<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>Evaluating Real-World Multi-View Vulnerabilities in Autonomous Driving Perception and Planning for Improved Safety and Regulation</title>
      <link>https://rip.trb.org/View/2742144</link>
      <description><![CDATA[Autonomous driving systems (ADS) increasingly rely on vision-based perception and learning-based decision modules, yet real-world safety depends on whether these systems remain stable as the ego vehicle continuously changes distance and viewpoint relative to roadway objects. Current evaluation practices often emphasize single images or limited viewpoints, which can mask trajectory-dependent failure modes that emerge during real driving under changing illumination, partial occlusion, and motion blur.

This project studies the limitations of existing ADS through a measurement-driven, multi-view robustness evaluation framework designed to produce actionable engineering insights and evidence-based inputs for transportation safety policy. Building on a differentiable, view-consistent scene representation (3D Gaussian Splatting with view-dependent appearance modeling), the team will generate controlled, physically plausible appearance variations across realistic approach trajectories and use them as a diagnostic tool to quantify perception instability and downstream planning sensitivity.

The project will deliver a reproducible set of safety-relevant scenarios and ego-vehicle approach trajectories representing how a vehicle observes the same object over time; a controllable multi-view rendering and perturbation engine built on 3D Gaussian Splatting that synthesizes viewpoint-consistent observations under bounded, physically plausible appearance variations; and a multi-view robustness evaluation methodology and benchmark protocol using trajectory-based sampling. It will produce quantitative robustness indicators summarizing perception stability and planning sensitivity, a structured taxonomy of observed failure modes, and a reproducible reporting package of metrics definitions, evaluation scripts, and documentation templates. Validation will be performed on representative research ADS models, with black-box evaluation of commercial systems where feasible and safe.]]></description>
      <pubDate>Sat, 01 Aug 2026 10:27:03 GMT</pubDate>
      <guid>https://rip.trb.org/View/2742144</guid>
    </item>
    <item>
      <title>GenAI-Enabled Automated Traffic Simulation Management</title>
      <link>https://rip.trb.org/View/2742141</link>
      <description><![CDATA[Microscopic traffic simulation software allows users to model traffic flow, assess traffic management strategies, and optimize transportation systems for efficiency. However, building a simulation model for a real-world road network is a complex, manual, time-consuming, and error-prone task. GenAI-Enabled Automated Traffic Simulation Management uses Generative Artificial Intelligence (AI) (GenAI) to automate the preparation of input data, the running of simulations, and the extraction of output results, enabling traffic engineers to focus on the purpose of the simulation rather than the tedious manual work of building the model.

The project maps user text-based scenario descriptions to actual simulation scenarios, with step-by-step validation from the user before execution, by wrapping the INTEGRATION simulation software with a callable API via the Model Context Protocol (MCP) and a web-based interface to a large language model (LLM).

The project will deliver a baseline simulation model built with the INTEGRATION microscopic simulation software for a selected freeway corridor or road network; an INTEGRATION API that wraps the simulation software using the Model Context Protocol so it can be called by any large language model; and a web-based graphical user interface that guides users in prompting an LLM to build simulation models and answer questions using Retrieval-Augmented Generation from the INTEGRATION manual. The GenAI system will be validated by comparing GenAI-generated model files against the baseline model, through human-in-the-loop validation, and through real-world deployment with the City of Alexandria.]]></description>
      <pubDate>Sat, 01 Aug 2026 09:48:00 GMT</pubDate>
      <guid>https://rip.trb.org/View/2742141</guid>
    </item>
    <item>
      <title>Risk-Based and Cost-Effective Agency Verification of Contractor-Collected Pavement and Bridge Profiles</title>
      <link>https://rip.trb.org/View/2712193</link>
      <description><![CDATA[State departments of transportation (DOTs) recognize that pavement and bridge smoothness is a key indicator of performance and public satisfaction. As state DOT staffing levels have declined, contractors have become increasingly responsible for collecting profile data, calculating smoothness indices, and sometimes determining pay factors. While federal regulations require independent verification of contractor data used for acceptance decisions, agencies remain uncertain about the level of verification needed to ensure accuracy and judicious allocation of public funds.

Current practices for validation and verification vary widely across state DOTs. Some agencies collect independent profiles on a subset of projects, while others rely on partial sampling, comparisons with contractor data, or limited review processes. The statistical reliability and risk implications of these approaches are not well understood. Additionally, advances in data collection technologies, such as high-speed profilers, have increased the volume of data, challenging traditional verification approaches. There is a need for research that helps state DOTs accurately determine pavement life through the potential use of emerging technologies and improved verification of contractor-collected pavement and bridge profile data.

The objective of this research is to develop a guide and supporting tool to assist state DOTs in conducting cost-effective, risk-based verification of contractor-collected pavement and bridge profiles.]]></description>
      <pubDate>Tue, 09 Jun 2026 17:10:07 GMT</pubDate>
      <guid>https://rip.trb.org/View/2712193</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>Statistical Evaluation of Illinois Modified AASHTO T161 Freeze–Thaw Testing Following Laboratory Relocation</title>
      <link>https://rip.trb.org/View/2686616</link>
      <description><![CDATA[A critical way to build high-performing pavements and bridges is to evaluate a mixture’s freeze-thaw performance in the lab to ensure it meets performance parameters. The aim of this project is to calibrate and validate new equipment for freeze-thaw testing at the Illinois Department of Transportation’s (IDOT's) Central Bureau of Materials. Researchers will test aggregate samples using IDOT’s new and existing freeze-thaw equipment, ensuring the new equipment produces consistent and replicable results. They will also create calibration guidelines that will help to establish a repeatable framework when replacing future freeze-thaw testing equipment.]]></description>
      <pubDate>Wed, 01 Apr 2026 09:41:33 GMT</pubDate>
      <guid>https://rip.trb.org/View/2686616</guid>
    </item>
    <item>
      <title>Aviation Infectious Risk and Safety: Dissemination and benchmarking of human motion for disease modeling</title>
      <link>https://rip.trb.org/View/2675923</link>
      <description><![CDATA[The research will strengthen the agent-based movement component of the TRIP-X communicable disease transmission model through structured benchmarking against publicly available modeling approaches and dissemination of previously collected human behavior datasets. Benchmarking will compare model performance to identify strengths, limitations, and opportunities for model refinement. Human behavior datasets developed under a related project (Communicable disease preparedness: M&S framework for analyzing cabin health hazards) will be prepared for public dissemination to encourage independent replication, facilitate peer review, and support broader adoption by government, industry, and academic researchers. Results will be documented in publications and used to improve confidence in the TRIP-X modeling framework for potential future FAA SRM applications. ]]></description>
      <pubDate>Mon, 02 Mar 2026 10:19:24 GMT</pubDate>
      <guid>https://rip.trb.org/View/2675923</guid>
    </item>
    <item>
      <title>Using Large Language Models to Generate Synthetic Data for Proactive
Pedestrian Safety Prediction: Overcoming Data Collection Barriers in Surrogate Safety Analysis</title>
      <link>https://rip.trb.org/View/2663604</link>
      <description><![CDATA[Pedestrian fatalities remain a persistent and growing safety crisis, with over 7,500 pedestrians killed on U.S. roads annually. Effective countermeasure deployment requires identifying high-risk locations before crashes occur, yet traditional crash-based analyses are insufficient due to the rarity of pedestrian crashes at individual intersections. Surrogate safety analysis using pedestrian–vehicle close calls offer a proactive alternative, but comprehensive observational data collection is prohibitively expensive and time-intensive. Video monitoring requires specialized equipment, extended deployment periods, and substantial manual processing. These practical constraints severely limit the geographic coverage, temporal scope, and contextual diversity of available datasets, ultimately hindering agencies' ability to develop reliable predictive tools that generalize across diverse intersection types and support evidence-based
safety interventions statewide. This project addresses these fundamental challenges by introducing Large Language Models (LLMs) as a novel tool to generate high-quality synthetic pedestrian–vehicle interaction data. LLMs possess extensive pre-trained knowledge spanning transportation systems, human behavior, and urban
environments, successfully demonstrated in healthcare and climate science for data augmentation. Building upon the Minnesota Traffic Observatory (MTO) dataset, where 18 intersections with 3,314 interactions involving 4,941 pedestrians, the research team will develop a validated methodology to generate contextually realistic scenarios incorporating roadway geometry, traffic control, land use, pedestrian demographics, and temporal patterns. This approach directly tackles the data scarcity problem that prevents agencies from conducting comprehensive pedestrian safety analyses across their jurisdictions.
The project has three objectives: (1) develop a transparent LLM-based synthetic transportation-targeted data generation methodology with validation protocols ensuring realism and quality; (2) evaluate whether synthetic data-augmented models improve prediction accuracy and transferability across intersections compared to observational data alone, using precision-recall AUC, calibration diagnostics, leave-one-site-out validation and other appropriate approaches; and (3) determine the mechanisms driving performance improvements: whether from introducing realistic scenario diversity or addressing rare-event limitations, to guide best practices. The framework will incorporate probability calibration, split-conformal risk control, and decision-curve analysis to deliver deployment-ready tools with quantified uncertainty for operational use.]]></description>
      <pubDate>Tue, 03 Feb 2026 15:34:23 GMT</pubDate>
      <guid>https://rip.trb.org/View/2663604</guid>
    </item>
    <item>
      <title>Accelerating IFC Adoption by Advancing IFC Validation Service and Software Certification Program</title>
      <link>https://rip.trb.org/View/2652044</link>
      <description><![CDATA[This proposed Pooled Fund Study would look at the viability and best means to significantly enhance the scale and maturity of services (i.e., IFC Validation Service and Global IFC Software Certification), as well as recommend any additional technical and procedural efforts (such as Use Case-based Certification), needed to support software implementation and United States industry adoption and deployment. The following two primary business objectives would be achieved: Enabling state departments of transportation (DOTs) to specify certified (IFC and US industry standard exchange requirement compliant) software for road and bridge projects; Enabling state DOTs to validate deliverables from consultants and contractors to enhance project delivery and management quality. This work would be separate but complimentary to the ongoing work of TPF-5(523) BIM for Bridges & Structures Pooled Fund and TPF-5(480) BIM for Infrastructure Pooled Fund.]]></description>
      <pubDate>Sat, 10 Jan 2026 11:59:41 GMT</pubDate>
      <guid>https://rip.trb.org/View/2652044</guid>
    </item>
    <item>
      <title>Aeromedical HFACS Nanocode Review and Validation</title>
      <link>https://rip.trb.org/View/2646975</link>
      <description><![CDATA[The Office of Aerospace Medicine (AAM) has developed a specialized Human Factors Analysis and Classification System (HFACS) nanocode framework designed to systematically capture medical contributors to aviation accidents. This innovative taxonomy aims to link latent or undetected pilot health issues to unsafe acts and broader systemic oversight deficiencies, thereby enhancing the Federal Aviation Administration's (FAA’s) ability to understand and mitigate medically related accident risks. However, before this framework can be operationalized within FAA safety programs, it requires rigorous, independent validation to ensure its reliability, usability, and overall effectiveness in real-world applications. The core objective of this research is to evaluate whether the nanocode system accurately identifies causal medical factors in aviation accidents and supports improved aeromedical decision-making. To achieve this, the study will address key questions: How consistently can trained analysts apply the nanocode framework to actual accident cases? Does the framework clearly capture essential medical and supervisory contributors to unsafe acts? And, what refinements are necessary to enhance its clarity, usability, and integration with other FAA safety analysis systems? The answers to these questions will determine the readiness of the framework for widespread implementation and inform future training, oversight protocols, and policy guidance within the FAA’s aeromedical and safety assurance ecosystems.]]></description>
      <pubDate>Thu, 08 Jan 2026 08:56:35 GMT</pubDate>
      <guid>https://rip.trb.org/View/2646975</guid>
    </item>
    <item>
      <title>Safe and Personalized Control of Autonomous Vehicles with On-Board Vision Language
Models: System Design and Real-World Validation
</title>
      <link>https://rip.trb.org/View/2625313</link>
      <description><![CDATA[This project focuses on enhancing autonomous vehicle control systems by integrating on-board Vision-Language Models (VLMs) for safe and personalized driving experiences. Building on the previously awarded Center for Connected and Automated Transportation
(CCAT) project on “CAV Pilot Development and Deployment in Midwest Winter,” this research addresses critical challenges in autonomous vehicle development regarding limited on-board computational resources by implementing lightweight VLM frameworks and Retrieval-Augmented Generation (RAG)-based memory modules. The project will validate the system’s ability to handle challenging urban scenarios, reduce human takeover rates, and adapt to diverse environmental conditions.
]]></description>
      <pubDate>Thu, 13 Nov 2025 15:43:04 GMT</pubDate>
      <guid>https://rip.trb.org/View/2625313</guid>
    </item>
    <item>
      <title>Enhancing Flexible Pavement System 23 (FPS23) by Incorporating a Top-Down Cracking Model in Texas Mechanistic-Empirical Flexible Pavement Design System (TxME)</title>
      <link>https://rip.trb.org/View/2604524</link>
      <description><![CDATA[Several Texas Department of Transportation (TxDOT) districts have reported early top-down cracking issues linked to the use of Reclaimed Asphalt Pavement (RAP) materials, which can make the surface layer excessively stiff. Unlike bottom-up fatigue cracking—where distress originates at the bottom of the hot mix asphalt (HMA) layer—top-down cracking begins at the surface and propagates downward. While bottom-up fatigue cracking and the negative effects of RAP in lower asphalt layers have been well addressed, top-down cracking remains unaccounted for in Texas Mechanistic-Empirical Flexible Pavement Design System (TxME). As a result, premature top-down cracking cannot currently be predicted at the design stage. With growing economic and environmental incentives for RAP use—and current specifications allowing it in surface layers—integrating a top-down cracking model into FPS23/TxME is essential to assess its impact properly. The research team will: (1) Evaluate and develop an appropriate mechanistic-empirical (ME) top-down cracking model, (2) Implement it in TxME, and (3) Calibrate/validate the model. The research team will review the literature, identify the ME model, integrate it into TxME, and collect test section data—including mixture properties, structure, and field performance—for calibration and validation.]]></description>
      <pubDate>Mon, 29 Sep 2025 16:12:23 GMT</pubDate>
      <guid>https://rip.trb.org/View/2604524</guid>
    </item>
    <item>
      <title>Validation of HSM Crash Prediction Methods for Specific Intersection Types in Oregon</title>
      <link>https://rip.trb.org/View/2593954</link>
      <description><![CDATA[The Highway Safety Manual (HSM) is the national guidance of quantitative safety analysis used in highway transportation planning, alternatives development, highway design, operations, and maintenance. However, some crash prediction models and crash modification factors in the Highway Safety Manual were developed using data from other states, not Oregon. Therefore, it is necessary to validate these models and crash modification factors for the implementation in Oregon.
Recently the National Cooperative Highway Research Program (NCHRP) project 17-68 “Intersection Crash Prediction Methods for the Highway Safety Manual” has developed crash prediction models of more intersection types for inclusion in the HSM. The types of intersections include all-way stop control, three-leg intersections with signal control on rural highways, intersections on high-speed urban and suburban arterials, five-leg intersections, etc. Currently, there is no guideline for how to use these new crash prediction models particularly in Oregon. It is necessary to validate these models and crash modification factors in Oregon to guide the statewide implementation.
This research proposes to focus on intersections on urban and suburban arterials, which are common intersection types.]]></description>
      <pubDate>Thu, 28 Aug 2025 12:53:55 GMT</pubDate>
      <guid>https://rip.trb.org/View/2593954</guid>
    </item>
    <item>
      <title>KYTC Geotechnical Data 
Transition Support and 
Application Development</title>
      <link>https://rip.trb.org/View/2593940</link>
      <description><![CDATA[With the planned discontinuation of gINT, the Kentucky Transportation Cabinet (KYTC) must transition to a new geotechnical data management system. This project will facilitate that transition by ensuring geotechnical data can be accurately transferred, validated, and integrated across existing and proposed systems. Researchers will investigate current geotechnical data transfer protocols and data validation tools before developing Cabinet-specific tools that can maintain data quality and enable efficient data sharing within the agency and with external partners.]]></description>
      <pubDate>Thu, 28 Aug 2025 11:32:34 GMT</pubDate>
      <guid>https://rip.trb.org/View/2593940</guid>
    </item>
    <item>
      <title>Balance Mix Design Data 
Validation</title>
      <link>https://rip.trb.org/View/2593939</link>
      <description><![CDATA[Balanced mix design (BMD) focuses on optimizing an asphalt mixture’s cracking and rutting performance rather than relying on traditional volumetric properties in its formulation. Over the past five years, Kentucky Transportation Cabinet (KYTC) asphalt contractors have implemented BMD practices. However, no research has looked at the relationship between asphalt performance test results submitted by contractors and the real-world performance of asphalt mixtures.]]></description>
      <pubDate>Thu, 28 Aug 2025 11:32:34 GMT</pubDate>
      <guid>https://rip.trb.org/View/2593939</guid>
    </item>
    <item>
      <title>Evaluating and Implementing Ground Penetrating Radar (GPR) for Continuous and Rapid Monitoring of Moisture Fluctuations in In-Service Roads</title>
      <link>https://rip.trb.org/View/2487309</link>
      <description><![CDATA[Traditional methods for measuring pavement moisture, including in-place sensors and indirect assessments like FWD, can be costly, invasive, slow, offer limited spatial coverage, and disrupt traffic. In contrast, ground penetrating radar (GPR) offers a non-invasive, portable solution for swiftly evaluating extensive road segments, detecting subsurface moisture levels with reasonable cost, thereby supporting local road authorities in promptly assessing moisture conditions in critical pavement areas. The aim of this research study is to advance the validation and implementation of GPR-based pavement moisture assessments on actual low-volume roads.]]></description>
      <pubDate>Fri, 18 Jul 2025 09:49:56 GMT</pubDate>
      <guid>https://rip.trb.org/View/2487309</guid>
    </item>
  </channel>
</rss>