<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 Pavement Performance Model for Effective Pavement Management of Wyoming County Roads, Phase I</title>
      <link>https://rip.trb.org/View/2777829</link>
      <description><![CDATA[As pavements progressively age and deteriorate over time, it becomes necessary for agencies to allocate substantial financial resources to sustain their pavement network in a condition deemed acceptable. A significant number of county roads were constructed decades ago and have received on-demand maintenance, resulting in suboptimal overall road conditions for Wyoming counties. Therefore, since 2014, the Wyoming Technology Transfer Center, in association with Wyoming Department of Transportation (WYDOT), has been collecting county road pavement performance data in Wyoming to make informed management decisions in the future. The pavement data collected includes rut depth, cracking, roughness, and other associated data such as route, direction, mile post, road width, length, district, county, and speed. Local governmental entities are responsible for the management of county roads, relying on their engineering expertise and judgment, without the implementation of a county-specific Pavement Management System (PMS). Also, different vendors have collected this data over time. There exists a need to check the consistency, quality, and continuity of this data from vendors. This study addresses this gap and plans to develop a pavement performance model from the collected data for county roads. Overall, this study is divided into two phases. Phase I of the research will review the data collected from different vendors for consistency, check quality, and continuity. Thereafter, the study will examine the existing pavement performance deterioration model for county roads. Finally, Phase II of this research plans to develop a new county pavement deterioration model and performance index, along with decision trees for pavement management. This research will help aid decision-makers in making better choices by allocating the funding appropriately with preventive treatment, minor and major rehabilitation to ensure good quality county roads. Finally, the outcome of this research can be used by policymakers to implement the best practices of PMS in Wyoming counties.]]></description>
      <pubDate>Mon, 14 Sep 2026 14:14:50 GMT</pubDate>
      <guid>https://rip.trb.org/View/2777829</guid>
    </item>
    <item>
      <title>Agentic AI for ASTM-Aligned Pavement Assessment Framework</title>
      <link>https://rip.trb.org/View/2777810</link>
      <description><![CDATA[This project proposes an agentic artificial intelligence (AI) framework for pavement assessment that brings together multimodal deep learning, depth-aware evidence, and standards-aligned reasoning within a single workflow. Although recent automated methods have improved distress detection, segmentation, and severity labeling, they still function largely as isolated tasks and therefore do not support the broader engineering reasoning required for maintenance decision-making. As a result, an important gap remains between model prediction and practical pavement assessment. Building on prior advances in pavement condition index estimation, dense captioning, and annotation-efficient segmentation, the proposed framework will detect and classify pavement distress, estimate severity and depth-related condition indicators, identify the appropriate ASTM-aligned assessment pathway, and generate clear engineering-oriented reports. In this way, the project connects perception, interpretation, pathway selection, and reporting in a coordinated system. Ultimately, it aims to move pavement AI beyond passive prediction toward a more interpretable, scalable, and decision-ready tool for transportation practice.]]></description>
      <pubDate>Mon, 14 Sep 2026 14:03:26 GMT</pubDate>
      <guid>https://rip.trb.org/View/2777810</guid>
    </item>
    <item>
      <title>Enhancing The Wyoming Pavement Quality Rating Estimation</title>
      <link>https://rip.trb.org/View/2772465</link>
      <description><![CDATA[The Wyoming Department of Transportation (WYDOT) currently relies on the Pavement Quality Rating (PQR) as the primary performance indicator within its pavement management system. Although PQR is conceptually bounded between 0 and 5, the existing formulations occasionally produce negative values due to nonlinear distress transformations, reducing interpretability and limiting long-term forecasting reliability. This research aims to refine, calibrate, and validate an improved PQR model that addresses these deficiencies while aligning with national performance metrics. The study aims to document existing pavement performance practices from state agencies and research institutions, evaluate and modify the current PQR equations to ensure bounded and explainable outputs, incorporate a layered cracking taxonomy, quantify the influence of traffic loading and pavement structural characteristics, and validate predictive capability using historical distress datasets. Expected outcomes include a robust, bounded PQR equation, decision-support thresholds, and associated implementation tools for integration into WYDOT's pavement management workflows. The resulting model will improve data-driven decision-making, support cost-effective rehabilitation planning, and enhance long-term asset management capability. The project will also provide educational and technology transfer benefits through student engagement, conference presentations, and peer-reviewed publications.]]></description>
      <pubDate>Tue, 01 Sep 2026 08:55:36 GMT</pubDate>
      <guid>https://rip.trb.org/View/2772465</guid>
    </item>
    <item>
      <title>Pavement Deterioration Models Review</title>
      <link>https://rip.trb.org/View/2764010</link>
      <description><![CDATA[The Virginia Department of Transportation (VDOT) maintains a pavement network consisting of more than 130,000 lane miles. Each year, VDOT uses the results of an automated condition survey to quantify the pavement condition in terms of a Critical Condition Index (CCI). From this survey and considering other constraints, VDOT employs a decision-tree process to suggest one of five treatment categories to program pavement maintenance treatments each year. Pavement deterioration models that were developed by a consultant in 2007 are used to predict the future condition of a pavement based on the pavement family type and previous maintenance treatment category. The purpose of this study is to review the pavement deterioration models used in VDOTs pavement management system to determine if they still reflect the current trends of VDOT’s pavement network and suggesting updates if required.   ]]></description>
      <pubDate>Thu, 20 Aug 2026 08:08:45 GMT</pubDate>
      <guid>https://rip.trb.org/View/2764010</guid>
    </item>
    <item>
      <title>Development of a Pavement Friction Management Program for Illinois - Phase II</title>
      <link>https://rip.trb.org/View/2761613</link>
      <description><![CDATA[Friction between pavement and vehicles is a key part to highway safety, allowing drivers to change directions safely as well as reducing skidding or hydroplaning. This effort builds off Illinois Center for Transportation and Illinois Department of Transportation (IDOT) project R27-264, which developed a statewide management program for pavement friction by using statistical modeling to correlate pavement friction and safety analysis. In this project, researchers will use pavement friction data for Illinois’ road network to further enhance the developed program, continue revisions to the friction aggregate mixture policy and conduct pilot implementation in a few IDOT districts. The enhanced program will allow IDOT to identify areas with elevated safety risks and determine improvements to friction to reduce crashes, increasing safety for roadway users.]]></description>
      <pubDate>Mon, 17 Aug 2026 10:55:10 GMT</pubDate>
      <guid>https://rip.trb.org/View/2761613</guid>
    </item>
    <item>
      <title>AI-assisted Condition Assessment of Roads</title>
      <link>https://rip.trb.org/View/2752288</link>
      <description><![CDATA[The objective of this project is to develop an AI-assisted road monitoring system that enables low-cost, autonomous, and frequent condition-based assessments using a network of mobile sensing units. The system will use computer vision and machine learning to detect and quantify pavement defects, replacing traditional schedule-based inspections with continuous, data-driven monitoring. The proposed system provides transportation agencies with an affordable, scalable, and intelligent tool for real-time pavement monitoring. By using low-cost sensors on existing vehicles and automated data interpretation, it delivers accurate condition insights, reduces inspection costs, and supports timely maintenance decisions.]]></description>
      <pubDate>Thu, 13 Aug 2026 15:31:12 GMT</pubDate>
      <guid>https://rip.trb.org/View/2752288</guid>
    </item>
    <item>
      <title>Developing a Nebraska-Specific Evaluation Framework for Superheavy Load Movements on Pavements</title>
      <link>https://rip.trb.org/View/2689391</link>
      <description><![CDATA[Nebraska continues to receive superload permit requests whose non-standard axle/tire layouts, slow-roll operations, and edge-proximity produce subsurface stress patterns that are not consistently captured by current screening practices. Although the federal framework and SuperPACK provide a sound mechanistic basis, they have not yet been exercised in a Nebraska-focused parametric fashion to reveal which combinations of pavement structure, material properties, axle weights, and spacings govern ultimate capacity and service-limit responses on state routes. Without that evidence, route approvals remain slower and less consistent, and operating conditions or mitigations are difficult to specify with confidence. This study will provide the Nebraska Department of Transportation (NDOT) with a focused, evidence-based screen for superload movements on Nebraska highways. By exercising SuperPACK in a structured parametric study and benchmarking marginal cases with an advanced finite element (FE) tool, the work will yield preliminary acceptance bounds that can be applied directly to permit reviews. The project will also clarify when a simple mechanics-based screen is sufficient and when an advanced check is warranted, improving the efficiency of reviewer time and aligning engineering findings with transparent cost-recovery logic. Because the analysis uses Nebraska-representative sections, inputs, and axle/tire nuclei taken from real permits, the results will be credible to internal reviewers and external stakeholders and will establish a practical pathway to extend the approach to rigid and composite pavements in subsequent phases.]]></description>
      <pubDate>Tue, 02 Jun 2026 12:24:39 GMT</pubDate>
      <guid>https://rip.trb.org/View/2689391</guid>
    </item>
    <item>
      <title>How Can NMDOT Use TSD Data to Support Pavement Design</title>
      <link>https://rip.trb.org/View/2704033</link>
      <description><![CDATA[TSD is a valuable technology for measuring surface deflections at short intervals and capturing data on roughness, texture, and rutting at traffic speed. Several highway agencies in the United States and other countries are currently either looking into how to use TSD data in their pavement management system (PMS) to ensure responsible expenditure of taxpayers’ dollars.]]></description>
      <pubDate>Wed, 20 May 2026 11:15:23 GMT</pubDate>
      <guid>https://rip.trb.org/View/2704033</guid>
    </item>
    <item>
      <title>SPR-5031: Developing INDOT Road Crack Image Datasets for Advanced Analytics Research</title>
      <link>https://rip.trb.org/View/2691526</link>
      <description><![CDATA[The Indiana Department of Transportation (INDOT) requires a comprehensive, annotated crack image dataset from falling weight deflectometer (FWD) testing to enable advanced analytics for pavement management. This project delivers systematically labeled crack images to correlate with structural deflection data, and standardized annotation protocol. Dataset enables automated crack detection, enhanced structural assessment capabilities, and data-driven pavement management decisions while leveraging existing image archives cost-effectively through annotators.]]></description>
      <pubDate>Wed, 06 May 2026 14:55:27 GMT</pubDate>
      <guid>https://rip.trb.org/View/2691526</guid>
    </item>
    <item>
      <title>Modernization and Web-Based Implementation of the Illinois Pavement Feedback System</title>
      <link>https://rip.trb.org/View/2677555</link>
      <description><![CDATA[This project will modernize the Illinois Department of Transportation’s (IDOT's) Illinois Pavement Feedback System, a pavement management system that contains detailed construction history, performance data and traffic data of the Illinois interstate system. Researchers will transition the database from a mainframe-based system into a secure, web-based pavement data management and analysis platform. Transitioning to a web-based platform will provide IDOT with an easy way to access the data, monitor interstate sections, and make informed maintenance and rehabilitation decisions. The system will also have a detailed dataset on Illinois’ interstate system available to researchers.]]></description>
      <pubDate>Wed, 04 Mar 2026 09:22:25 GMT</pubDate>
      <guid>https://rip.trb.org/View/2677555</guid>
    </item>
    <item>
      <title>Incorporating Pavement Structural Capacity into TxDOT Pavement Management Information System</title>
      <link>https://rip.trb.org/View/2666837</link>
      <description><![CDATA[The research team will provide the Texas Department of Transportation (TxDOT) a means to use Traffic Speed Deflectometer (TSD) data to assess the structural condition of their roadways at the network-level by (a) leveraging TSD measurements and pavement data from existing databases in the US to complement the information collected in Texas for proposing and validating indices derived from velocity-based TSD measurements. To do this, the research team will develop a novel, velocity-based methodology for analyzing TSD data, as existing approaches rely on deflection-based methods not suited for the TSD, consider appropriate velocity indices and thresholds for classifying pavement structural condition, assess load transfer efficiency of jointed pavements, and ensure seamless integration of these data into PMIS.]]></description>
      <pubDate>Tue, 10 Feb 2026 14:45:51 GMT</pubDate>
      <guid>https://rip.trb.org/View/2666837</guid>
    </item>
    <item>
      <title>Development of Data Driven Digital Twin for Enhancing Pavement Performance Prediction in South-Central United States</title>
      <link>https://rip.trb.org/View/2658057</link>
      <description><![CDATA[A comprehensive survey conducted by National Cooperative Highway Research Program (NCHRP) Synthesis 501 revealed that many state departments of transportation (DOTs) update their pavement performance models only every 2 to 5 years, with some agencies updating even less frequently. Such lengthy update cycles mean that the models often fail to reflect recent trends in traffic loading and material performance, leading to outdated forecasts that diminish the accuracy and usefulness of maintenance and rehabilitation planning. The primary objective of this project is to develop a data-driven Digital Twin (DT) framework based on pavement management system data that will regularly update Artificial Intelligence (AI)-based performance models for pavements in Louisiana. This framework aims to help state agencies make smarter, more accurate maintenance decisions while reducing costs over time. The proposed Digital Twin platform will focus on the interstate network in Louisiana, given its importance to the state and its wide implications on mobility and freight movement. The work will be divided into five tasks: (1) collect and preprocess pavement management system data for the interstate network, (2) development of digital twin framework, (3) forecast future pavement conditions in digital twin platform, (4) suggest potential maintenance strategies in the digital twin platform, and (5) prepare final report. The project will address the growing need for innovative approaches that can dynamically integrate diverse datasets, learn from both historical and emerging patterns, and provide transportation agencies with actionable, real-time insights. Digital twin technology offers this dynamic capability by enabling a shift from reactive maintenance toward predictive and proactive strategies.  ]]></description>
      <pubDate>Fri, 23 Jan 2026 13:50:08 GMT</pubDate>
      <guid>https://rip.trb.org/View/2658057</guid>
    </item>
    <item>
      <title>Correlating Pavement Conditions and Traffic Accidents through AI-based Data Mining
</title>
      <link>https://rip.trb.org/View/2627710</link>
      <description><![CDATA[Pavement surface conditions have a strong positive effect on accident risks. Pavement surface distresses directly affect ride comfort and indirectly cause distraction to the driver resulting in loss of control of the vehicle, which may lead to injuries or deaths. The reason for the lack of research on contribution of bad pavement condition to traffic crashes maybe lies in the fact that previously the data of pavement condition are not readily available to researchers in traffic safety, or sometimes it is comparatively hard for researchers to get the systematic data of pavement condition to conduct analyses. The proposed research will take opportunity of current well-known databases such as the long-term pavement performance (LTPP) database and pavement management system (PMS) at state agencies, to conduct deep and systematic data mining on the existing pavement performance and traffic safety data using data-driven intelligence technologies, and develop predictive models in terms of pavement performance, material properties, traffic effects, and pavement maintenance plans. The research outcome will help guide highway agencies to better design, maintain, and manage pavement infrastructures with enhanced roadway safety. 
]]></description>
      <pubDate>Fri, 21 Nov 2025 14:09:04 GMT</pubDate>
      <guid>https://rip.trb.org/View/2627710</guid>
    </item>
    <item>
      <title>AI-Driven Infrastructure Prioritization: Vision-Language Model Framework for Capital Planning</title>
      <link>https://rip.trb.org/View/2620732</link>
      <description><![CDATA[This project develops a scalable, artificial intelligence (AI)-powered framework for automated condition assessment and capital investment prioritization of road and bridge infrastructure across Colorado. Current manual inspection methods are costly, slow, and limited in coverage, often missing early signs of degradation. Leveraging recent advances in Vision-Language Models (VLMs), the project proposes a novel approach that extracts Pavement Condition Index (PCI) and bridge deck ratings from satellite and street-level imagery using VLMs guided by prompt engineering and in-context learning, requiring no retraining, and will be validated against Colorado Department of Transportation (CDOT) inspection records using machine learning model accuracy metrics.

The framework integrates three components: (1) Infrastructure condition (2) network criticality, computed via graph-theoretic metrics and traffic data, and (3) hazard exposure, based on geospatial data for landslides, wildfires, and floods. These layers will be synthesized into a weighted prioritization model to rank road segments for capital upgrades, refined through CDOT expert review.

A web-based geographic information system (GIS) tool will visualize prioritization results, supporting interactive exploration and decision-making. The tool will be pilot-tested with CDOT districts, and outcomes will be disseminated through a final report, peer-reviewed publication, Transportation Learning Network (TLN) webinar, and Colorado LTAP training.

By integrating AI, geospatial analytics, and network modeling, this project addresses data-driven infrastructure planning needs—enhancing efficiency, reliability, and resilience—while offering a replicable model nationwide.]]></description>
      <pubDate>Mon, 10 Nov 2025 16:24:50 GMT</pubDate>
      <guid>https://rip.trb.org/View/2620732</guid>
    </item>
    <item>
      <title>Develop Performance Models for Different Preventive Maintenance Treatments</title>
      <link>https://rip.trb.org/View/2604521</link>
      <description><![CDATA[The Texas Department of Transportation's (TxDOT) Pavement Management Information System (PMIS), recently implemented as Pavement Analyst (PA), stores and analyses network information and pavement performance data to select projects for maintenance and rehabilitation. After the network is analysed, an optimization algorithm produces one of the following recommendations: do nothing, preventive maintenance (PM), light, medium or heavy rehabilitation. PM includes several treatment options associated with very different cost and performance, e.g., seal coat, thin overlay, microsurfacing, etc. Since the performance and cost of these options are different, research is needed to quantify the difference and to incorporate this information into PMIS. Previous TxDOT-sponsored projects have developed performance models and decision trees that were last updated in 2021 as part of Project 0-6988, "Quantification of the Performance of Preventive Maintenance and Rehabilitation Strategies." This update was based on data available at that time, which was a combination of visual distress surveys and automated data. Now, more accurate automated data are available. Therefore, the research team will develop pavement performance models for different PM treatments, update the current decision trees and performance models, validate the models with new data, and develop an implementation plan to incorporate the findings into PMIS.]]></description>
      <pubDate>Mon, 29 Sep 2025 16:08:57 GMT</pubDate>
      <guid>https://rip.trb.org/View/2604521</guid>
    </item>
  </channel>
</rss>