<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Transport Research International Documentation (TRID)</title>
    <link>https://trid.trb.org/</link>
    <atom:link href="https://trid.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>Transport Research International Documentation (TRID)</title>
      <url>https://trid.trb.org/Images/PageHeader-wTitle.jpg</url>
      <link>https://trid.trb.org/</link>
    </image>
    <item>
      <title>A Simulation-Based Methodology for Road Freight Network Abstraction: Case Study in the Canadian Prairie Region</title>
      <link>https://trid.trb.org/View/2658093</link>
      <description><![CDATA[Efficient planning and design of road freight networks require an understanding of their spatial characteristics and demand patterns. However, the large scale and dense interconnections of these networks pose challenges in accurately representing and analyzing freight movement while ensuring computational efficiency. Public agencies also face difficulties in traffic monitoring, safety analysis, and asset management on a broader scale. This study focuses on the Prairie region of Canada and leverages data from the Canadian Freight Analysis Framework (CFAF) to propose a methodology for network extraction. Using a multi-model traffic assignment approach, the method extracts a sub-network from the original while preserving essential functional features. Results indicate that the proposed approach significantly simplifies the network without compromising structural integrity, offering a robust foundation for practical applications.]]></description>
      <pubDate>Thu, 12 Mar 2026 08:52:52 GMT</pubDate>
      <guid>https://trid.trb.org/View/2658093</guid>
    </item>
    <item>
      <title>Advancing deep learning-based driver intention recognition : towards a safe integration framework of high-risk AI systems</title>
      <link>https://trid.trb.org/View/2666559</link>
      <description><![CDATA[Progress in artificial intelligence (AI), onboard computation capabilities, and the integration of advanced sensors in cars have facilitated the development of Advanced Driver Assistance Systems (ADAS). These systems aim to continuously minimize human driving errors. {An example application of an ADAS could be to support a human driver by informing if an intended driving maneuver is safe to pursue given the current state of the driving environment. One of the components enabling such an ADAS is recognizing the driver's intentions. Driver intention recognition (DIR) concerns the identification of what driving maneuver a driver aspires to perform in the near future, commonly spanning a few seconds. A challenging aspect of integrating such a system into a car is the ability of the ADAS to handle unseen scenarios. Deploying any AI-based system in an environment where mistakes can cause harm to human beings is considered a high-risk AI system. Upcoming AI regulations require a car manufacturer to motivate the design, performance-complexity trade-off, and the understanding of potential blind spots of a high-risk AI system.} Therefore, this licentiate thesis focuses on AI-based DIR systems and presents an overview of the current state of the DIR research field. Additionally, experimental results are included that demonstrate the process of empirically motivating and evaluating the design of deep neural networks for DIR. To avoid the reliance on sequential Monte Carlo sampling techniques to produce an uncertainty estimation, we evaluated a surrogate model to reproduce uncertainty estimations learned from probabilistic deep-learning models. Lastly, to contextualize the results within the broader scope of safely integrating future high-risk AI-based systems into a car, we propose a foundational conceptual framework.]]></description>
      <pubDate>Thu, 05 Feb 2026 08:33:54 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666559</guid>
    </item>
    <item>
      <title>Monitoring tire-road friction using connected vehicle data</title>
      <link>https://trid.trb.org/View/2666552</link>
      <description><![CDATA[One in five serious or fatal road traffic accidents occur under severe weather conditions. Despite notable improvements in traffic safety, the Vision Zero approach of shared responsibility for eliminating fatalities and serious injuries remains a global challenge. As the vehicle fleet becomes increasingly connected and automated, vast amounts of data are generated for every kilometer traveled, data that can be used to enhance road safety. One promising application is the monitoring of tire-road friction to improve understanding of road surface conditions and the interaction between tire and road. Since 2018, the Swedish Transport Administration has obtained connected vehicle data, sometimes referred to as floating car data (FCD) or probed vehicle data, to follow up on tire-road friction. The focus of the administration has been on how connected vehicle data can be applied to support and improve winter road maintenance on Sweden's public road network. Within the Digital Vinter project, connected vehicle data have been validated and analyzed alongside conventional tire-road friction estimation methods and in relation to Road Weather Information Systems (RWIS) and Mobile Reporting of Ploughing (MIP). Some of the results from the Digital Vinter project are presented within this thesis.]]></description>
      <pubDate>Thu, 05 Feb 2026 08:33:47 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666552</guid>
    </item>
    <item>
      <title>Deep learning-based driver intention recognition : evaluating performance, complexity and uncertainty estimations</title>
      <link>https://trid.trb.org/View/2666547</link>
      <description><![CDATA[Deep learning (DL) methods have advanced rapidly and are commonly applied in high-risk, resource-constrained environments such as advanced driver assistance systems (ADAS), where misclassifications can have serious consequences. With upcoming artificial intelligence (AI) legislation, it is essential to extensively evaluate and minimize the undesirable behavior of DL-based systems in such settings. An example is an ADAS that continuously evaluates whether a driver's intended maneuvers are safe to execute given the current traffic context. Driver intention recognition (DIR), which predicts the maneuver a driver intends to perform in the near future, is a central DL-based component of such systems. Since deep neural networks (DNNs) do not inherently provide uncertainty estimates for their predictions, probabilistic deep learning (PDL) methods can be applied to improve the identification of scenarios where model outputs may be unreliable. In this thesis, we first review the current state of DIR research, focusing on the recent shift toward DL methods. We then examine how both established and novel PDL methods influence DIR performance. We evaluate the uncertainty estimations by analyzing their ability to distinguish between correct and incorrect predictions and by measuring their effectiveness in out-of-distribution (OOD) detection. Furthermore, we employ neural architecture search with multiple objectives and search strategies to explore how architectural complexity impacts DIR and OOD detection performance. Finally, we conduct a comparative experiment to evaluate human performance against that of DL-based models in video-based recognition of road user intentions.]]></description>
      <pubDate>Thu, 05 Feb 2026 08:33:40 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666547</guid>
    </item>
    <item>
      <title>Capacity modeling and shift optimization for train dispatchers (CAPMO-Train)</title>
      <link>https://trid.trb.org/View/2666521</link>
      <description><![CDATA[In the CAPMO-Train project, we aimed to illuminated the possibilities of automated, optimized train-dispatcher shifts that take all legal and operational restrictions into account and integrate train-dispatcher workload. To this end, we developed an optimization frame-work for shift scheduling. We exemplified our framework with results for Malmo¨ dispatching center, but the framework itself is flexible and can be applied for other dispatching centers. We derived the number of train movements in a dispatching area during a time period as an approximation for the objective task load (which is correlated to the subjective dispatcher workload) and inferred an upper bound for this approximation based on discussion with operational experts. Together with legal and operational requirements for train-dispatcher shifts, this task-load measure build the basis for the optimization framework.]]></description>
      <pubDate>Thu, 05 Feb 2026 08:33:11 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666521</guid>
    </item>
    <item>
      <title>Computational models for safe interactions between automated vehicles and cyclists</title>
      <link>https://trid.trb.org/View/2666519</link>
      <description><![CDATA[Cyclists, as vulnerable road users, face significant safety risks in traffic, especially at unsignalized intersections where they must interact with motorized vehicles. This PhD thesis investigated bicycle-vehicle interactions at unsignalized intersections and developed predictive models to improve active safety systems and automated driving. The research integrates naturalistic and simulator data to model the behavior of both cyclists and vehicles at intersections. The models included kinematic factors, non-verbal communication, and glance behavior. The studies included in this thesis revealed that kinematic factors, such as time to arrival (DTA), along with cyclists' non-verbal cues, like head movements and pedaling, significantly affect yielding behavior at intersections. Both simulator data and naturalistic data confirmed that visibility conditions and DTA played a critical role in cyclists' decision-making while subjective data from questionnaires highlighted the importance of communication and eye contact between cyclists and drivers in reducing the severity of interactions. Additionally, an analysis of naturalistic data uncovered differences in yielding behavior between professional and non-professional drivers, with professional drivers being less likely to yield to cyclists. Different models, leveraging machine learning and game theory, were developed to predict yielding decisions during these interactions. Lastly, simulator data was used to model drivers' behavior, incorporating kinematics, demographics, and gaze metrics to predict drivers' responses to crossing cyclists. The predictive models developed through this research provide novel insights for the design of threat assessment algorithms for active safety and automated driving, enhancing the machine ability to anticipate cyclist behavior and improve safety.]]></description>
      <pubDate>Thu, 05 Feb 2026 08:33:09 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666519</guid>
    </item>
    <item>
      <title>Monitoring and prediction of road traffic using drones : METRIC</title>
      <link>https://trid.trb.org/View/2666516</link>
      <description><![CDATA[Unmanned aerial vehicle (UAV), also called drone, is increasingly considered as one of the most promising techniques that pave the road towards future intelligent traffic management system. Drone-based system has the potential to be adopted as a technological platform for efficient and cost-effective data collection as well as for proactively conducting traffic monitoring and solving problems of congestion and incident in reality. This project started with initial ideas of investigating two essential technologies identified for drone-based traffic management system i.e. real-time data streaming and video image analysis techniques. Following the project development, a cyber-physical framework has been proposed for back-end system together with essential technologies to perform traffic monitoring, data communication, real-time video analysis and traffic information estimation tasks. The perception of live video feed and derived traffic information will play essential roles to support real-time decision makings for future traffic management. Demonstrators are also developed to show the modular functions of the essential technical components. Finally, traffic data collection, implemented through drone technologies, has the potential to be first applied as service in real applications e.g. for offline traffic analysis, planning, operation and so on.]]></description>
      <pubDate>Thu, 05 Feb 2026 08:33:04 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666516</guid>
    </item>
    <item>
      <title>Acoustic sensing for road traffic modelling and noise assessment</title>
      <link>https://trid.trb.org/View/2666504</link>
      <description><![CDATA[Road traffic noise is a major environmental pollutant with significant societal impact, warranting reliable exposure assessment. Beyond its health impact, noise also contains rich temporal features that can be exploited for analysis. The state-of-the-art CNOSSOS-EU framework requires detailed traffic data, but in cities with limited monitoring infrastructure this input is often unreliable, reducing assessment accuracy. The thesis addresses this gap by developing a methodology that exploits data from roadside noise sensors and expands their functionality to also serve as traffic sensors, providing the necessary inputs to a modelling chain for road traffic noise. The methodology is validated through a case study on a busy urban road in Stockholm, Sweden. Three primary objectives are considered: (i) estimating traffic flow rates from noise measurements, (ii) evaluating the use of noise data as an alternative to radar in a microscopic noise assessment framework, and (iii) developing a methodology to define noise mitigation strategies using city-wide noise assessments. Ad-hoc noise sensors were deployed at three positions at the case study location for over 400 days, generating data for the development and testing of traffic flow estimation models. These models were also adapted through specialized training to reduce the need for expensive traffic sensor data when estimating conditions at a new location. A microscopic-traffic-based noise simulation framework was implemented and run with input from noise data, and its outputs were compared against those from radar-based input. Algorithms for optimal vehicle routing were combined with noise-based cost functions to determine vehicle routes reducing population exposure to noise. Results show reliable traffic flow estimation across temporal and spatial variations. Combining datasets from multiple locations and using synthesized data show potential for cost-effective implementation at new locations. Output of noise simulations based on noise measurements show good agreement with output based on radar data. Inclusion of noise exposure constraints in vehicle routing identifies routes with lower noise exposure, while remaining logistically feasible.]]></description>
      <pubDate>Thu, 05 Feb 2026 08:32:56 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666504</guid>
    </item>
    <item>
      <title>Artificial intelligence for enhanced prehospital stroke care : focus on efficient mobile stroke unit allocation and travel time estimation</title>
      <link>https://trid.trb.org/View/2666503</link>
      <description><![CDATA[This thesis aims to use artificial intelligence's power to enhance prehospital stroke care. To accomplish this, we study challenges in prehospital stroke care by focusing on three interrelated research challenges: Mobile stroke unit (MSU) allocation, ambulance travel time estimation, and improving travel time calculations within emergency medical service (EMS) simulation. We develop and analyze different optimization and machine learning (ML) methods to achieve improved analysis and planning of prehospital stroke care. In particular, we propose methods to solve the MSU allocation problem, which aims to identify the optimal locations for a fixed number of MSUs at the existing ambulance station locations within a geographic region. Moreover, we develop a machine learning-based regression method for ambulance travel time estimation. Next, we apply our pre-trained ML-based regression method to improve ambulance travel time estimation within an EMS simulation framework.]]></description>
      <pubDate>Thu, 05 Feb 2026 08:32:55 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666503</guid>
    </item>
    <item>
      <title>Big fun</title>
      <link>https://trid.trb.org/View/2666480</link>
      <description><![CDATA[The BIG FUN project aims to understand how to apply quantitative analytic methods to identify moments of interest in real-world vehicle journeys. The combination of these findings with advanced qualitative analytic methods will generate actionable insights such as a deeper understanding of challenges and opportunities for improving truck function, feature and service design to better suit commercial mobility needs.]]></description>
      <pubDate>Thu, 05 Feb 2026 08:32:31 GMT</pubDate>
      <guid>https://trid.trb.org/View/2666480</guid>
    </item>
    <item>
      <title>Safety performance functions in a road environment with automated vehicles</title>
      <link>https://trid.trb.org/View/2640566</link>
      <description><![CDATA[The reduction of road fatalities can be achieved by intervening in various aspects, including infrastructure, transportation policy, vehicles, and driver behavior. One of the most promising solutions to solve this issue is to rely on Automated Vehicles (AVs), which can prevent human errors, which account for most crashes. However, the impact of AVs on road safety is still unquantifiable. The reason resides in a lack of observed data, as well as in the uncertainty about AV introduction on roads and their interaction with other vehicles and users. In this paper, a methodology to predict the impact of AVs is proposed, relying on Safety Performance Functions (SPFs). An ad hoc SPF for AVs has been developed just for multivehicle crashes, based on a set of market penetration rates, to propose a mathematical model that can include recent technological innovations in road traffic and be adapted to other contexts. Considering the area of the Province of Bari and three different time horizons, crashes were simulated with the presence of AVs in different traffic scenarios. The proposed scenarios were taken from extensive literature studies about the deployment of AVs. The SPF for the predicted crashes was developed by adding one coefficient that considers the presence of AVs to the baseline equation, controlling for the road geometry. The fitted models show a satisfactory goodness-of-fit, based on different metrics, including CuRe (Cumulative Residuals) plots.]]></description>
      <pubDate>Fri, 19 Dec 2025 10:03:38 GMT</pubDate>
      <guid>https://trid.trb.org/View/2640566</guid>
    </item>
    <item>
      <title>Railway bridge dynamic amplification factors : investigation of effects from track irregularities</title>
      <link>https://trid.trb.org/View/2598650</link>
      <description><![CDATA[This work investigates the dynamic effects on short-span railway bridges, with a particular focus on the impact of track irregularities and the resulting dynamic amplification factor, notated as φ &#8242;&#8242;. The objective of this study is to investigate whether the current design formula, which is based on older investigations, is un necessary conservative and could be refined to increase the allowable axle loads and enhance the effectiveness of the railway transport system. The study is focused on short-span bridges, with a span length between 4-20 m, given that they are more susceptible to dynamic effects. The research involves experimental testing on two concrete bridges located on the southern main line near Katrineholm, Sweden. The objective is to validate the finite element models used for a larger number of simulations. The principal model employed for simulations is a two-dimensional model that incorporates train-track bridge interaction. The impact of track irregularities is incorporated into the model to calculate their isolated effect. The track irregularities used are derived from measurements on track sections in Sweden. The results show that the current formula overestimates the dynamic amplification factor for a significant portion of the studied interval compared to the formula given in Eurocode, with the upper limit for eigenfrequency and for the studied spans of 4-20 m and train speeds of up to 120 km/h, particularly for lower speeds. Based on the simulation results, a new formula for φ &#8242;&#8242; is proposed. A big difference between the formulas, is that the Eurocode formula is no longer affected by speed after 80 km/h, which was not in line with the simulations. The magnitude of difference also depends on with what kind of track quality is being compared against, the new formula for φ &#8242;&#8242;, proposed in this study, uses a scaling factor depending on standard deviation σ, instead of only using "good track" or not.]]></description>
      <pubDate>Fri, 12 Sep 2025 10:19:37 GMT</pubDate>
      <guid>https://trid.trb.org/View/2598650</guid>
    </item>
    <item>
      <title>Planning and operation optimization of mobility-on-demand services in the multimodal mobility system</title>
      <link>https://trid.trb.org/View/2598649</link>
      <description><![CDATA[Multimodal mobility systems provide seamless service by integrating various travel modes like driving, cycling, Mobility-on-Demand (MoD) services, and Public Transit (PT) services. With the advancement in autonomous driving and electric vehicles, MoD services show their significant potential in coordinating with other travel modes, especially for PT services. To make the best use of its potential, it is essential to investigate the planning and operations of MoD and PT services in the multimodal mobility system. In the multimodal mobility system, service operations on the supply side should focus on intermodal coordination. On the demand side, customers decide on routes and modes according to service levels such as travel time and price. However, research gaps exist in the planning and operations of integrated MoD and PT services. First, existing literature lacks in optimizing service operations that conform to customer behavior for multimodal mobility systems. Second, existing methods are not applicable to solve such an optimization problem with consistent 'expected' (from service operations) and 'actual' customer behavior. Third, there is a lack of operational optimization models with temporal dynamics for electric MoD vehicles integrated with PT service. To address the above issues, the included papers propose (1. service operation planning in multimodal mobility systems, (2. a generic mathematical solution algorithm for the choice-based optimization problem, and (3. electric MoD operation in multimodal mobility systems.]]></description>
      <pubDate>Fri, 12 Sep 2025 10:19:36 GMT</pubDate>
      <guid>https://trid.trb.org/View/2598649</guid>
    </item>
    <item>
      <title>Situation awareness for autonomous agents under limited sensing</title>
      <link>https://trid.trb.org/View/2598648</link>
      <description><![CDATA[Autonomous agents, such as robots and automated vehicles, rely on their ability to perceive and interpret their environment to make informed decisions and execute actions that align with their goals. A key aspect of this capability is situation awareness, which involves understanding the current state of the environment and predicting its future evolution. Traditional autonomous systems address perception and prediction as separate tasks within a sequential pipeline, where raw sensor data is processed into increasingly abstract representations. While this structured approach has driven significant advancements, it remains constrained by sensor limitations, including occlusions, measurement uncertainty, and adverse weather conditions. This thesis investigates how predictions from past observations can enhance perception algorithms, enabling agents to infer missing information, reduce uncertainty, and better anticipate changes. To support this integration, alternative environment representations are explored that allow feedback between prediction and perception while capturing uncertainty. This tighter coupling improves decision-making, particularly in complex and partially observable environments. The contributions include: (1. a reachability-based reasoning framework for tracking possible hidden obstacles; (2. its extension to handle delayed and partial external data; (3. a probabilistic mapping method, Transitional Grid Maps (TGM), that jointly models static and dynamic occupancy; and (4. an extension of TGM to mitigate weather-induced sensor noise. The proposed methods are evaluated in simulated and real scenarios where traditional perception pipelines struggle, such as occluded, highly dynamic and noisy environments. By bridging the gap between perception and prediction, this work contributes to the development of more robust and intelligent autonomous systems.]]></description>
      <pubDate>Fri, 12 Sep 2025 10:19:35 GMT</pubDate>
      <guid>https://trid.trb.org/View/2598648</guid>
    </item>
    <item>
      <title>Mind the unknown : risk- and occlusion-aware motion planning for autonomous vehicles</title>
      <link>https://trid.trb.org/View/2598606</link>
      <description><![CDATA[Autonomous vehicles (AVs) must navigate uncertain environments while ensuring safety, particularly in scenarios involving risk and occlusions. This thesis develops structured approaches to risk- and occlusion-aware motion planning, integrating theoretical advancements with real-world validation. To address risk in motion planning, we introduce a framework that quantifies both the probability and severity of safety violations, enabling AVs to reason about risk while maintaining operational efficiency. Complementing this, we investigate pedestrian-aware motion planning in urban environments, incorporating a harm-based risk model to balance safety and progress in interactions with vulnerable road users. Occlusions pose a major challenge by limiting direct visibility of critical road users. We develop a method for tracking and reasoning about hidden obstacles using reachability analysis and formal logics. By incorporating prior observations, our approach systematically refines possible states of occluded agents, reducing unnecessary conservatism. For high-speed driving, we refine velocity bounds on occluded traffic participants, preventing worst-case assumptions that could lead to excessive braking. Additionally, we explore vehicle-to-everything (V2X) communication to enhance situational awareness, enabling AVs to infer and share information about occluded regions in real time. Finally, we propose an occlusion-aware planning framework that integrates tree-based motion planning with reachability-based occlusion tracking. This enables AVs to proactively reason about future observations-or their absence-ensuring robust decision-making under limited sensing. By reducing overly conservative constraints while maintaining safety guarantees, our approach addresses key issues in occlusion-aware motion planning. Together, these contributions advance the ability of AVs to operate safely and efficiently in demanding environments, supporting scalable real-world deployment.]]></description>
      <pubDate>Fri, 12 Sep 2025 10:18:58 GMT</pubDate>
      <guid>https://trid.trb.org/View/2598606</guid>
    </item>
  </channel>
</rss>