity features to predict crash likelihood, achieving an accuracy of 87.98% with original features alone and 90.46% with the added latent complexity features. Ablation studies confirm that a combination of semantic, kinematic, and contextual features yields the best results, which emphasize their role in capturing roadway complexity. Additionally, complexity index annotations generated by the Large Language Model outperform those by Amazon Mechanical Turk, highlighting the potential of AI-based tools for accurate, scalable crash prediction systems.]]></description>
      <pubDate>Fri, 19 Jan 2024 10:22:19 GMT</pubDate>
      <guid>https://rip.trb.org/View/2325387</guid>
    </item>
    <item>
      <title>Development of a Traffic Incident Management Toolbox and Evaluation of Data Sources for Effective Early Warning and Detection of Abnormal Traffic Conditions</title>
      <link>https://rip.trb.org/View/2301125</link>
      <description><![CDATA[The main goal of this research is to identify, compare, and evaluate various Traffic Incident Managemetn (TIM) data sources and warning systems to provide FDOT with a toolbox of effective data sources and warning systems for different scenarios. These data sources and warning systems could be used to proactively provide early warnings of abnormal traffic conditions which could potentially lead to crashes if not addressed. The effectiveness and performance of the studied data sources and warning systems will be compared to existing data sources and systems used by FDOT for different event types (road hazards, congestion, etc.) and area/ environmental characteristics (such as urban vs. rural and day vs. night) to identify the best data sources and warning systems for different areas and roadways. The developed TIM toolbox will be tailored to the appropriate end users (traffic management center (TMC) operators, operations managers, etc.), allowing FDOT to easily identify the most effective data sources and warning systems for potential future deployment and testing, reducing congestion and saving lives.]]></description>
      <pubDate>Thu, 30 Nov 2023 11:04:07 GMT</pubDate>
      <guid>https://rip.trb.org/View/2301125</guid>
    </item>
    <item>
      <title>Utilizing Telematics to Understand Driving Behavior During Missed Exits and Wrong Turns</title>
      <link>https://rip.trb.org/View/2256324</link>
      <description><![CDATA[Texas is currently experiencing its largest population growth in decades. More and more lands are being urbanized and complex design methods are often adopted. As a result, drivers are likely confused at certain locations such as ramps, roadway exits and intersections. The overarching goal of this project is to identify unsafe and inefficient locations of Texas state highways, where driving behaviors often reveal excessive abnormities (e.g., hard brakes, control stops and/or missing of road entrances/exits). Problematic locations are due to misleading roadway designs or signage configurations in many cases. In the past, Texas Department of Transportation (TxDOT) could not identify such locations until either a driver called to complain or crashes occurred frequently. The emerging telematics data from connected vehicles (CVs) will enable such possibility to identify and fix problematic locations proactively. Applying the state-of-the-art big data analytics and Artificial Intelligence (AI) techniques on the emerging vehicle telematics data (delivered by Wejo and INRIX), the research team will demonstrate how to identify problematic locations within the selected area. The research team will also integrate multiple advanced computing techniques (e.g., high-performance computing, cloud-computing etc.) to cost-effectively streamline the process of traffic big data fusion, cleaning, and reduction for TxDOT's future practices.]]></description>
      <pubDate>Wed, 27 Sep 2023 16:18:49 GMT</pubDate>
      <guid>https://rip.trb.org/View/2256324</guid>
    </item>
  </channel>
</rss>