<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 policy evaluation of healthcare access using heterogeneous emergency medical services vehicles and incidents</title>
      <link>https://trid.trb.org/View/2728163</link>
      <description><![CDATA[Efficient dispatch policies are critical for ensuring equitable and effective emergency medical services (EMS). While vehicle specialisation offers tangible clinical benefits, integrating vehicle types into dispatch policy presents significant challenges. This study employs an agent-based simulation framework to evaluate the effects of alternative dispatch policies under varying proportions of specialised ambulances. Results indicate that allowing specialised vehicles to respond to a broader range of high-priority incidents enhances overall survival rates. However, the benefits of specialisation depend on how these vehicles are deployed within the system. When the supply of specialised vehicles exceeds demand, restrictive policies lead to longer response times and worsened outcomes for non-prioritised cases. In particular, restricting specialised vehicles to a narrow set of incidents can reduce overall system efficiency by limiting dispatch flexibility and increasing waiting times for other patients. Moderately flexible dispatch policies provide balance between outcome efficiency and response equity. These findings suggest that both the proportion of specialised vehicles and their dispatch eligibility should reflect the underlying mix of incidents in order to avoid over-constraining the system. Spatial analysis shows that survival and response disparities are more pronounced in peripheral areas. These findings underscore the need to align dispatch policy and fleet composition with incident typology and spatial demand, offering actionable insights for EMS policy and resource planning.]]></description>
      <pubDate>Wed, 30 Sep 2026 16:23:21 GMT</pubDate>
      <guid>https://trid.trb.org/View/2728163</guid>
    </item>
    <item>
      <title>Exploring False Warnings and Modalities for Emergency Vehicle Alerts and Their Impact on Driver Behavior</title>
      <link>https://trid.trb.org/View/2732392</link>
      <description><![CDATA[Objective: This study explores the order effects in false alarms and the effect of warning modality when drivers receive an Emergency Vehicle Approaching (EVA) alert. Background: EVA alerts have the potential to decrease delays for emergency vehicles. However, false alarms and suboptimal warning designs can decrease warning effectiveness. Aligned with previous research, drivers should benefit from receiving an alert that is not visual. Method: A driving simulator study with 80 participants was conducted. During a 30-minute drive, the participants received three EVA alerts, one of which was false. One group received a false alert first, followed by a true alert. The other group had the opposite order. Both groups received another true alert before the experiment ended. Half of the drivers received auditory warnings, and the other half visual warnings. Results: Drivers who received auditory warnings moved over more quickly compared to drivers who received visual alerts. There was an order effect of false warnings, suggesting that drivers who had received a false warning before they received a true warning were slower at moving over, compared to drivers who received a true warning in their first interaction. However, when the drivers received one true and one false warning each, there was no order effect in the third interaction. Conclusion: Both alert modality and false warning effects are important when implementing EVA alerts. Application: This research should be used to understand the order effect of false warnings on in-car warnings. When designing in-car warnings, auditory warnings may be more effective.]]></description>
      <pubDate>Mon, 28 Sep 2026 08:36:51 GMT</pubDate>
      <guid>https://trid.trb.org/View/2732392</guid>
    </item>
    <item>
      <title>One-stage motion planning with probabilistic traversability risk awareness for unmanned ground vehicles in unstructured environments via accelerated model predictive path integral control</title>
      <link>https://trid.trb.org/View/2732004</link>
      <description><![CDATA[Unmanned ground vehicles are indispensable for autonomous navigation in unstructured environments, particularly in critical applications such as search and rescue, disaster response, and exploration. However, the inherent challenges of dynamic terrain conditions and uncertain traversability complicate motion planning in such scenarios. To address these challenges, this paper introduces a probabilistic traversability risk-aware one-stage motion planning framework, which integrates three key innovations: a deep learning-based perception system augmented with Bayesian regression to probabilistically assess terrain traversability and quantify risk; an entropy-based risk measure that consolidates probabilistic traversability estimates into a unified decision-making metric for robust motion planning; and an accelerated model predictive path integral control strategy, optimized via Numba-based parallelization, to ensure globally optimal yet locally feasible trajectories in real time. Extensive BenchNav simulations validate the framework’s superior performance, exhibiting the highest success rate while achieving a 4.5% reduction in travel time compared to conventional two-stage planners (e.g., A*-DWA) and generating 24.7% shorter paths than existing one-stage methods (e.g., CL-RRT). Crucially, the probabilistic traversability evaluation approach proves more robust than mean estimation in uncertain, high-risk unstructured scenarios. Furthermore, real-world vehicle experiments validate the method’s real-time computational feasibility and effective risk-aware navigation in unstructured terrains.]]></description>
      <pubDate>Wed, 23 Sep 2026 15:55:46 GMT</pubDate>
      <guid>https://trid.trb.org/View/2732004</guid>
    </item>
    <item>
      <title>An AI-Reinforced Traffic Digital Twin for Testing Emergency Vehicle Interventions</title>
      <link>https://trid.trb.org/View/2719268</link>
      <description><![CDATA[Emergency response time is a vital indicator of public safety effectiveness in dense urban settings like New York City, where even small delays can significantly affect survival rates. To support data-driven decision-making and enhance emergency response strategies, this project developed a Traffic Digital Twin (TDT): a high-fidelity, simulation- and AI-enhanced framework that replicates Emergency Medical Vehicle (EMV) operations under real-world, transient conditions. Developed in collaboration with the New York City Fire Department (FDNY), the TDT integrated diverse data sources and employed advanced calibration methods to accurately model EMV behavior and surrounding driver responses as detailed in a separate paper. This paper focuses on a complementary AI model, EMVAID, based on a Traffic Simulation-Informed Explainable Boosting Machine (TSI-EBM), designed to interpret key factors influencing EMV speeds. As an illustration of TDT decision support, it is then applied to optimize ambulance Cross Street Locations (CSLs), achieving up to 14.5% reductions in expected travel time during morning traffic while accounting for the likelihood of a congested CSL being unavailable. This study also demonstrates that proxy traffic features, such as 5-minute average speeds, can effectively support real-time EMV operations, underscoring the TDT’s potential as a scalable, interpretable decision-support tool for emergency response planning.]]></description>
      <pubDate>Wed, 23 Sep 2026 15:55:45 GMT</pubDate>
      <guid>https://trid.trb.org/View/2719268</guid>
    </item>
    <item>
      <title>Optimization of hard shoulder running on highways using multi-agent reinforcement learning considering emergency vehicles</title>
      <link>https://trid.trb.org/View/2767353</link>
      <description><![CDATA[With increasing travel demand, highway congestion and accidents have become more frequent. As an essential component of intelligent transportation systems (ITS), Hard Shoulder Running (HSR) provides a dynamic strategy to mitigate congestion by temporarily opening shoulder lanes, yet traditional methods often fail to adapt to real-time traffic changes and overlook the shoulder’s critical role in ensuring emergency vehicle access. This study proposes a novel HSR optimization framework based on the Long Short-Term Memory (LSTM) and Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm, integrated with an improved A* algorithm for EV lane clearing. LSTM is used to extract temporal features from traffic data to support intelligent decision-making in MADDPG, enhanced with prioritized experience replay and importance sampling. The EV lane-clearing task is formulated using graph theory, and the improved A* algorithm determines the optimal path for clearing. A simulation case was developed using Simulation of Urban MObility (SUMO) for a section of the Jinan City Ring Highway, China, evaluating four levels of traffic service. Results show the proposed method reduces total travel time by 14.6%, Time Integrated Time-to-Collision (TIT) by 45.2%, and CO2 emissions by 11.9%. Additionally, with EV intervention, braking times are reduced by up to 376.3% and travel time by 18.1% using the improved A* strategy. These findings demonstrate that the integrated LSTM-MADDPG and A* approach effectively enhances highway traffic efficiency, safety, and sustainability under complex real-world conditions.]]></description>
      <pubDate>Wed, 16 Sep 2026 16:15:41 GMT</pubDate>
      <guid>https://trid.trb.org/View/2767353</guid>
    </item>
    <item>
      <title>Linkages and Propagation Mechanisms of Risk Sources during Electric Vehicles Transportation</title>
      <link>https://trid.trb.org/View/2777928</link>
      <description><![CDATA[This study addresses safety issues in three representative logistics scenarios for electric vehicles (EVs) as cargo-car carriers, roll-on/roll-off (Ro-Ro) vessels, and containers. To address the heterogeneity across these modes, we develop an integrated “process–spatiotemporal load–risk factor” framework that embeds operational steps and confinement conditions into the indicator system, overcoming the limitations of single-scenario or single-factor studies in explaining chain-type propagation. Building on process mapping and spatiotemporal load characteristics, we develop a risk indicator system spanning “person-equipment-transported object-operation & environment-system management.” Expert judgments are then analyzed using an integrated DEMATEL-ISM approach to quantify inter-factor linkages and transmission pathways. The results indicate that regulatory oversight and carrier-side emergency equipment constitute the deep root causes of thermal runaway. The most hazardous transmission route is “regulatory oversight, procedural compliance and skill-experience match”, while “battery type, road/sea conditions and hoisting impacts” forms the shortest path. These findings reveal weaknesses in management and equipment that are amplified by operational execution and limited personnel capability, ultimately precipitating severe transportation incidents.]]></description>
      <pubDate>Wed, 16 Sep 2026 09:17:33 GMT</pubDate>
      <guid>https://trid.trb.org/View/2777928</guid>
    </item>
    <item>
      <title>A Dual-Mode Multi-Agent Reinforcement Learning Method for Context-Aware Traffic Control Optimization</title>
      <link>https://trid.trb.org/View/2698396</link>
      <description><![CDATA[Effective urban traffic control is essential not only for improving travel reliability and reducing vehicle emissions, but also for enhancing public safety. Reinforcement learning (RL) has shown strong potential for optimizing adaptive traffic signals. However, most existing RL-based systems lack the flexibility to prioritize emergency vehicles such as ambulances and fire trucks without significantly compromising regular traffic flow. To address this, we propose a dual-policy multi-agent reinforcement learning framework for context-sensitive traffic signal control that balances emergency responsiveness with overall efficiency. Our method employs a real-time contextual flag to switch between two specialized control policies: one for regular traffic and another for emergency scenarios. During emergencies, the system dynamically reconfigures signal phases to facilitate the smooth passage for high-priority vehicles. In the absence of emergencies, decentralized intersection-level agents use deep RL to minimize congestion and optimize traffic flow. Experiments conducted on two road networks demonstrate that the proposed framework effectively reduces both travel and waiting times for emergency and regular vehicles.]]></description>
      <pubDate>Fri, 28 Aug 2026 08:35:06 GMT</pubDate>
      <guid>https://trid.trb.org/View/2698396</guid>
    </item>
    <item>
      <title>A UAV-Assisted Coordination Framework for Emergency Vehicle Priority and CAV Speed Optimization in Hybrid Human-Machine Driving on Expressways</title>
      <link>https://trid.trb.org/View/2717769</link>
      <description><![CDATA[Providing convenient passage conditions for emergency vehicles (EVs) is crucial for ensuring their safe and swift arrival at the rescue scene. To optimize the efficiency of EVs within mixed human-machine driving environments on expressways, an innovative collaborative control framework that synergizes uncrewed aerial vehicle (UAV) surveillance with multi-vehicle dynamic coordination strategies on expressways is proposed in this study. First, a real-time vehicle coordination framework is developed, leveraging UAV-aided data collection and control to enable EV yielding. Second, an integer nonlinear programming model is constructed to achieve coordinated control of human-machine hybrid traffic flows under dynamic constraints, and a rolling speed-coordinated robust optimization control (SROC) method is proposed to reduce the uncertainty caused by manual vehicle lane-changing. Then, a UAV-assisted trajectory planning approach is established, which integrates quintic polynomial modeling and uncertainty set analysis for hybrid traffic lane-changing. Next, an O-CAV (connected autonomous vehicle in the objective lane) speed adjustment mechanism is introduced to alleviate cascading deceleration effects on subsequent traffic. Finally, a bi-level particle swarm optimization (PSO) model is designed to validate EV avoidance algorithm effectiveness and platform performance. The results show that the method constructed in this study effectively enhances the traffic efficiency of EVs. The rolling SROC method reduces vehicle evacuation time by 17.3%, EV travel time by 12.5%, advances vehicle lane-changing time by 14.2%, and decreases acceleration by 21.0% compared with the one-time SROC method. Increasing the penetration rate and selecting appropriate initial positions for O-CAV and EV can effectively improve the traffic efficiency of EVs. Limited time delays do not significantly affect the applicability of the method. The travel distance of O-CAV increases by 25.1% after the implementation of the O-CAV speed recovery mechanism. These findings demonstrate the potential of UAV-assisted coordination to significantly enhance road safety and traffic efficiency in hybrid human-machine driving environments.]]></description>
      <pubDate>Wed, 29 Jul 2026 09:13:58 GMT</pubDate>
      <guid>https://trid.trb.org/View/2717769</guid>
    </item>
    <item>
      <title>A macroscopic Game-Theoretic Model Predictive Control framework for emergency vehicle prioritization in urban traffic networks</title>
      <link>https://trid.trb.org/View/2717879</link>
      <description><![CDATA[Efficient Emergency Vehicle (EV) prioritization in congested urban networks remains a critical challenge for smart city infrastructure, as traditional preemption methods often trigger secondary congestion and network instability. This paper proposes a decentralized, macroscopic Game-Theoretic Model Predictive Control (GTMPC) framework designed to facilitate rapid EV movement while preserving overall traffic equilibrium. The core of the proposed architecture integrates a weighted non-cooperative game with a potential function structure within a receding-horizon Model Predictive Control (MPC) structure, allowing each intersection to act as an autonomous agent that strategically allocates green-time allocations among competing traffic phases. By assigning dynamic priority weights to EV-serving approaches, the controller proactively clears queues and minimizes stop-and-go behavior. The framework is validated using high-fidelity SUMO simulations initialized with real-world traffic data from Dublin, Ireland, across varying demand profiles, including a 50% flow increase to simulate heavy traffic saturation. Experimental results demonstrate that the GTMPC framework significantly outperforms both Fixed-Time and Classical MPC strategies. Specifically, it achieves substantial reductions in Average Suffering Red-lights, Average Time Loss, and Average Stop Count, while markedly enhancing Average Speed for emergency vehicles. Notably, under heavy traffic conditions, GTMPC maintains robust performance, reducing Average Waiting Time by over 20% in scenarios where standard MPC baselines experience severe congestion and degraded traffic performance. Furthermore, the framework demonstrates an adaptive capability to manage concurrent EV arrivals through strategic multi-player negotiations. Owing to its decentralized structure, the proposed approach shows promising scalability and robustness properties in the conducted simulation studies, making it suitable for large-scale, real-time urban traffic control applications.]]></description>
      <pubDate>Tue, 21 Jul 2026 09:49:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2717879</guid>
    </item>
    <item>
      <title>Traffic Signal Pre-emption Effectiveness in Michigan</title>
      <link>https://trid.trb.org/View/2731919</link>
      <description><![CDATA[Current Michigan Department of Transportation (MDOT) policy allows signal pre-emption for emergency vehicles, but the emergency agency is responsible for paying
for the equipment required for implementation. However, MDOT still has costs associated with the operation and maintenance
of the system. It is unknown at this time how many of the emergency pre-emption implementations are working as designed.
Question- for existing systems that are operational, are the expected benefits being realized? As the complexity of traffic
signal technology continues to grow, the resources available to maintain the signal infrastructure are becoming more strained.
As such, it is important to ensure that the resources dedicated to implementing pre-emption are worthwhile and should be
prioritized over other competing needs. This project will investigate current state of pre-emption technologies and the various
practices underway in MI, as well as develop recommendations for the most effective and reliable systems to maximize the
return on investment with minimum disruptions to daily traffic operations. In addition to existing implementations, the
technology has developed to a point where more and more use cases are being considered for using signal pre-emption. In
cases where it is possible for multiple different use cases to exist along the same corridor, another question/unknown is- how
should the various pre-emption calls be prioritized?]]></description>
      <pubDate>Fri, 17 Jul 2026 11:58:12 GMT</pubDate>
      <guid>https://trid.trb.org/View/2731919</guid>
    </item>
    <item>
      <title>Data-Driven Approach to Designing Safety Service-Patrol Vehicles in Florida</title>
      <link>https://trid.trb.org/View/2720601</link>
      <description><![CDATA[Florida’s Road Ranger program plays a critical role in incident management but lacks a standardized vehicle design, resulting in inconsistent visibility and public recognition. This study presents a stakeholder-informed, data-driven approach to developing consistent design principles for safety service-patrol (SSP) vehicles in Florida. The methodology included a nationwide survey of 44 agencies, a review of national and international practices, and a series of stakeholder workshops. Based on these inputs, three key design principles were established: enhancing safety, improving recognition, and strengthening branding. Three vehicle-design prototypes were created and evaluated through post-design surveys of district program managers. The preferred design featured a fluorescent yellow-green base with blue accenting and received broad support for its visibility and clarity. This methodological framework and study findings offer actionable guidance for agencies seeking to implement cohesive SSP vehicle designs that improve responder safety and reduce motorist perceptual ambiguity.]]></description>
      <pubDate>Sat, 04 Jul 2026 16:35:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/2720601</guid>
    </item>
    <item>
      <title>From Concept to Reality: Augmented PDI Solutions Supporting Connected, Cooperative and Automated Mobility in Madrid</title>
      <link>https://trid.trb.org/View/2671780</link>
      <description><![CDATA[The work described in this paper provides valuable insight into the novel PDI solutions to be developed for CCAM support within the Horizon Europe-funded AUGMENTED CCAM project. To this aim, two different test sites are being prepared in Madrid, Spain, for the implementation and demonstration of four cutting-edge solutions: Equipped Vulnerable Road Users (VRU) protection; Traffic Management Optimization based on Probe Vehicle Data (PVD) from CCAM; Emergency Vehicle approaching; and Ad-hoc on-demand unmanned aerial vehicle (UAV) based VRU protection for closed environments. This document unveils how the proposed services underline the vast potential of CCAM when synergized with advanced Infrastructure support, which is not only limited to the extension of the Operational Design Domain of Connected and Automated Vehicles. This approach also demonstrates PDI’s capacity to significantly enhance road safety, traffic efficiency and sustainability. Additionally, the importance of the Digital Twin is highlighted as an indispensable element for advanced traffic management and comprehensive infrastructure monitoring.]]></description>
      <pubDate>Tue, 30 Jun 2026 16:05:35 GMT</pubDate>
      <guid>https://trid.trb.org/View/2671780</guid>
    </item>
    <item>
      <title>Enhancing the Performance of Emergency Vehicles Through Reinforcement Learning Based DVSL Control Systems</title>
      <link>https://trid.trb.org/View/2671023</link>
      <description><![CDATA[Variable Speed Limits (VSL) have been used to dynamically control traffic via the adaptation of vehicular speed with the aim to mitigate congestion, enhance safety and traffic flow performance. Recent studies have demonstrated the effectiveness of employing Deep Reinforcement Learning (DRL) techniques for VSL controllers, resulting in improved safety, efficiency, and environmental sustainability on highways. However, the conventional RL models for VSL control systems have not been trained to prioritize and facilitate the movement of emergency vehicles. This paper proposes a deep deterministic policy gradient (DDPG) algorithm which utilizes an actor-critic model by training the DVSL controller and a novel reward function to optimize the time loss of emergency vehicles across a highway weaving section. The results show that the proposed approach outperforms the baseline method with no VSL in terms of the accumulated waiting time, accumulated time loss, average time loss of emergency vehicles and the average travel time of all the vehicles.]]></description>
      <pubDate>Tue, 30 Jun 2026 09:45:09 GMT</pubDate>
      <guid>https://trid.trb.org/View/2671023</guid>
    </item>
    <item>
      <title>A generalized three-stage optimization model for emergency medical services under uncertainties: Integrating rescue station locations, ambulance deployment, and vehicle dispatch</title>
      <link>https://trid.trb.org/View/2614748</link>
      <description><![CDATA[The rapid pace of urbanization and increasing social complexity have made the efficiency of Emergency Medical Services (EMS) crucial for public safety and societal stability. Most existing studies analyze rescue station locations, ambulance deployment, and vehicle dispatch separately. However, these studies mainly focus on deterministic factors, such as travel time and rescue demand, without addressing uncertainties in real-world transportation networks and resource constraints. To overcome these limitations, this paper proposes a three-stage optimization model. The first two stages aim to determine the optimal layout of rescue stations and the number of vehicles to deploy, considering effective travel time instead of traditional Euclidean distance. The concepts of “contribution” and “fairness” are introduced to maximize vehicle service efficiency. The third stage applies a multi-objective scheduling strategy that integrates road network data. This study proposes an exact algorithm based on the greedy (EABG) approach. The results show significant improvements in demand coverage and response efficiency, despite limited resources. Sensitivity analysis confirms that fuzzy logic effectively handles demand uncertainty. These results offer actionable insights for EMS resource allocation and policy design, advancing emergency response strategies in complex urban environments. In addition, the proposed algorithm significantly outperforms GA in terms of solution speed and quality.]]></description>
      <pubDate>Wed, 17 Jun 2026 16:14:26 GMT</pubDate>
      <guid>https://trid.trb.org/View/2614748</guid>
    </item>
    <item>
      <title>An AI-Based Traffic Light Control System Using Yolov10 with Emergency and Public Bus Prioritization: A Case Study in Baghdad</title>
      <link>https://trid.trb.org/View/2676037</link>
      <description><![CDATA[The increasing desire for people to own personal cars, combined with their reluctance to use public transportation, has led to traffic jams and delays in emergency vehicle arrivals. Traffic lights in densely populated cities pose a significant challenge because they rely on fixed or variable timings, yet are not particularly effective. As a result, they can worsen congestion or cause traffic jams instead of alleviating it. For example, a city like Baghdad faces severe traffic congestion, requiring intervention from traffic police. Additionally, there is no specific system in place for emergency vehicle passage, and public transportation remains ineffective, as people are hesitant to use buses due to longer congestion times and the difficulty in navigating, which is exacerbated by their larger size compared to private small cars. Unlike previous YOLO-based systems, our system integrates emergency vehicle and public transport buses prioritization. It adjusts timing based on vehicle type, number, and estimated speed, showing a 31.11% improvement in flow efficiency and reducing queue delays by 21.64% compared to fixed-time signal systems. The improved algorithm can recognize all four vehicle classes (fire trucks, ambulances, public transport buses, and cars) with an accuracy of 85-99%, depending on vehicle density and complex lighting conditions.]]></description>
      <pubDate>Wed, 17 Jun 2026 12:23:23 GMT</pubDate>
      <guid>https://trid.trb.org/View/2676037</guid>
    </item>
  </channel>
</rss>