<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>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>A Benchmark Dataset and YOLO-Based Evaluation Framework for Vehicle Detection Before, During, and After Heavy Snow</title>
      <link>https://rip.trb.org/View/2742155</link>
      <description><![CDATA[Heavy snow substantially degrades the quality and reliability of vision-based traffic monitoring, yet most existing perception benchmarks focus on onboard driving datasets, mixed adverse-weather settings, or broad surveillance scenarios rather than fixed roadside CCTV imagery collected before, during, and after a snow event.

This project develops a public benchmark dataset and evaluation framework for vehicle detection using roadside CCTV camera imagery collected before, during, and after heavy snow events, along with an improved YOLO-based vehicle detection method to handle heavy snow conditions. The study targets a sensing setting that is highly relevant to transportation agencies but underrepresented in existing benchmarks: medium-resolution, street-level roadside cameras deployed for routine mobility, safety surveillance, and operational monitoring. It will synthesize the literature on adverse-weather detection, curate and manually annotate a fixed-camera dataset, develop YOLO-based detection pipelines, and rigorously compare out-of-the-box and retrained models across the three snow phases.

The project is expected to produce four primary outputs. First, a publicly available benchmark dataset of manually labeled roadside CCTV images spanning before-, during-, and after-snow conditions, drawn from open-source Maryland DOT traffic cameras and annotated with bounding boxes, class labels, and metadata such as timestamp, camera ID, and snow phase. Second, a rigorous benchmark evaluation quantifying how heavy snow and residual post-snow scene changes affect detection performance, compared across standard metrics including precision, recall, F1-score, and mAP. Third, a retrained YOLO-based model, incorporating snow-specific augmentation, phase-balanced sampling, and domain-adaptive fine-tuning, that improves robustness relative to the default baseline. Fourth, an open evaluation protocol and trained model weights released to support reproducible research.]]></description>
      <pubDate>Sat, 01 Aug 2026 10:40:59 GMT</pubDate>
      <guid>https://rip.trb.org/View/2742155</guid>
    </item>
    <item>
      <title>Using Artificial Intelligence-Based Computer Vision for Traffic Monitoring </title>
      <link>https://rip.trb.org/View/2736590</link>
      <description><![CDATA[The proposed research project would employ Artificial Intelligence (AI)-based Computer Vision to collect traffic data including vehicle count (traffic volume), Federal Highway Administration (FHWA) vehicle classification, and turning movements. Using video footage taken by existing roadside cameras (such as the Ohio Department of Transportation (ODOT)'s Milestone cameras) or other temporary cameras to collect traffic data allows for a safer and less expensive option compared with other methods. Computer Vision is an important AI application and using it to automatically collect traffic data will save significant amount of time and cost. This project epitomizes innovation as it will use cutting edge technologies to perform practical tasks while improving ODOT workers' and driving public's safety, reducing cost, and enhancing operational efficiency. 

A previous project conducted by the University of Toledo for ODOT Office of Technical Services developed a prototype tool that used AI-Computer Vision to collect vehicle count and classification data from recorded roadway videos. This research would investigate ways to more efficiently access videos from Milestone cameras and improve the previous work by developing a web-based traffic monitoring application, so that it can be used for routine traffic flow data collection. The outcome of this research will provide ODOT a safe, efficient, accurate, and economical alternative for collecting traffic data.

The overall goal of the project is to develop a safer method to collect accurate traffic data, while reducing costs and increasing operational efficiency.
                  ]]></description>
      <pubDate>Mon, 27 Jul 2026 13:57:59 GMT</pubDate>
      <guid>https://rip.trb.org/View/2736590</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>Artificial Intelligence for Pavement Condition Assessment from 2D/3D Surface Images</title>
      <link>https://rip.trb.org/View/2727389</link>
      <description><![CDATA[In phase I, the research team selected/annotated a library of two-dimensional/three-dimensional (2D/3D) pavement surface images in AASHTO standard and developed Artificial Intelligence (AI) Machine Learning (ML) models, using the established dataset. Phase I achieved a Technology Readiness Level (TRL) of 6, significantly below TRL 8 required for implementation. This gap was compounded by the lack of sufficient data for several pavement distress types and a new functional requirement requested by TxDOT to include distress segmentation to the scope of work. In phase II, the research team will prepare more pavement image data provided by TxDOT to achieve the needed diversity on all pavement distress types in the 2D/3D image data library. The research team will revisit the tasks of literature review and AI/ML model selection, revise and optimize the trained models to make improvements, and develop new models to more accurately detect/segment and quantify pavement distresses for TxDOT.]]></description>
      <pubDate>Fri, 10 Jul 2026 17:50:55 GMT</pubDate>
      <guid>https://rip.trb.org/View/2727389</guid>
    </item>
    <item>
      <title>Monitoring Active Transportation Demand and Safety with Computer Vision</title>
      <link>https://rip.trb.org/View/2696847</link>
      <description><![CDATA[Monitoring demand for and safety of active transportation has been a challenge for decades. With a history of designing roads for cars and monitoring efforts similarly aimed at the flow of cars, transportation researchers and professionals lack system-level knowledge of active transportation. The current state of bicycle and pedestrian counting practice in most cities deploys a few costly permanent counters using inductive loops and passive radar, combined with a few days of manual peak hour traffic counts at few intersections. This neither monitors system-wide demand nor safety. However, recently several companies have produced video- and LiDAR-based sensors and multiclass tracking technology to monitor active transportation demand and unsafe events. These sensors can be installed permanently, or temporarily, and are generally lower in cost to install than other permanent counting devices. This research will leverage an ongoing Caltrans project with these sensors to validate safety metrics, and a mobile version of the sensors to collect active transportation count data for modeling system level active transportation volume in Davis, California as a pilot for other cities and agencies. It will include the prediction of network-wide travel volumes for planning the intervention purposes, and two safety metric evaluations. The final report is expected to not only provide information on the state-of-the-art in active transportation monitoring, but will have direct policy impacts by informing the Active Transportation Data program within Caltrans Traffic Operations, among other programs such as the Active Transportation Resource Center research-to-practice education elements.]]></description>
      <pubDate>Tue, 28 Apr 2026 11:05:10 GMT</pubDate>
      <guid>https://rip.trb.org/View/2696847</guid>
    </item>
    <item>
      <title>ViewBridgeInEnvironments: A Holistic, Context-Aware Approach to Bridge
Assessment Using Computer Vision Segmentation Technologies</title>
      <link>https://rip.trb.org/View/2696156</link>
      <description><![CDATA[ViewBridgeInEnvironments introduces a pioneering framework that integrates environmental factors and contexts into bridge assessment, leveraging advanced panoptic segmentation technologies, while also incorporating the latest computer vision (CV) methods beyond segmentation. Traditional bridge inspections focus primarily on structural integrity, often overlooking the surrounding natural and manmade environments that can influence deterioration, accessibility, and safety. This framework addresses that gap by capturing comprehensive visual data from both bridge structures and their environments, enabling a holistic understanding of bridge health and the interactions between structural elements and surrounding conditions. By incorporating CV-based models, the framework produces interpretable outputs such as binary masks and quantified features, which support actionable decision making in bridge monitoring, maintenance, and management. The approach allows for simultaneous assessment of structural and environmental conditions, providing insight into potential vulnerabilities caused by adjacent terrain, vegetation, hydrological factors, and nearby infrastructure. Through these analyses, transportation agencies can identify risks, prioritize interventions, and allocate resources more effectively to enhance bridge safety and functionality. ViewBridgeInEnvironments is designed to leverage low-cost, widely accessible data collection technologies, including imagery from cell phones, cameras, and affordable drones, making it practical for both state-managed and locally owned bridges. The framework is scalable and adaptable, capable of being applied across diverse geographic regions and bridge types, including those in rural or hard-to access areas where traditional inspection is challenging. While erosion is one example of a feature that can be monitored, the framework is not limited to this, and the project will identify additional key features for comprehensive bridge assessment. By integrating structural evaluation with environmental context, ViewBridgeInEnvironments enables bridge owners and agencies to make timely, informed decisions, supporting resilient, safe, and sustainable infrastructure. The project represents a significant advancement in applying computer vision and panoptic segmentation to civil infrastructure, combining precision, environmental awareness, and practical deployment to enhance bridge monitoring and management.]]></description>
      <pubDate>Mon, 27 Apr 2026 19:52:59 GMT</pubDate>
      <guid>https://rip.trb.org/View/2696156</guid>
    </item>
    <item>
      <title>VISIAM (Visual Street Index for Active Mobility): An AI-Based Tool for Assessing Bikeability and Walkability of Streets</title>
      <link>https://rip.trb.org/View/2680127</link>
      <description><![CDATA[This project proposes the Visual Street Index for Active Mobility (VISIAM)—an AI-driven framework that integrates computer vision, self-supervised deep learning, and human-perception data to systematically assess bikeability and walkability at the street segment level. Current tools for assessing bikeability and walkability are limited because they rely on subjective audits or basic metrics. VISIAM addresses this gap through a multi-stage framework: computer vision models extract and classify streetscape features from Google Street View imagery, human-perception evaluations from diverse stakeholder groups rate street imagery across multiple dimensions, and the AI-derived classifications and human ratings are integrated to produce a composite bikeability and walkability score for each street segment. The final output is a citywide, street-level index visualized through interactive maps and dashboards, enabling policymakers to identify gaps, prioritize investments, and explore how infrastructure improvements could improve street quality.
]]></description>
      <pubDate>Wed, 11 Mar 2026 15:15:43 GMT</pubDate>
      <guid>https://rip.trb.org/View/2680127</guid>
    </item>
    <item>
      <title>Observational Intersection Traffic Safety Analysis</title>
      <link>https://rip.trb.org/View/2655705</link>
      <description><![CDATA[While planners and engineers design intersections with safety in mind, the intended use and actual use of facilities do not always align. This misalignment can lead to increased safety risks for all intersection participants, particularly non-motorized users including pedestrians and cyclists. Although facility utilization mismatches can be detected through observation, typical monitoring occurs only during limited peak hours, failing to fully capture comprehensive usage patterns and emerging safety concerns.

This research proposes long-term intersection monitoring to uncover emerging facility utilization patterns and assess inherent intersection safety. The approach leverages existing traffic camera infrastructure combined with modern deep learning techniques for accurate detection and tracking of vehicles, bicycles, and pedestrians. As an explicit use case, the study examines unprotected left-turns to characterize both vehicle-vehicle conflicts through time gap analysis and trajectory conflicts involving other road users. The project develops a computer vision system capable of processing trajectories to quantify left-turns with insufficient gaps, instances where vehicles fail to yield appropriately, and average time gaps, collectively providing metrics to characterize intersection safety.

This interdisciplinary project combines computer vision algorithm development expertise from the University of Nevada, Las Vegas (UNLV) with programming support from Howard University. System evaluation will occur at intersections in both the Washington, DC area and the Las Vegas metropolitan area, utilizing purpose-built high-resolution monitoring equipment for short-term deployment as well as existing lower-resolution traffic cameras for long-term analysis. The project leverages intersection equipment acquired through NSF Award Number 2216489.

Expected outcomes include research contributions in computer vision and machine learning for trajectory analysis, workforce development through student training across both institutions, and technology transfer through publications on intersection safety scoring and practitioner engagement for field deployment.]]></description>
      <pubDate>Mon, 19 Jan 2026 16:30:17 GMT</pubDate>
      <guid>https://rip.trb.org/View/2655705</guid>
    </item>
    <item>
      <title>Use of a Synthetic Vision Guidance System (SVGS) as a Category III (CAT III) Rollout Aid </title>
      <link>https://rip.trb.org/View/2646191</link>
      <description><![CDATA[A human-in-the-loop (HITL) simulation will be conducted to provide human factors data to aid in determining whether an Synthetic Vision Guidance System (SVGS) on a head-up display HUD, a head-down display (HDD), and/or both displays is an acceptable substitute for the visual references and flight guidance and control systems currently required to conduct manual Cagegory III (CAT III) Rollout (RO) operations. This research will examine the use of an SVGS throughout the entire CAT III flight operation (approach, landing, and RO), with a specific focus on the landing and RO, when an SVGS is used in lieu of a traditional fail-passive RO system, to determine if pilot performance, pilot workload, and crew coordination during landing and RO with an SVGS are comparable to existing levels during currently approved operations using a traditional fail-passive CAT III landing and RO system. While CAT III operations can also be conducted using other CAT III aircraft systems, such as fail-operational automatic landing and RO systems, or hybrid CAT III systems with fail-operational and fail-passive components, those systems and operational concepts are not within the scope of this research. Results from this research can inform safety risk management decisions and provide a basis to expand operational credit for SVGS technologies. The empirical data from this research can inform low visibility operation (LVO) policy and guidance decisions related to the use of an SVGS. These decisions may result in the authorization of lower CAT III minima for aircraft equipped with a fail-passive CAT III system at existing CAT III runways. This research may also expand LVO benefits to aircraft operators that have an SVGS but lack a fail-passive CAT III RO system.]]></description>
      <pubDate>Mon, 29 Dec 2025 12:31:10 GMT</pubDate>
      <guid>https://rip.trb.org/View/2646191</guid>
    </item>
    <item>
      <title>Safety and Operational Performance Assessment of CFIs and DDIs in Utah</title>
      <link>https://rip.trb.org/View/2632836</link>
      <description><![CDATA[This research project will assess the safety and operational performance of Continuous Flow Intersections (CFIs) and Diverging Diamond Interchanges (DDIs) in Utah. The study will develop Utah-specific Safety Performance Functions (SPFs), Crash Modification Factors (CMFs), and Adjustment Factors (AFs), using Utah Department of Transportation (UDOT) data resources and advanced analytical techniques including statistical modeling, machine learning, and computer vision. The findings will support updates to UDOT design guidelines and planning tools such as CAP-X, SPICE, and ICE.]]></description>
      <pubDate>Thu, 27 Nov 2025 08:54:32 GMT</pubDate>
      <guid>https://rip.trb.org/View/2632836</guid>
    </item>
    <item>
      <title>Enhancing Structural Safety and Promoting Equity in Infrastructure Maintenance through Human-Centered Bridge Inspection empowered by Artificial Intelligence and Augmented Reality
</title>
      <link>https://rip.trb.org/View/2627937</link>
      <description><![CDATA[Bridges are crucial civil infrastructure, but their deterioration over time poses significant safety risks. Traditional human visual inspections are limited in accuracy and efficiency, leading to challenges in maintaining the inventory of bridges in the United States, particularly in economically disadvantaged communities. Leveraging recent advancements in computer vision (CV), artificial intelligence (AI), and augmented reality (AR), the team proposes a novel human-centered approach to enhance the accuracy and efficiency of concrete bridge inspections and promote equity in infrastructure maintenance. By automating detection and documentation of damage in concrete bridges, and empowering human inspectors by overlaying real-time detection results onto bridges thereby enabling human-machine collaboration, the project aims to improve inspection effectiveness and efficiency, promote equity in infrastructure maintenance, and enhance public safety.
]]></description>
      <pubDate>Fri, 21 Nov 2025 14:16:23 GMT</pubDate>
      <guid>https://rip.trb.org/View/2627937</guid>
    </item>
    <item>
      <title>Are Automonous Vehicles Safer Drivers than Humans? Comparing performance in San Francisco</title>
      <link>https://rip.trb.org/View/2625584</link>
      <description><![CDATA[This research project seeks to determine if automated vehicles (AVs) are safer drivers than humans by comparing their pedestrian interaction behaviors and yielding performance in real-world conditions in San Francisco. The study will be framed by the city's "Focus on Five" strategy, which targets the five moving violations most commonly associated with traffic fatalities. Researchers will conduct evaluations of two focus violations, with the first being a comparison of the compliance of AVs and human drivers in yielding to pedestrians in a crosswalk. To gather data, the team will install high-resolution video cameras at two or more crosswalks with no traffic control for a period of one to three weeks to passively record vehicle-pedestrian interactions. Machine learning-based computer vision methods will then be used to automatically classify vehicles as either automated or human-driven. Following this classification, researchers will review the footage to code each interaction, noting if the vehicle yielded to the pedestrian. Finally, the performance of the two groups will be compared using two-sample t-tests to determine if any observed differences are statistically significant. A parallel analysis will be conducted for a second violation, to be determined.]]></description>
      <pubDate>Tue, 18 Nov 2025 15:14:24 GMT</pubDate>
      <guid>https://rip.trb.org/View/2625584</guid>
    </item>
    <item>
      <title>UAV-Imagery Based Track Component Health Condition Inspection</title>
      <link>https://rip.trb.org/View/2572335</link>
      <description><![CDATA[This project will develop a unmanned aerial vehicle (UAV)-imagery based intelligent track component health condition inspection system, that will utilize a camera and global positioning system (GPS) in a UAV integrated with edge computer device to identify missing and broken fasteners at the real-time speed. There are a considerable number of studies on the use of UAVs in track inspection. However, these studies utilize drones as a carrier of cameras and need human pilots to operate and control the drones. The collected images are stored onboard for a later analysis at some centralized facility. So, the current practices based on these studies has several drawbacks and limitations. Human pilot cost can be significant. Images collected by different pilots at the same track segment could vary and depend on the pilots’ operation skill, experience, and judgement. The inspection route is also subjective. The delay between data collection, data processing, and decision making depreciate the value of the inspections because track conditions can quickly deteriorate as traffic accumulates. To address these limitations, this project proposes a next generation UAV-imagery based track inspection system featuring advanced computer vision for real-time fattener defect defection and  efficient edge computing for field data processing. The advanced, embedded computer vision model will extract the features of various track components to evaluate their health conditions, such as missing or broken spikes, clips, rail surface detect, welding crack, broken ties. All inspected data will be immediately processed onboard for track condition assessment without the need for intensive data storage or transferring. The processed results will also be linked to the image-acquisition locations with the on-board GPS unit of the UAV. Both software and hardware are based on a modular and open-source design, which makes it compatible and transferable to other drone platforms, which to the best of the proposer’s knowledge is still unavailable in commercial or academic sectors. The proposed research consists of three modules: Module I --Training Image Library module; Module II -- Artificial Intelligence (AI)-based Track Component Detection module; and Module III -- Edge-computing system module. Module I will establish specialized drone-based track image database for convolutional neural network (CNN)-based computer vision model training. In Module II, a pixel-level detection system will be developed by using a tailored instance segmentation model to detect track components in a fast and accurate fashion. In Module III, to enable in-situ image analysis and AI inference, an appropriate mobile edge-computing platform and integration strategy will be developed. The proposed system will significantly reduce inspection cost and derailment risk, optimize maintenance strategy, and improve track safety. It will also greatly reduce the workload and improve the work conditions for the track inspectors because the system will automatically process the images and record the detected defects and access the track where it is hard to reach for the inspectors.]]></description>
      <pubDate>Wed, 09 Jul 2025 16:04:48 GMT</pubDate>
      <guid>https://rip.trb.org/View/2572335</guid>
    </item>
    <item>
      <title>Statewide augmented information in the driver environment study</title>
      <link>https://rip.trb.org/View/2570738</link>
      <description><![CDATA[The purpose of this project is to increase lifelong independence and safe vehicle operation by improving access to environmental information while driving, particularly among older adults and people with visual impairments. By simulating a new framework for computer-vision assisted augmented reality (CVAR) in the driving environment, the research team intends to study how augmenting roadway elements (e.g., lines on the road, lane markers, and obstructions) improves overall operational performance. It is predicted that the universal design approach used in this work will not only substantially benefit older adult drivers but will also benefit all drivers. This is because the University of Maine (UMaine) CVAR solution can be used to improve access to roadway elements during situations of reduced visibility (e.g., at night or during inclement weather) while also highlighting an eventual suite of potential hazards (e.g., downed limbs, wildlife, and pedestrians).  

The work will expand UMaine's Virtual Environments and Multimodal Interaction Laboratory (VEMI Lab)’s current autonomous vehicle simulator (MOISIN: Multimodal Omnidirectional Immersive Simulator for Inclusive Navigation) to include a manual driving operational mode. Related software will also be developed to simulate new inclusive CVAR approaches that combine multisensory feedback with augmented visual information to expand access to a wide range of potential drivers. The resulting UIs will be tested in a series of user studies examining the impact on driving performance across various driving scenarios.]]></description>
      <pubDate>Wed, 02 Jul 2025 13:53:38 GMT</pubDate>
      <guid>https://rip.trb.org/View/2570738</guid>
    </item>
  </channel>
</rss>