<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>Implementing an Advanced Open-Source Activity Based Travel Demand Model to Support Rural Transportation Planning and Policy Decisions</title>
      <link>https://rip.trb.org/View/2692312</link>
      <description><![CDATA[Travel demand models (TDMs) are used to support state and regional transportation planning and policy decisions. TDMs were originally developed to forecast passenger traffic volumes with the primary objective of identifying investments to reduce traffic congestion. Today, TDMs are used to support a much broader range of purposes, including multimodal and freight transportation planning, demand management strategies, forecasting accessibility outcomes, evaluating network resiliency to disasters, and modeling air quality and public health impacts. However, the aggregate, trip based TDMs used by most regional and state transportation agencies lack the fidelity and sensitivity to evaluate contemporary planning and policy decisions. Activity based travel demand models (ABMs) offer substantial improvements and their agent-based simulation platforms allow for integration with a wide range of other agent-based modeling including land use simulation, vehicle adoption, population growth simulation models among others. Despite their advantages, the complexity of ABMs has constrained their adoption to all but the largest metropolitan areas, often with support from academic researchers. Smaller urban areas and rural states like Vermont could benefit substantially from adopting ABMs. The goal of this project is to implement an open source and/or free for public use ABM in Vermont. Several ABMs meeting these criteria have been developed by US Department of Energy labs. This project will implement a modeling platform that University of Vermont can use in partnership with regional and state stakeholders to advance rural transportation planning and policy research; perform a case study to demonstrate the unique capabilities of ABMs to inform current transportation policy debates in Vermont; identify implementation barriers; and identify future research directions to address implementation barriers to enable wider ABM adoption outside of large urban areas.]]></description>
      <pubDate>Tue, 14 Apr 2026 12:09:54 GMT</pubDate>
      <guid>https://rip.trb.org/View/2692312</guid>
    </item>
    <item>
      <title>Implementing an Advanced Open-Source Activity Based Travel Demand Model to Support Rural Transportation Planning and Policy Decisions: Phase 2 – Calibration</title>
      <link>https://rip.trb.org/View/2691726</link>
      <description><![CDATA[Travel demand models (TDMs) are used to support state and regional transportation planning and policy decisions. TDMs were originally developed to forecast passenger traffic volumes with the primary objective of identifying investments to reduce traffic congestion. Today, TDMs are used to support a much broader range of purposes, including multimodal and freight transportation planning, demand management strategies, forecasting transportation access outcomes, evaluating network resiliency to disasters, and modeling air quality and public health impacts. However, the aggregate, trip based TDMs used by most regional and state transportation agencies lack the fidelity and sensitivity to evaluate contemporary planning and policy decisions. Activity based travel demand models (ABMs) offer substantial improvements and their agent-based simulation platforms allow for integration with agent-based population growth and land use simulation tools, among others. Despite their advantages, the complexity of ABMs has constrained their adoption to all but the largest metropolitan areas, often with support from academic researchers. Smaller urban areas and rural states like Vermont could benefit substantially from adopting ABMs. The goal of this project is to continue current National Center for Sustainable Transportation (NCST)-funded work on implementing a statewide ABM in Vermont using the POLARIS modeling system developed by Argonne National Lab. The current project is focused on initial model setup and testing. This Phase 2 project will focus on calibration and validation. The expected outcome is a calibrated implementation of the POLARIS modeling system for the state of Vermont that can be used for the evaluation of statewide and regional transportation planning and policy decisions and to advance research on rural transportation challenges.]]></description>
      <pubDate>Sun, 12 Apr 2026 23:58:15 GMT</pubDate>
      <guid>https://rip.trb.org/View/2691726</guid>
    </item>
    <item>
      <title>The San José's Mobility Credit Pilot: A Delayed Randomized Control Trial Evaluation</title>
      <link>https://rip.trb.org/View/2691659</link>
      <description><![CDATA[The San Jose Mobility Credit pilot (MCP) tests a new approach that allows individuals the freedom to travel when, where, and how they want to go. The pilot provides MCs that enable individuals to maximize travel while minimizing costs. Interest in these programs is growing throughout the U.S. The research team has experience evaluating similar programs in the U.S. The project will include a delayed longitudinal randomized control trial (RCT) to evaluate the MCP. The design of the 18-month MCP in-person participant recruitment, training, and support by the City of San Jose will support high participation and survey response rates. The study will be the first to use a delayed RCT design with a difference-in-differences (DID) statistical analysis to evaluate an MCP. In general, RCTs are rarely used to test the effectiveness of transportation projects and policies. The proposed study will evaluate the effects of the MCP, not only on individuals’ overall travel freedom, but also on transportation security (e.g., travel speed, time, and reliability), community participation (e.g., church, family, school, and volunteer activities), employment, education, and overall health (which could lead savings in health care costs). Few studies have evaluated the significance of transportation access interventions on these measures. The longer duration of the MCP may allow for a better assessment of evaluation measures. The MCP evaluation will be one of few studies that examine the causal effects (randomized control trial with difference-in-differences analysis) of a transportation intervention on multiple evaluation measures.]]></description>
      <pubDate>Sun, 12 Apr 2026 23:10:13 GMT</pubDate>
      <guid>https://rip.trb.org/View/2691659</guid>
    </item>
    <item>
      <title>Scaling Shared Autonomous Vehicle Services: Adoption, Demand, and System Implications</title>
      <link>https://rip.trb.org/View/2691658</link>
      <description><![CDATA[Autonomous vehicle (AV) operations are expanding across major U.S. cities, prompting public agencies and industry stakeholders to consider how shared AV services should be deployed, scaled, and integrated into existing transportation systems. Shared AVs have the potential to serve a wide range of travelers, including individuals who currently drive but may choose to use AVs occasionally, those seeking alternative travel options that allow more productive use of travel time, and travelers who may not consistently rely on a private vehicle for day-to-day transportation. Despite growing deployment, empirical evidence remains limited on how shared AV services will be adopted across regions, travel needs, and service contexts, and how their expansion can be guided to align with observed demand and system performance goals. Most prior AV studies were conducted before widespread deployment and relied on respondents with little to no direct exposure to AV services. As AV operations expand, more individuals are encountering these vehicles firsthand as passengers, road users, or through broader media exposure, creating a timely opportunity to reassess their implications for travel behavior and system-level outcomes. This transition from limited testing to sustained operations highlights the need for updated evidence that reflects current deployment conditions and real-world exposure. This study will generate policy-relevant evidence to support informed shared AV deployment by examining adoption expectations, anticipated use by trip purpose, and geographic variation across urban, suburban, and rural areas. Using data from the UC Davis Mobility Panel Survey and a targeted convenience sample from regions with active AV operations, researchers will analyze anticipated shared AV use for commuting, shopping, escorting, and healthcare travel. The project will also assess how service attributes such as pricing, wait times, and availability influence adoption and demand across various geographic contexts. By identifying where shared AV services are most likely to complement existing transportation services, the study will provide actionable guidance on deployment strategies, service design, and policy considerations, supporting policymakers and industry stakeholders in evaluating scaling pathways and system impacts as services expand.]]></description>
      <pubDate>Sun, 12 Apr 2026 23:06:23 GMT</pubDate>
      <guid>https://rip.trb.org/View/2691658</guid>
    </item>
    <item>
      <title>Assessing the Reliability and Usability of Mobile Ticketing App Data for Transit Analytics: A Case Study of Unitrans in Davis, California</title>
      <link>https://rip.trb.org/View/2690984</link>
      <description><![CDATA[Mobile ticketing apps have become increasingly popular among transit agencies due to their cost efficiency and ability to streamline payments. Beyond operational efficiencies, these apps also generate vast travel data with the potential to support transit agencies in decision-making. However, this data contains incomplete trip information and suffers from representation bias. Several questions remain unanswered: Is this data a statistically representative sample of all transit riders? What are its potential applications? This research will address this gap by evaluating the potential applications and representativeness of app data. The project focuses on ZipPass, a mobile ticketing app used by Unitrans in Davis, California. Within six months of launch, ZipPass has already generated over 350,000 spatial activation records. Researchers devised a strategy to integrate ZipPass data with the onboard transit survey and the UC Davis campus travel survey. They also plan to conduct a targeted survey of active ZipPass users to supplement rider-specific and trip-level information. The team will explore how ZipPass data, along with support from supplementary data sources, can be used for two potential applications to support the agency: (1) estimating transit ridership and (2) understanding riders' origin-destinations. This research will study the reliability and usability of mobile ticketing app data for transit analytics by assessing its quality after augmenting the data with other existing resources to increase contextual information. The research will provide valuable insights to transit agencies looking to harness mobile ticketing data for operational purposes. Since periodic onboard transit surveys are required for federal funding, both mobile ticketing data and transit survey data are available to agencies at no extra expense. Small agencies can leverage our findings to integrate at least these two datasets and effectively utilize them for operational improvement. The project will create a framework for them to integrate mobile ticketing data with periodic transit surveys to support their transit planning and decision-making. While Unitrans serves as our primary case study, the research is designed to be applicable and scalable to transit agencies nationwide.]]></description>
      <pubDate>Thu, 09 Apr 2026 14:29:48 GMT</pubDate>
      <guid>https://rip.trb.org/View/2690984</guid>
    </item>
    <item>
      <title>Utility of Improving Nonmotorized Volume Forecasts for Bike Infrastructure</title>
      <link>https://rip.trb.org/View/2681257</link>
      <description><![CDATA[Virginia Department of Transportation (VDOT) lacks clarity on several foundational questions for bicycle and pedestrian demand forecasting: (1) the accuracy of the current forecasting method(s), (2) the full range of decisions that would benefit from more precise demand estimates, (3) the availability and reliability of existing bicycle and pedestrian count data, and (4) whether a more advanced forecasting method could be effectively adapted for Virginia. Given these four unknowns and the anticipated large expense of a Virginia-specific model, it is unclear whether VDOT should spend substantial time and resources creating a better approach for estimating nonmotorized demand. Through a literature review, survey and potentially follow-up interviews, assessment of alternative methods, evaluation of existing count data, and data analysis to evaluate the utility of improving forecasts, this research will determine if VDOT should develop a better method or continue the current approach.  ]]></description>
      <pubDate>Tue, 17 Mar 2026 09:48:42 GMT</pubDate>
      <guid>https://rip.trb.org/View/2681257</guid>
    </item>
    <item>
      <title>Evaluating Fuzzed Connected Vehicle Data to Support Travel Demand Modeling </title>
      <link>https://rip.trb.org/View/2663276</link>
      <description><![CDATA[Virginia Department of Transportation (VDOT) is currently developing a method to use connected vehicle (CV) data to support the development of travel demand models. The work includes estimating nuanced information about trip time, trip distance, and path patterns with fine geographic and temporal resolution. Recently, CV trajectory data providers in the U.S. started to “fuzz” the raw vehicle trajectory data for privacy reasons. These data-fuzzing algorithms may affect the feasibility, accuracy, and robustness of VDOT’s application of CV data for planning purposes. This project assesses the impact of data fuzzing algorithms used by two different CV trajectory data providers, Streetlight and Compass IoT, on potential VDOT application scenarios related to calibration and validation of transportation planning models. This research will further assess the potential of using Compass IoT data to support the development of truck ODs, and if feasible, a valuable enhancement to the current VDOT truck origin-destination (OD) estimation procedure]]></description>
      <pubDate>Sun, 01 Feb 2026 11:00:46 GMT</pubDate>
      <guid>https://rip.trb.org/View/2663276</guid>
    </item>
    <item>
      <title>Strategic Approaches to Managing Emerging Transportation Infrastructure Assets Through Public-Private Partnership</title>
      <link>https://rip.trb.org/View/2658058</link>
      <description><![CDATA[Oklahoma is currently undergoing major transportation infrastructure network expansions statewide yet faces unique challenges especially in low population regions with insufficient travel demand and questions of economic viability. This project aims to develop a business case for the management of emerging transportation infrastructure assets for different regions in Oklahoma by analyzing best practices from other states, assessing the interdependence between infrastructure assets and travel demand, and evaluating innovative funding and partnership models. The project will focus on charging infrastructure for alternative fuel vehicles as the use case. The research will identify strategies to reduce long-term maintenance cost, increase technology adoption, and prioritize locations for infrastructure expansions based on short-range and long-term community needs and economic impacts. Key tasks include a (1) comprehensive literature review and policy benchmarking, (2) vulnerability, interdependency, and accessibility analysis, (3) key stakeholder engagement, (4) economic and technical feasibility analysis, (5) development of asset management strategies and implementable guidelines for Oklahoma DOT and its partners. The anticipated outcomes include actionable recommendations to support the long-term financial viability of transportation infrastructure asset management, promote access, and foster economic growth in different communities. Overall, the proposed research will analyze the economic feasibility of emerging transportation infrastructure asset management strategies through cost-benefit assessments and investment justifications, strengthening the case for federal and private funding. Its alignment with national priorities and ODOT’s goals ensures the findings are both timely and impactful. Based on the results, ODOT may need to revise Oklahoma’s Transportation Asset Management (2022-2031) and Long Range Transportation (2022-2031) plans to incorporate updated guidelines on financial viability, location priorities, and infrastructure life cycle management. Implementing these changes before future expansions will improve efficiency and ensure smoother project delivery. The results will directly contribute to the state’s mission of building a safer, more reliable, and efficient transportation system.  ]]></description>
      <pubDate>Fri, 23 Jan 2026 13:43:13 GMT</pubDate>
      <guid>https://rip.trb.org/View/2658058</guid>
    </item>
    <item>
      <title>Evaluate Speed Estimation Techniques for EPA Moves Model Input Using Big Data and Travel Demand Models for Regional Conformity Analysis</title>
      <link>https://rip.trb.org/View/2562324</link>
      <description><![CDATA[Michigan Department of Transportation's (MDOT’s) Statewide and Urban Travel Analysis (SUTA) Section is required to run the Environmental Protection Agency’s (EPA) MOtor
Vehicle Emission Simulator (MOVES) Model for regional transportation conformity analysis, and for other purposes. One crucial input
to the MOVES model is an average speed distribution configured into sixteen-speed bin classifications, categorized by MOVES road
type and source type, hour of the day, and for base and future analysis years. SUTA’s current methodology incorporates average
speeds from their statewide and urban [regional] travel demand models (traditional four-step trip-based models administered in the
Caliper TransCAD Platform). There exists a gap between the travel demand model outputs (average speed) and the required inputs
(sixteen speed bin distribution) to the MOVES Model. SUTA staff are proposing a research project to identify how archived real time
speed data available to MDOT (currently INRIX speed data available through the CATT Lab’s RITIS Platform) can be used to fill this
gap between travel demand and air quality models, as well as forecast speed distributions using the results from the travel demand
model(s). The results are to be organized into a useable format to generate a reliable average speed distribution that can be used as
input into the EPA MOVES Model.]]></description>
      <pubDate>Mon, 09 Jun 2025 08:02:14 GMT</pubDate>
      <guid>https://rip.trb.org/View/2562324</guid>
    </item>
    <item>
      <title>Enhancing Transit Demand Estimation with Emerging Data-as-a-Service (DaaS)</title>
      <link>https://rip.trb.org/View/2553995</link>
      <description><![CDATA[The overall goal of this research is to better understand the potential value of various emerging Data-as-a-Service platforms in transit demand estimation and transit service planning. Specific research objectives are: (1) survey the state-of-the-art research, development, and related practice of using Data-as-a-Service for transit demand estimation and transit planning, and (2) conduct case studies in Florida to identify transit underserved areas and enhance transit service planning by leveraging Data-as-a-Service in addition to standard transit data.]]></description>
      <pubDate>Fri, 16 May 2025 07:10:17 GMT</pubDate>
      <guid>https://rip.trb.org/View/2553995</guid>
    </item>
    <item>
      <title>The Reverse Side of Online Shopping: Examining Sociodemographic and Built-Environment Determinants of Delivery Returns</title>
      <link>https://rip.trb.org/View/2553166</link>
      <description><![CDATA[The rise of online shopping has led to a significant increase in the return rate for items purchased online (or "delivery returns"). The process of returning items, once a rare occurrence in the traditional retail setting, has become a commonplace aspect of the e-commerce experience. Online purchase return rates (30%) significantly exceed those of physical stores (8.89%). Overall, these high return rates, have substantial financial, logistical, and transportation-related repercussions. From a transportation perspective, the large volume of returns necessitates additional truck trips, leading to increased freight vehicle miles traveled. This trend also results in more truck traffic at residential locations or return points. Despite the acknowledged impacts, this topic remains under-researched, with existing studies focusing on product characteristics, or retailer policies while overlooking consumer-level perspectives. This study aims to bridge this gap by examining how sociodemographic and built-environment factors influence the frequency and channel choice (physical store, mail carrier, Amazon drop-off, home pickup) for returning online purchases. Utilizing the National Household Travel Survey (NHTS) 2022 dataset, the research team analyzes responses on delivery return frequency across four channels. The team employs a multivariate probit ordered-response model to jointly analyze the full product returning behavior spectrum. This approach recognizes that behaviors are multifaceted, involving both the decision to return an item and the choice of a channel, and accounts for the interconnectedness of decision-making processes. The findings provide a foundation for developing targeted strategies to reduce return rates, streamline reverse logistics, manage travel demand, enhance customer satisfaction, and contribute to a more sustainable e-commerce future. ]]></description>
      <pubDate>Thu, 15 May 2025 14:53:38 GMT</pubDate>
      <guid>https://rip.trb.org/View/2553166</guid>
    </item>
    <item>
      <title>How Effective Are Attitudinal Variables at Improving Travel Behavior Models? Evaluation Using an Overlapping Sample From an Attitude-Rich Survey and the 2017 National Household Travel Survey</title>
      <link>https://rip.trb.org/View/2553161</link>
      <description><![CDATA[Facing various factors affecting travel behavior, including altered work/commute patterns and advancements in transportation technologies, travel demand models are, and will be, in need of enhanced prediction performances. One well-established way to better understand and predict travel behavior is to include attitudes in travel behavior models, which enables explaining behavior more completely and meaningfully and simulating scenarios involving changes in attitudes. To encourage measuring and utilizing attitudes in practice-oriented travel demand models, a clear demonstration of the effectiveness of such an approach is necessary. To this end, this study aims to evaluate the efficacy of including a handful of attitudinal marker variables in government-sponsored surveys, by examining the improvements that those variables bring to modeling travel behavior measured in the surveys. The datasets to be used are the responses to the 2017 Georgia Department of Transportation (GDOT) Emerging Technologies survey (an attitude-rich survey dataset) and the Georgia add-on sample’s responses to the 2017 National Household Travel Survey (NHTS). Using attitudes predicted from machine learning functions trained on the non-overlapping sample of respondents to the former survey (N » 1,800) using only a skeletal set of attitudinal variables (called marker variables), the overlap sample of respondents completing both surveys (N » 1,500) will be deployed to model several travel behavior variables found in the latter survey, to investigate how effective the predicted attitudes are as explanatory variables, compared to the “observed” attitudinal factor scores created from the former survey, and to the marker variables themselves. This study will yield insight into the potential of employing attitudinal marker variables in practice-oriented travel behavior modeling based on government-administered surveys.  ]]></description>
      <pubDate>Thu, 15 May 2025 14:39:16 GMT</pubDate>
      <guid>https://rip.trb.org/View/2553161</guid>
    </item>
    <item>
      <title>Utilizing Big Data to Verify and Enhance Route Choice Models in Travel Demand Modeling</title>
      <link>https://rip.trb.org/View/2553840</link>
      <description><![CDATA[Virginia Department of Transportation (VDOT) has invested roughly $5M to maintain and improve its long-range travel demand models, which are needed to help analyze candidate transportation projects.  A key step within these models is “trip assignment” where the path vehicles follow is represented in the network.  High-resolution global positioning system (GPS)-level data offers the potential to improve the accuracy of this step.  However, VDOT staff are finding some discrepancies between route choice as currently represented in demand models and route choice as observed by GPS data—and it is not immediately clear how to resolve this discrepancy.  This research effort will determine the best way to use the GPS data to enhance model accuracy.  Note that a substantial amount of effort needed to make this determination has already been completed through an earlier research effort, and thus, this new study adds additional work to address this trip assignment step.]]></description>
      <pubDate>Thu, 15 May 2025 09:16:33 GMT</pubDate>
      <guid>https://rip.trb.org/View/2553840</guid>
    </item>
    <item>
      <title>Quasi-Sparsity in Transportation Origin-Destination Demand</title>
      <link>https://rip.trb.org/View/2553156</link>
      <description><![CDATA[Quasi-sparsity (QS) indicates that for a large-scale transportation network, most origin-destination (OD) demands are concentrated on a small fraction of the OD pairs, while majority of the OD pairs exhibit small (maybe non-zero) travel demands. One example is the King County network (the area that includes the City of Seattle in the State of Washington): more than 90% of the nearly 500,000 OD pairs in the network have less than 2 trips per day, and such trips count for less than 15% of the total demands in the network. While QS was proposed in Wang et al. [1] and used therein for the estimation of vehicular OD demands, its existence on real-world transportation networks and other modes has not been well studied, and its potential to help improve existing OD demand estimation methods (e.g., for vehicular demand matrices) or OD synthesis methods (e.g., for freight demand matrices) has not been explored. Many interesting questions still remain open: e.g., does QS hold for all the major modes (car, transit, freight) of a network? If so, how similar are the QS properties between different modes? Also, how does the QS property for the same mode on the same network evolve over time? Answers to these questions are not only scientifically intriguing but also helpful to the understanding of inherent human mobility patterns and to practical OD estimation/synthesis. This research aims to investigate the QS of OD travel demands on large-scale transportation networks, aiming to answer the above key questions. The research team plans to collect agency and open-source data, and will also leverage the aggregated big mobility data from third-party from previous research projects. Using the data, the team will define formal measures of QS, and apply them to study the QS property of different networks and for different modes, including vehicular traffic, transit, ride-hailing services, and freight traffic. The team will also compare the similarities of the QS measures for the OD matrices of different travel modes on the same network, and investigate the connections between the similarities and the inherent human mobility patterns of the network.]]></description>
      <pubDate>Tue, 13 May 2025 19:25:03 GMT</pubDate>
      <guid>https://rip.trb.org/View/2553156</guid>
    </item>
    <item>
      <title>Vehicle Edge Computing for Travel Behavior and Demand in Future Intelligent Transportation Systems (ITS)</title>
      <link>https://rip.trb.org/View/2553151</link>
      <description><![CDATA[Meeting the diverse needs of stakeholders such as passengers, drivers, and service providers is imperative. Modern travelers seek real-time updates and personalized journey experiences. Drivers need consolidated data for safety and punctuality (Chen et al., 2021), while service providers rely on data analytics to optimize resources and enhance reliability (Wang et al., 2020). Traditional centralized computing infrastructures struggle with the agility and responsiveness needed in the dynamic transportation landscape (Li et al., 2017). Edge computing emerges as a transformative solution by offloading computational tasks to roadside units. This enables swift processing for real-time applications, facilitating dynamic route optimization, congestion management, and resource allocation, thereby enhancing operational efficiency and reducing travel times. The project will investigate how edge computing impacts travel behavior. Field studies and simulations will measure travelers’ responsiveness to real-time data and how it influences their travel choices and demand patterns. This ensures the research is relevant to travel behavior studies. 

Edge computing not only enhances current transportation operations but is also crucial for autonomous vehicles. It allows real-time data processing and analysis for navigation, hazard detection, and collision avoidance. By leveraging edge computing, autonomous vehicles can offload computational tasks, alleviating the burden on onboard systems and ensuring seamless, responsive data processing without compromising safety or performance. The collaborative framework between autonomous vehicles and roadside units facilitates continuous learning and adaptation. Real-time access to advanced computing enables autonomous vehicles to use machine learning for predictive analysis, enhancing their ability to anticipate and respond to changing road conditions and traffic patterns. Integrating edge computing with autonomous vehicles creates a symbiotic relationship that enhances autonomous driving systems and accelerates the development of safer, more efficient transportation systems. This aligns the project with the theme of improving the mobility of people and goods, fitting the TBD center’s priorities. ]]></description>
      <pubDate>Tue, 13 May 2025 19:05:22 GMT</pubDate>
      <guid>https://rip.trb.org/View/2553151</guid>
    </item>
  </channel>
</rss>