<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>Human-AI Collaborative Bridge Inspection for Advanced Damage Detection
and Defect Quantification</title>
      <link>https://rip.trb.org/View/2689757</link>
      <description><![CDATA[The aging concrete bridge infrastructure across the U.S. poses increasing risks to safety and reliability, amplifying the urgency to modernize inspection processes. Traditional manual inspection methods are labor-intensive, subjective, and inconsistent, creating barriers to effective infrastructure management. This research proposes an innovative human-AI collaborative framework designed to enhance the durability, resiliency, and technological capabilities of bridge inspections. The project integrates advanced artificial intelligence (AI) and computer vision technologies to automate damage detection and defect quantification. To ensure reliability and trustworthiness, the AI system incorporates rigorous uncertainty quantification methods, increasing transparency and inspector confidence. An active learning component strategically facilitates human-AI collaboration, enabling inspectors to focus on the most critical inspection cases identified by the AI, significantly reducing manual workloads. Additionally, engineering domain expertise, particularly in structural reliability and risk assessment, will inform and prioritize inspection processes within the AI framework. The outcomes of this project will substantially improve the accuracy, efficiency, and reliability of bridge inspections, promoting safer, longer-lasting, and more resilient transportation infrastructure. Anticipated benefits include reduced inspection costs, enhanced public safety, and a proactive approach to infrastructure management that significantly extends service life and supports sustainability. ]]></description>
      <pubDate>Thu, 10 Sep 2026 09:04:28 GMT</pubDate>
      <guid>https://rip.trb.org/View/2689757</guid>
    </item>
    <item>
      <title>SHM-based Bridge Element Deterioration Modeling and Prediction</title>
      <link>https://rip.trb.org/View/2692311</link>
      <description><![CDATA[The transportation legislation MAP-21 and the FAST Act have advanced the integration of performance-based asset management into transportation decision-making across federal, state, and local levels. Through Transportation Asset Management (TAM), agencies are establishing systematic processes to operate, maintain, and preserve infrastructure assets throughout their lifecycle. The objective of the project described herein is to support these goals by developing a methodology for predicting bridge element deterioration using long-term Structural Health Monitoring (SHM) data. Current approaches rely on periodic inspections and NDT/NDE methods, which miss real-time changes and pose safety risks. By combining SHM data with traditional models (Markov chains, Weibull distributions) and advanced algorithms, this research aims to produce accurate, time-based deterioration curves for bridge elements. Using high-resolution data from the BEAST lab at Rutgers University, the models will be calibrated and validated to reflect real-world deterioration mechanisms. This work supports NCIT’s mission to improve durability and extend the life of transportation infrastructure. It directly addresses the topical pillars of Infrastructure Durability, Resiliency, and Technology, offering tools for predictive maintenance, life-cycle cost management, and improved safety. The outcome will aid bridge owners in making data-driven decisions that enhance long-term performance and resilience. ]]></description>
      <pubDate>Thu, 10 Sep 2026 08:40:39 GMT</pubDate>
      <guid>https://rip.trb.org/View/2692311</guid>
    </item>
    <item>
      <title>Developing a Multi-Resolution Remote Monitoring System for Bridge Integrity
Assessment (BIA) Using IoT and AI Technologies</title>
      <link>https://rip.trb.org/View/2696932</link>
      <description><![CDATA[Bridges are an integral part of U.S. transportation networks, improving highway connectivity and accessibility. For instance, there are over 55,000 bridges in Texas, with an average age of 43 years. The maintenance of this bridge network costs the TxDOT more than $300 million annually. The traditional Bridge Integrity Assessment (BIA) monitoring methods include periodic manual inspections to observe visible cracks, wearing surface, drainage features, signs of scouring or erosion at the piers or abutment, and overall structural integrity, and other sensors to monitor stress, vibrations, and movements continuously. With the advancement of AI and IoT, it is more possible than ever to develop an innovative BIA system that can address the challenges of traditional BIA methods and support bridge structure safety and integrity. The proposed research has three objectives: (1) Design an AI-enabled secure remote monitoring architecture for supporting BIA and maintenance. (2) Build an end-to-end simulation system to evaluate and validate the developed architecture to detect threats that pose a risk to bridge structure safety. (3) Implement a prototype of the proposed multi-resolution remote monitoring system using various remote sensing technologies and conduct real-world field experiments using the developed system (i.e., UAV and IoT sensors). Additionally, the Blinn College District (BCD) will organize an educational workshop for Prairie View A&M University (PVAMU) and BCD students, during which unmanned aerial vehicle (UAV) technologies will be demonstrated. The project outcomes will assist the DOTs (Department of Transportation) in monitoring the bridge infrastructure condition and conducting preventive maintenance more efficiently. This project is directly related to NCIT’s focus area of “Improving the Durability and Extending the Life of Transportation Infrastructure” and the NCIT’s topical pillar, “Technology.”]]></description>
      <pubDate>Thu, 10 Sep 2026 08:32:55 GMT</pubDate>
      <guid>https://rip.trb.org/View/2696932</guid>
    </item>
    <item>
      <title>AI-Powered Infrastructure Monitoring and Decision Support for Transportation Safety: Field Deployment and TDI Integration</title>
      <link>https://rip.trb.org/View/2742139</link>
      <description><![CDATA[In its fourth year, this project continues to advance transportation safety through the deployment and scaling of cutting-edge technologies for near real-time monitoring of infrastructure. Building on the foundational work of Year 1 (inverse problem framework development and vision-based structural health monitoring for bridges) and Year 3 (AI-powered video analytics scaled to urban infrastructure), the Year 4 initiative at Howard University integrates three funded years of research into a deployable, scalable monitoring solution.

The core focus of Year 4 is field deployment of the integrated monitoring platform on an operational bridge in Washington, DC, identified in coordination with the District Department of Transportation (DDOT). In parallel, the project will conduct exploratory trials of drone-based video and imagery for structural inspection, in collaboration with DDOT’s Drones team, to assess whether this complementary sensing approach warrants full integration in a potential Year 5. The work integrates civil engineering, computer vision, machine learning, and applied mathematics for AI-powered structural diagnosis.]]></description>
      <pubDate>Sat, 01 Aug 2026 09:43:24 GMT</pubDate>
      <guid>https://rip.trb.org/View/2742139</guid>
    </item>
    <item>
      <title>Inverse Problem Approaches for Bridge Structural Health Monitoring Using Displacement Data</title>
      <link>https://rip.trb.org/View/2732495</link>
      <description><![CDATA[This project aims to develop an inverse problem framework for bridge structural health monitoring (SHM) using displacement data as the primary diagnostic input. Traditional SHM methods based on finite element model updating and contact-based sensor networks are computationally demanding and require extensive field calibration, while acceleration-based techniques struggle to detect local damage. To address these limitations, the study applies inverse problem-solving methodologies that enable the direct inference of unknown structural parameters—such as stiffness variations, damage locations, and boundary conditions—from displacement measurements. Recent advancements in computer vision technologies have significantly improved the accessibility, accuracy, and cost-effectiveness of displacement data collection, making bridge condition assessment increasingly feasible. Through data analysis, inverse modeling, and validation, the research develops a validated framework for bridge condition assessment based on displacement data, reducing reliance on contact sensor networks and improving the accuracy of local damage detection across transportation infrastructure.]]></description>
      <pubDate>Wed, 22 Jul 2026 12:08:48 GMT</pubDate>
      <guid>https://rip.trb.org/View/2732495</guid>
    </item>
    <item>
      <title>Deep Learning–Based Digital Image Correlation for Fatigue Crack  Characterization in Steel Structures
</title>
      <link>https://rip.trb.org/View/2703927</link>
      <description><![CDATA[This proposal presents a strategic approach to improving transportation safety through the advancement of deep learning–based Digital Image Correlation (DIC) for fatigue crack characterization in steel structural components. With aging transportation infrastructure and increasing cumulative traffic loading, fatigue-related deterioration in steel bridges and related systems presents ongoing safety risks. Accurate measurement of crack-induced displacement fields is critical for reliable structural assessment and informed maintenance decisions. The primary objectives of this proposal are to advance artificial intelligence (AI)-driven DIC methods beyond the limitations of conventional correlation-based approaches by enabling sub-pixel displacement learning through synthetic data generation, incorporating physics-informed modeling of crack-induced displacement discontinuities, and supporting high-resolution analysis of large image regions without loss of spatial detail. The methodology involves grayscale synthetic speckle data generation for sub-pixel displacement learning, mechanics-based displacement field modeling using finite element simulations, and development of an attention-enhanced deep learning architecture for full-field displacement prediction. Experimental validation against commercial DIC systems will establish a transferable methodology supporting safer fatigue crack evaluation practices.
]]></description>
      <pubDate>Tue, 19 May 2026 13:48:19 GMT</pubDate>
      <guid>https://rip.trb.org/View/2703927</guid>
    </item>
    <item>
      <title>Phase II Pilot Program for UAS-Enabled Component Level Bridge Inspection in New Mexico</title>
      <link>https://rip.trb.org/View/2703713</link>
      <description><![CDATA[Building on the success of Phase I, Phase II of the project seeks to expand unmanned aircraft system (UAS) inspection capabilities to focus on bridge superstructures. This is a more complex and critical component of overall structural performance, because superstructures, comprising elements such as girders, beams, and trusses, are responsible for transferring deck loads to substructures and ultimately to the ground. Their integrity is essential for bridge safety and serviceability.]]></description>
      <pubDate>Fri, 15 May 2026 13:14:08 GMT</pubDate>
      <guid>https://rip.trb.org/View/2703713</guid>
    </item>
    <item>
      <title>Artificial Intelligence (AI) Technologies for Data-Driven Bridge Management</title>
      <link>https://rip.trb.org/View/2703687</link>
      <description><![CDATA[Artificial intelligence (AI) is showing promise for providing quick analysis, summary and documentation of field conditions for bridges. This project will provide the Illinois Department of Transportation (IDOT) with an overview of AI products available for bridge inspection and management. Researchers will review other state agencies’ practices and policies for use of AI in this field as well as develop recommendations for IDOT. Aid in formulation of AI policy for bridge inspection within IDOT may be considered if the department deems the technology essential. Effective use of AI in bridge inspection and management systems will provide cost and time savings to the state, allowing for quicker bridge inspections, diagnosis of issues and documentation.]]></description>
      <pubDate>Fri, 15 May 2026 09:24:49 GMT</pubDate>
      <guid>https://rip.trb.org/View/2703687</guid>
    </item>
    <item>
      <title>Cybersecurity Assurance via AI-Driven Digital Twins for Transportation Safety  </title>
      <link>https://rip.trb.org/View/2663600</link>
      <description><![CDATA[Transportation infrastructure increasingly depends on networked sensor systems for structural health monitoring, yet many operational deployments lack robust data-integrity protections, rendering them vulnerable to cyber-physical attacks. Manipulated sensor readings can misrepresent bridge health, rail conditions, or load limits, thereby creating risks of undetected structural failure, service closures, or catastrophic crashes. Because cyber manipulation directly produces false-safe readings, delays critical maintenance actions, and conceals structural distress, cybersecurity protection constitutes a core safety requirement, not an ancillary concern, for modern monitoring infrastructure.
This project develops a secure, artificial intelligence (AI)-driven digital twin framework that continuously compares real-time sensor data against expected behavioral responses to detect spoofing, tampering, replay, and delay manipulation, and other cyber-physical disruptions. The digital twin is intentionally implemented as a lightweight behavioral model; its purpose is not full structural simulation but rather the generation of expected-response profiles that serve as the ground-truth reference for anomaly detection. Combined with secure sensing hardware, AI-based detection algorithms, and survivability logic, the integrated system maintains reliable monitoring capability even under partial cyber compromise. The framework supports the U.S. Department of Transportation (USDOT) Safe System Approach by preventing cyber-induced safety failures and provides a clear pathway to pilot deployment through a Python-based prototype, agency demonstrations, and structured partner engagement.

Key milestones include the twin baseline model, secure sensing validation, AI detection module completion , and a survivability demonstration with partner input. The resulting system provides transportation agencies with a low-cost cybersecurity layer that protects safety-critical sensing systems from data manipulation and disruption. Deliverables include a Python detection module, interactive dashboard, and validated datasets compatible with existing DOT workflows. By ensuring the trustworthiness of monitoring data, the proposed approach reduces hazard risk, strengthens maintenance decision-making, and scales across bridges, tunnels, and rail systems, offering a realistic and immediate path to pilot adoption within USDOT transportation-cybersecurity priorities.
]]></description>
      <pubDate>Tue, 03 Feb 2026 15:23:30 GMT</pubDate>
      <guid>https://rip.trb.org/View/2663600</guid>
    </item>
    <item>
      <title>Coastal pavement maintenance and rehabilitation decision making based on both surface and subsurface conditions</title>
      <link>https://rip.trb.org/View/2662938</link>
      <description><![CDATA[Texas has approximately 3,359 miles of coastline spanning five geographically distinct districts. Pavements in these regions are exposed to highly variable subgrade soils, diverse traffic loading levels, and unique climatic challenges, including hurricanes, storm surges, and recurrent flooding. Effective decision-making for pavement Maintenance and Rehabilitation (M&R) is therefore critical to ensuring resilient infrastructure, optimizing project selection, and allocating limited resources efficiently. Current M&R selection practices primarily rely on surface-level indicators—such as distress manifestations (cracking, rutting, etc.) and ride quality. While these measures are useful, they fail to provide a comprehensive understanding of the pavement’s structural health. To address this limitation, this study will propose an integrated framework that combines both surface and subsurface information for M&R decision-making. In particular, subsurface conditions derived from non-destructive testing will be emphasized as a means to bridge the existing knowledge gap, enabling a more holistic and data-driven approach to pavement management.]]></description>
      <pubDate>Thu, 29 Jan 2026 15:57:56 GMT</pubDate>
      <guid>https://rip.trb.org/View/2662938</guid>
    </item>
    <item>
      <title>Continuous 3D Strain Imaging for Structural Health Monitoring of Pavements </title>
      <link>https://rip.trb.org/View/2646968</link>
      <description><![CDATA[This project proposes to advance road infrastructure monitoring by leveraging distributed fiber optic sensing (DFOS) technologies in conjunction with advanced visualization techniques. While typical assessment tools rely on surface measurements and back calculation methods to infer internal conditions, they cannot measure strains within the pavement layers directly. On the other hand, traditional localized sensors offer limited spatial coverage, missing critical information between sensing points. Embedding distributed fiber optic sensing sensors directly into pavement structures will potentially enable the acquisition of high-resolution, real-time distributed strain measurements across extended lengths, providing an unprecedented, comprehensive understanding of the infrastructure condition under traffic loads. Furthermore, the integration of distributed fiber optic sensing measurements with mapping tools will allow transportation engineers to readily identify potential damage areas and structural deficiencies, which can potentially lead to optimized maintenance scheduling, improved road safety, and reduced long-term infrastructure management costs for highway agencies. 

This project aims to develop methods and tools to advance road infrastructure monitoring by integrating fiber optic strain sensing with 3D visualization. To achieve this goal, laboratory testing of pavement specimens strategically instrumented with distributed fiber optic sensing while trafficked with simulated traffic loads will be conducted to generate detailed strain measurements. Key objectives include developing methods for referencing, acquiring, and processing real-time, distributed strain data from embedded fiber optic sensors to generate insightful maps capable of representing strain distributions and their evolution in response to traffic, environment, and distress. This will facilitate the early identification of structural deficiencies, ultimately supporting proactive maintenance planning for highway agencies.  

The project scope involves developing and validating a comprehensive monitoring and visualization framework. This includes optimizing data acquisition, creating algorithms for efficient data reduction and processing of continuous strain measurements, and designing interactive 3D visualization tools. Laboratory validation of the techniques will be conducted, with the goal of future field testing on actual test sections to demonstrate the practical applicability and benefits of the developed system for highway agencies. ]]></description>
      <pubDate>Tue, 06 Jan 2026 17:23:14 GMT</pubDate>
      <guid>https://rip.trb.org/View/2646968</guid>
    </item>
    <item>
      <title>Development of Methods for Rapidly and Accurately Processing LiDAR Data for Evaluating Deformations in Bridges and Bridge Elements</title>
      <link>https://rip.trb.org/View/2633315</link>
      <description><![CDATA[Light Detection And Ranging (LiDAR) is a remote sensing method that creates point-clouds defining physical configuration of objects within line of sight by measuring travel time of pulsed lasers. It promises to revolutionize structural testing and health monitoring by allowing for the replacement of a legion of point measurement devices with a single device that provides exceptionally accurate and synchronized data to accurately describe external structural features. The point clouds that are generated are useful in both qualitative visualization and quantitative analysis of structural state and changes. LiDAR produces very large data sets which are typically well-suited to assessment with data science methods. These methods include both classical curve/surface fitting methods, and modern machine learning (ML)-based approaches. However, there must be engineers “in the loop” at the development stage to ensure that models produce engineering quantities of interest. For example, models that automatically identify beam and girder elements, and generate plots of deformation, slope, curvature, or changes in these quantities over time. The proposed work seeks to provide a bridge from the raw data to engineering insights with easy-to-use software tools.]]></description>
      <pubDate>Tue, 02 Dec 2025 16:22:19 GMT</pubDate>
      <guid>https://rip.trb.org/View/2633315</guid>
    </item>
    <item>
      <title>AI-Driven Drone Technology for Bridge Displacement and Vibration Monitoring</title>
      <link>https://rip.trb.org/View/2633312</link>
      <description><![CDATA[This research proposes developing an autonomous drone system equipped with advanced artificial intelligence (AI) algorithms and dual-camera configurations for precise structural health monitoring. The system utilizes a dual-camera setup (telephoto and wide-angle) to enhance measurement precision, while stabilization techniques and calibration methods minimize errors caused by atmospheric interference and lighting variations. Designed to autonomously detect and analyze bridge vibrations and displacements in real time, the system addresses the limitations of traditional methods such as global positioning system (GPS), sensors, and vision-based approaches, which often struggle with large-scale structures, environmental interference, and stability challenges. Real-world testing on bridges and tall buildings will validate the system's effectiveness, ensuring its reliability for large-scale infrastructure monitoring. The deliverables include the drone-AI system, best practices for deployment, and data analysis protocols, providing a scalable solution for infrastructure monitoring.]]></description>
      <pubDate>Tue, 02 Dec 2025 16:06:43 GMT</pubDate>
      <guid>https://rip.trb.org/View/2633312</guid>
    </item>
    <item>
      <title>Damage Progression of Highway Bridges and Operational Vibration-Waveforms
</title>
      <link>https://rip.trb.org/View/2627353</link>
      <description><![CDATA[The dynamic response of civil structures has long been utilized in damage detection. Techniques such as vibration-based damage identification, usually focused on experimentally determining modal parameters, have shown promising applications in detecting damage on bridges. A major drawback of most current damage-detection techniques, including the current video-based approach using drones, is their inability to explain the cause or the condition under which certain types of damage occur at different locations on the bridge. In this work, a nondestructive vibration-based approach, operational response and waveform analysis (ORWA), will be used to determine a cause and possible prevention solutions to the local damage occurring on bridges. In ORWA, damage on a bridge is correlated to the structural motions that are generated by the operational crossing traffic. By identifying the type and speed of vehicles that can put the bridge in deformation modes that can cause detrimenttal damage when they cross the bridge, new mitigation, maintenance, and (potentially) traffic rules can be developed to reduce these effects. In a previous work supported by the Iowa Department of Transportation, the initial idea of ORWA was presented and tested on a single-span highway bridge. A modified form of ORWA was developed and used finite element analysis to correlate traffic vibration waveforms with the modal response of the bridge. In this work, ORWA will be enhanced to include a camera-based system that would be integrated and synched with the vibration waveform measurements. The newly developed ORWA will be tested and validated on two bridges in Iowa.

]]></description>
      <pubDate>Wed, 19 Nov 2025 14:42:07 GMT</pubDate>
      <guid>https://rip.trb.org/View/2627353</guid>
    </item>
    <item>
      <title>UAV-Imagery Based Track Component Health Condition Inspection</title>
      <link>https://rip.trb.org/View/2572335</link>
      <description><![CDATA[Railway fasteners and other small track components play an important role in keeping rails properly aligned and trains operating safely. However, these components can become worn, broken, loose, or missing over time. Current inspection practices often depend on people walking the track or using specialized inspection vehicles. These approaches can be time-consuming, costly, and difficult to perform frequently over long rail corridors. This project developed an AI-powered drone system that can help inspect railway track components more quickly, safely, and consistently.

The project created a new image database, called the Rail Components Dataset (RCD), using photographs collected at the Transportation Technology Center in Pueblo, Colorado. The dataset includes 2,100 high-resolution track images and more than 41,000 detailed labels identifying rails, ties, fasteners, and their conditions. This information was used to develop YG-Net, an AI tool that can identify track components, outline their locations in an image, and determine whether they appear normal or damaged. Instead of looking at each feature separately, the system considers the surrounding arrangement of rails, fasteners, and tie plates to make a more informed decision. This approach improved its ability to identify missing spikes, increasing the overall detection reliability from about 81% to 89%.

The inspection system was installed on a compact drone equipped with a camera and a small onboard computer. The onboard processing method was improved so that the system could analyze images much faster, increasing processing speed from about 13 images per second to nearly 55 images per second. Field testing showed that the drone could collect track images, analyze them during flight, identify components and potential defects, and send the results wirelessly to the ground station in real time.

The project demonstrates that drones, AI, and onboard computing can be combined into a practical tool to support railway inspections. The system can help agencies identify locations that need closer attention, reduce the need for time-consuming manual inspections, improve worker safety near active tracks, and support more proactive maintenance decisions.]]></description>
      <pubDate>Wed, 09 Jul 2025 16:04:48 GMT</pubDate>
      <guid>https://rip.trb.org/View/2572335</guid>
    </item>
  </channel>
</rss>