<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-Enabled Vision System for Intersection Analytics </title>
      <link>https://rip.trb.org/View/2673053</link>
      <description><![CDATA[Phase I of this project revealed limitations of using a single camera per intersection to automatically extract key traffic performance and safety information from video feeds. To overcome these limitations and enhance data accuracy, the Phase II approach will deploy a second camera at selected high-impact intersections. By fusing the views from two different camera angles, the system can establish a true spatial relationship of objects in the intersection, essentially achieving a more complete 3D understanding of vehicle and pedestrian trajectories.]]></description>
      <pubDate>Tue, 24 Feb 2026 15:00:25 GMT</pubDate>
      <guid>https://rip.trb.org/View/2673053</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>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>STEER AV - Safety Tuned Emulation of Emerging Responses for Autonomous Vehicles
</title>
      <link>https://rip.trb.org/View/2640184</link>
      <description><![CDATA[Autonomous vehicles (AVs) produced by different manufacturers often display distinct driving styles because each system uses its own proprietary decision rules. These variations can affect safety and traffic flow during the long transition period when automated and human driven vehicles operate together. This project will study real world AV trajectory data to assess how AVs follow other vehicles, how they balance safety and efficiency, and which factors shape their decision making. The research team will use inverse reinforcement learning and interpretable generative methods to infer the policies that guide AV actions and to create models that reproduce these behaviors.

After the initial models are created, the project will incorporate additional constraints that guide the system toward safer behavior while preserving mobility. Simulation experiments will examine how these modified policies perform under a range of conditions and will evaluate possible trade offs between safety and efficiency. The resulting framework will support efforts to standardize and improve AV driving policies, help researchers understand AV decision patterns, and assist agencies and manufacturers as they prepare for increasing levels of automated travel.]]></description>
      <pubDate>Thu, 11 Dec 2025 13:33:06 GMT</pubDate>
      <guid>https://rip.trb.org/View/2640184</guid>
    </item>
    <item>
      <title>Toward Ubiquitous Trajectory‐Based Traffic Network Diagnosis Systems
</title>
      <link>https://rip.trb.org/View/2625315</link>
      <description><![CDATA[This project aims to develop a trajectory-based traffic network diagnosis system to address urban congestion by leveraging vehicle trajectory data and open-source tools. The system operates at both planning and operational levels, offering scalable, real-time diagnosis and mitigation of congestion issues. It integrates advanced equilibrium models and mesoscopic simulations, prioritizing computational efficiency and actionable results. By democratizing access to traffic diagnostics and enabling rapid deployment, the project envisions empowering cities worldwide to manage congestion sustainably, enhance urban mobility, and improve quality of life.

]]></description>
      <pubDate>Thu, 13 Nov 2025 16:01:21 GMT</pubDate>
      <guid>https://rip.trb.org/View/2625315</guid>
    </item>
    <item>
      <title>A Low-cost Roadside Device System for Cooperative Automated Driving
Phase 2: Work Zone Safety Applications</title>
      <link>https://rip.trb.org/View/2625304</link>
      <description><![CDATA[Despite the significant progress in automated driving, technical challenges still exist, especially for complex Operational Design Domains (ODDs). A low-cost roadside device system, the Connected Reference Marker (CRM) System, was developed to facilitate connected and automated vehicle (CAV) localization. A project was funded by Center for Connected and Automated Transportation (CCAT) FY2024 to build a prototype system and evaluate its performance. The initial results show that the CRM System is capable of maintaining low positional errors and, therefore, has the potential to be a reliable solution for vehicle localization for cooperative driving automation (CDA). In this project phase, the research team aims to develop a deployable work zone safety system built upon the prototype CRM system from the previous project phase. Specifically, the work zone safety system can track and predict the trajectories of individual vehicles, estimate the vehicle’s collision risk, and send customized warning messages if the risk is elevated. This work zone safety system will also incorporate modules from the CARMA CDA platform to ensure system interoperability.]]></description>
      <pubDate>Thu, 13 Nov 2025 14:51:15 GMT</pubDate>
      <guid>https://rip.trb.org/View/2625304</guid>
    </item>
    <item>
      <title>Automatic Signal Retiming Using Vehicular Trajectory Data</title>
      <link>https://rip.trb.org/View/2562295</link>
      <description><![CDATA[Traffic signal optimization is a cost-effective method for reducing congestion and energy consumption in urban areas. However,
due to the high installation and maintenance costs of detection systems, most intersections are controlled by fixed-time traffic
signals that rely on manual data collection and are not regularly optimized. More cost-effective methods for signal optimization
need to be explored, such as the use of vehicle trajectory data that is now available. Research is needed to determine if this
process can provide optimized timings at more frequent and regular intervals, yielding better overall signal performance.]]></description>
      <pubDate>Fri, 06 Jun 2025 15:12:39 GMT</pubDate>
      <guid>https://rip.trb.org/View/2562295</guid>
    </item>
    <item>
      <title>Enhancing Road Safety Through Video Analytics and Connected and Automated Vehicles (CAV)</title>
      <link>https://rip.trb.org/View/2562267</link>
      <description><![CDATA[This project develops and demonstrates an end-to-end prototype that integrates roadside video analytics with connected vehicle (CV) technology to enable real-time safety warnings for drivers. Building upon the MSight roadside perception platform, the system detects, tracks, and predicts vehicle and vulnerable road users (VRU) trajectories using infrastructure-mounted cameras, then transmits safety-critical information to vehicles via C-V2X communication. A vehicle-side onboard application processes received messages and delivered timely, intuitive warnings to drivers. Rather than focusing on productization alone, the work uses a prototype-and-field-test approach at Mcity to quantify current technical performance, identify key technology gaps and integration barriers (e.g., detection reliability for VRUs, end-to-end latency, communication constraints, and driver warning usability), and translate findings into prioritized, actionable recommendations. The outcome is a practical assessment of what today’s video analytics + V2X stack can and cannot deliver, and a roadmap of high-impact next steps for DOTs to advance toward deployable, scalable crash-prevention applications.]]></description>
      <pubDate>Fri, 06 Jun 2025 14:55:37 GMT</pubDate>
      <guid>https://rip.trb.org/View/2562267</guid>
    </item>
    <item>
      <title>Development of Real-time Cyberattack Prediction &amp; Warning System</title>
      <link>https://rip.trb.org/View/2548667</link>
      <description><![CDATA[With the increasing prevalence of cyberattacks targeting transportation systems, there is a critical need for a proactive framework capable of predicting potential cyber threats and issuing timely warnings. This study introduces Cyber-TFWS, a trajectory-based forecasting and warning system designed to enhance connected vehicle (CV) safety under spoofing cyberattacks. By leveraging deep learning-based forecasting models, Cyber-TFWS predicts vehicle trajectories under attack, enabling early detection and effective mitigation strategies. The research involves a detailed literature review and the implementation of a generative adversarial model (CAGAN) for trajectory prediction. Key findings demonstrate that Cyber-TFWS significantly improves traffic safety, successfully preventing 100% red-light running incidents under specific perception-reaction time (PRT) conditions. The study also highlights the role of acceleration in improving prediction accuracy and identifies challenges in forecasting trajectories with abrupt velocity changes. Extensive simulations validate the system's robustness, underscoring its potential for real-world deployment in securing intelligent transportation systems against cyber threats.]]></description>
      <pubDate>Wed, 30 Apr 2025 16:06:29 GMT</pubDate>
      <guid>https://rip.trb.org/View/2548667</guid>
    </item>
    <item>
      <title>A Radar-Based Real-Time Cyberattack Detection, Classification, And Notification
System Based on Learning Driving-Simulated Vehicle Trajectory Data Under
Cyberattacks</title>
      <link>https://rip.trb.org/View/2548665</link>
      <description><![CDATA[As connected vehicle technologies gain widespread adoption, the risk of cyberattacks on transportation systems continues to rise. Cyberattacks targeting vehicle-to-infrastructure (V2I) communications, particularly spoofing attacks on wireless sensors, pose significant safety threats. Existing cyber-layer detection methods are vulnerable to being compromised, highlighting the need for alternative approaches. This study proposes a radar-based, real-time cyberattack detection, classification, and notification system leveraging vehicle trajectory data under cyberattacks. By conducting extensive driving simulator experiments, trajectory and driver behavior data were used to train and evaluate a Hidden Markov Model-based detection algorithm, HMM-4-C. The model successfully detected 98% of cyberattack scenarios, demonstrating its effectiveness in identifying abnormal vehicle behaviors at connected intersections. This research introduces a novel physical-layer detection approach that enhances cybersecurity in intelligent transportation systems and can complement traditional cyber-layer methods for improved attack mitigation.]]></description>
      <pubDate>Wed, 30 Apr 2025 16:01:32 GMT</pubDate>
      <guid>https://rip.trb.org/View/2548665</guid>
    </item>
    <item>
      <title>Freeway and Arterial Performance Analysis with High-Resolution Vehicle Trajectory Data (NDOT 500-22-803)</title>
      <link>https://rip.trb.org/View/2499171</link>
      <description><![CDATA[This research focuses on three major objectives: (1) Leverage high-resolution trajectory data to develop traffic operational and safety performance measures tailored to the needs of transportation agencies in Nevada. (2) Conduct case studies and develop implementation guidelines for using high-resolution trajectory data to enhance freeway and arterial performance analyses. (3) Develop an easy-to-use software tool that can extract and visualize trajectory data. The tool can ultimately be used to examine and enhance performance measures obtained from data platforms, generate custom performance measures to fulfil the performance analysis needs of the Nevada Department of Transportation (NDOT) and other project stakeholders, and facilitate signal timing projects and traffic management.]]></description>
      <pubDate>Wed, 29 Jan 2025 18:04:07 GMT</pubDate>
      <guid>https://rip.trb.org/View/2499171</guid>
    </item>
    <item>
      <title>An Updated Capacity Model for Mini-Roundabouts</title>
      <link>https://rip.trb.org/View/2452918</link>
      <description><![CDATA[Mini-roundabouts, characterized by their fully traversable central islands, provide a compact and efficient alternative to traditional single-lane roundabouts. They are particularly beneficial in areas with spatial constraints, where larger roundabouts would necessitate unwanted right-of-way impacts. The typical inscribed circle diameter (ICD) of these mini-roundabouts is often under 90 feet, and they are best suited for areas where speeds are limited to 30 mph or lower.

One of the primary advantages of mini-roundabouts is their smaller footprint, making them an effective replacement for stop signs or signal controls at intersections with moderate traffic volumes. Their traversable central island design is pivotal, offering adaptability in mixed traffic scenarios, especially facilitating the movement of larger vehicles.

However, there are aspects that require further scrutiny. In the early 2010s, the Federal Highway Administration (FHWA) developed capacity models for mini-roundabouts with two different ICDs. These models assumed that such roundabouts would function as a series of independent T-intersections, an assumption that may not always be accurate, especially in the presence of larger vehicles. When comparing the capacities of mini-roundabouts with all-way stop-controlled (AWSC) intersections, it is vital to understand their potential advantages and shortcomings. If mini-roundabouts do not significantly exceed the capacity of AWSC intersections, their unique positioning in traffic management might be challenged, especially when considering the cost-effectiveness of AWSC intersections.

The main objective of this research is to develop new capacity models for mini-roundabouts based on field data collected at 25 mini-roundabouts in North Carolina and other states within the midatantic and southeast regions. Video data will be recorded at all sites from 25-30 ft elevation. The videos will be analyzed using the DataFromSky (DFS) service, which the team successfully utilized in previous NCDOT projects. Vehicle trajectories will be obtained and analyzed to estimate key capacity parameters, including the critical and follow-up headways and the effect of heavy vehicles. The team will utilize a calibrated microsimulation model only to fill out gaps when field data are not available.]]></description>
      <pubDate>Fri, 15 Nov 2024 16:06:05 GMT</pubDate>
      <guid>https://rip.trb.org/View/2452918</guid>
    </item>
    <item>
      <title>Safe and efficient automated freeway traffic control- Phase 2</title>
      <link>https://rip.trb.org/View/2440020</link>
      <description><![CDATA[Shockwaves are a naturally emerging phenomena in freeway traffic, but they represent one of the largest safety risks on freeways. Freeway drivers do not expect to encounter abrupt drops in speed or stopped traffic, as a result, shockwaves sharply increase the accident rates, particularly in the context of rear end collisions. For example, US interstate highways in 2021 saw the following rear-end collision numbers: Fatality 985, Injury-Only 71,408, Property-Damage-Only 152,011. Rear end collision severity is directly related to the relative speed between the involved vehicles, shockwaves increase these relative speeds, and thus, they also increase accident severity. Shockwaves also reduce freeway capacity and have a detrimental impact on fuel consumption and emissions because accelerating engines are less efficient than when cruising.

Connected and autonomous vehicles (CAV) hold the promise to attenuate and eliminate shockwaves (and thus, also reduce the severity and number of accidents), but only if the system is explicitly designed to do so. The very factors that give rise shockwaves in human driven vehicles (HDV) will also do so in CAV. While CAV offer new ways to manage traffic dynamics, an automated freeway will still be subject to traffic dynamics. The real challenge is designing the CAV system so that it ensures the safest possible operation, and then within those bounds, the greatest operational efficiency (maximizing capacity, minimizing delays, etc.).

This research essentially seeks to take conventionally unstable queued traffic and bring it to a stable flow while queued. It will approach CAV traffic control by first establishing the desired macroscopic traffic states along a freeway corridor and will use a rolling horizon to continually update the desired states in response to perturbations in the macroscopic traffic stream. Under this macroscopic framework, the CAV will know what behavior they should take simply by knowing where they are in space relative to the set of desired states. The main objective of the macro to micro control scheme is that the system can efficiently anticipate and respond to disturbances over large distances. It is this macroscopic look-ahead that will allow the system to detect and attenuate shockwaves. Although communications bandwidth is not the focus of this work, the macro to micro control scheme also has the potential to greatly reduce the necessary communication bandwidth to control the freeway traffic.

This proposal is for a continuation of a first year project. Year 1 is focusing on the initial transition from unstable stop and go traffic to the first follower with a smooth trajectory. It uses current conditions along the corridor to estimate the trajectory of a vehicle just entering the corridor and calculate the optimal trajectory that maintains the same departure time while reducing acceleration/deceleration. Then continually update the forecasted trajectory over time based on evolving conditions. The year 2 focus will be extending and refining the smooth trajectories upstream of the first vehicle, addressing unanticipated disturbances (from minor lane change maneuvers to major vehicle failures), and anticipating the management strategies needed to maintain the smoothly flowing queued traffic.
]]></description>
      <pubDate>Sun, 13 Oct 2024 09:24:38 GMT</pubDate>
      <guid>https://rip.trb.org/View/2440020</guid>
    </item>
    <item>
      <title>Freeway and Arterial Performance and Safety Analysis with High Resolution Vehicle Trajectory Data</title>
      <link>https://rip.trb.org/View/2431597</link>
      <description><![CDATA[Local traffic agencies have large investments in intelligent transportation system (ITS)
infrastructure including sensors such as cameras, radars, and loop detectors and communication
to gain new insight for better planning, management, and operation of roadways. However, the
ITS infrastructure is generally limited to dense urban areas and requires significant support to
maintain coupled with limited in-house expertise to fully realize the promise of big data.
Further, new high resolution vehicle trajectory data (HRVT) streams have become available to
further complicate analysis and the value proposition of ITS hardware. This project will evaluate
the potential for HRVT to support infrastructure owner operators (IOOs) and practitioners to
more effectively plan, operate, and manage their systems and improve safety outcomes on their
networks. HRVT will be integrated into traditional traffic analyses as well as leading edge deep
learning research. The outcome of this project will be a tool to effectively query, store, process,
and visualize HRVT data for practitioner use.]]></description>
      <pubDate>Tue, 17 Sep 2024 17:43:12 GMT</pubDate>
      <guid>https://rip.trb.org/View/2431597</guid>
    </item>
    <item>
      <title>End-to-End Learning Framework for Transportation Network Equilibrium Modeling</title>
      <link>https://rip.trb.org/View/2425218</link>
      <description><![CDATA[This project aims to outline a groundbreaking "end-to-end" transportation demand modeling framework, driven by deep learning techniques and empirical multi-source data. Unlike traditional models, which typically employ a multi-step process, this framework directly associates time-series observations of traffic patterns, urban land use, and socioeconomic features with prediction of future traffic flow distributions. The end-to-end modeling framework is designed to learn travelers travel and route choices while refining link performance functions that estimate travel time based on traffic flow. After calibration against empirical data, the proposed framework can recommend optimal policies or projects for enhancement, thereby facilitating informed decision-making. By utilizing passively collected trajectory data, this framework aims to significantly improve modeling accuracy and the realism of behavioral representation, without additional costs for data collection in the existing modeling system.]]></description>
      <pubDate>Thu, 05 Sep 2024 10:35:31 GMT</pubDate>
      <guid>https://rip.trb.org/View/2425218</guid>
    </item>
  </channel>
</rss>