<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>Midblock Pedestrian Crossing Volumes and Crash Rates in Milwaukee, WI</title>
      <link>https://trid.trb.org/View/2691798</link>
      <description><![CDATA[Despite the majority of US fatal and severe pedestrian injuries occurring at midblock locations, few communities have collected counts to understand pedestrian midblock exposure and crash rates. This study developed a midblock pedestrian crossing count protocol and applied it to 61 street segments in the City of Milwaukee, WI. We counted midblock and adjacent intersection pedestrian crossings manually from 24-h video recordings. Midblock pedestrian crossings were common: 46 of the segments (75%) averaged more than one per hour. Among 48 segments with complete counts for both the midblock and an adjacent intersection crossing zone, 15 (31%) had more crossings in the midblock zone. We estimate that 17% of all pedestrian crossings along these 48 segments were midblock. Using these counts, we developed a negative binomial direct demand model of midblock pedestrian crossing volumes in Milwaukee. Midblock volumes were positively associated with nearby job density, commercial retail properties, and bus stops and negatively associated with posted speed limit and nearby parks. We demonstrated the value of this model by calculating pedestrian crash rates for all of our study segments and by estimating pedestrian crossing volumes for 133 additional street segments along seven roadway corridors. Expanding these methods beyond Milwaukee could lead to improved understanding of midblock pedestrian volumes and crash rates, ultimately helping communities reduce midblock pedestrian injuries and fatalities.]]></description>
      <pubDate>Tue, 14 Apr 2026 10:08:40 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691798</guid>
    </item>
    <item>
      <title>Investigating the effect of 30 km/h on neighborhood traffic safety perceptions- A three-wave repeated cross-sectional study in the Netherlands</title>
      <link>https://trid.trb.org/View/2681661</link>
      <description><![CDATA[Urban 30 km/h speed limits are increasingly implemented, potentially affecting perceived traffic safety. The authors assess how exposure to streets transitioning from 50 km/h to 30 km/h affects residents' traffic safety perceptions. The authors analyzed repeated cross-sectional data from two administrative surveys (N = 4968 and 5146) spanning 2015, 2017, and 2019. Exposure was defined as living within 400m of fifty-six streets across Rotterdam where speed limits reduced from 50 km/h to 30 km/h. Controls lived within 400m of streets undergoing future reductions. Using a difference-in-differences approach, the authors compared the probability of reporting seven binary outcomes on traffic-related safety, environmental annoyance, and pedestrian and cyclist safety between exposed and control individuals before and after speed limit reductions. The authors stratified the intervention group in tertiles of intervention street proportion within 400m Euclidian buffers, and additionally cross-sectionally investigated the association between dosage of intervention street density and perceived safety outcomes. No significant differences were observed between residents living near intervention streets and those near control streets. Small, non-significant improvements were found for perceived speeding (−4.6 percentage points (%pt) [95%CI -10.5,1.3]) and aggressive driving (−5.8%pt [95%CI -11.8,0.2]), while bicycle path safety showed a non-significant effect in the opposite direction (6.3%pt [95%CI -0.07,12.6]). The stratified analysis showed a non-significant improvement in the highest exposure tertile of sidewalk safety, but was inconclusive for the other indicators. Dosage findings indicated that a 5% increase in nearby intervention streets was associated with a lower probability of perceived speeding (−1.9%pt [95%CI −3.1,−0.6]), aggressive driving behavior (−1.5%pt [95%CI -3.1,0.04]) and increased bicycle path safety (−1.6%pt [95%CI -3.3,0.04]).Reducing urban speed limits to 30 km/h may have contributed to small, non-significant improvements in perceived traffic safety. The study may have been underpowered to detect statistically significant effects. Future studies should examine intended and unintended effects of traffic safety interventions.]]></description>
      <pubDate>Wed, 08 Apr 2026 13:40:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2681661</guid>
    </item>
    <item>
      <title>Optimal speed limit control for network mobility and safety: a twin-delayed deep deterministic policy gradient approach</title>
      <link>https://trid.trb.org/View/2643244</link>
      <description><![CDATA[Variable speed limit control (VSLC) has emerged as a promising approach for improving traffic safety and reducing congestion. However, local adjustment of VSLC may have broader impacts on the transportation network performance due to driver rerouting. This study proposes a deep reinforcement learning (DRL) controller based on twin-delayed deep deterministic policy gradient (TD3) algorithm to improve mobility and safety over a small-scale interconnected network considering rerouting behavior. The proposed DRL-based VSLC controller is designed to handle a large number of possible speed limits at each time step by utilizing a deep actor-critic framework. The study also experiments with different reward functions to characterize network mobility, safety, and traffic oscillation. Additionally, we investigate the sensitivity of the control algorithm across different traffic patterns, driving behavior, and VSLC locations, where the proposed TD3 algorithm demonstrated robustness and generalizability. Our findings indicate that implementing network-specific reward functions leads to improvements in traffic safety and mobility. Specifically, it results in a 3.84% enhancement in overall safety, as measured by time-to-collision metrics, and a 33.2% improvement in mobility by reducing total travel time compared to the scenario without VSL control. While comparable in safety performance, TD3 outperforms deep deterministic policy gradient (DDPG) algorithm by 15.1% in terms of mobility. This study contributes to the understanding of the impacts of VSLC on transportation networks and provides insights into effective ways of implementing VSLC to improve network mobility and safety.]]></description>
      <pubDate>Wed, 25 Mar 2026 15:50:27 GMT</pubDate>
      <guid>https://trid.trb.org/View/2643244</guid>
    </item>
    <item>
      <title>Influence of time pressure on the left-digit effect for reducing vehicle speeds</title>
      <link>https://trid.trb.org/View/2636336</link>
      <description><![CDATA[Controlling driving speed is one of the most effective strategies for reducing traffic accidents. Implementing a nudge based on the left-digit effect, such as displaying 49 km/h instead of 50 km/h on road signs, has been shown to be an effective way to reduce driving speeds. However, the utility of this approach might be limited by the presence of time pressure in typical traffic scenarios. This study examines how time pressure affects the impact of the nudge on driving speed. The findings indicate that despite the tendency for time pressure to increase vehicle speed, the left-digit effect remained effective.]]></description>
      <pubDate>Wed, 25 Mar 2026 11:43:31 GMT</pubDate>
      <guid>https://trid.trb.org/View/2636336</guid>
    </item>
    <item>
      <title>Modeling speed limit compliance in shared spaces</title>
      <link>https://trid.trb.org/View/2647963</link>
      <description><![CDATA[While shared spaces (also known as shared zones) encourage interaction among road users, non-compliance with posted speed limits is a key safety concern. Most research concerning drivers’ speeding behavior in shared spaces has predominantly centered on descriptive analyses and statistical testing, neglecting to account for the effects of shared space features, vehicle types, and traffic characteristics on speeds. As a result, there exists a significant knowledge gap regarding how the attributes of shared zones, surrounding traffic, and vehicle platoons impact driver speeds.  Speed data from two shared spaces in Australia were analyzed using left-censored Tobit regression models (non-compliant: continuous, compliant: zero) to assess drivers’ compliance with posted speed limits.  Results showed that the magnitude and probability of speeding were significantly reduced by the number of conflicts involving the vehicle and the provision of parking spaces in shared spaces. Conversely, vehicles such as cars, two-wheelers, and those with surrounding vehicles speeding exhibited lower compliance probabilities, while heavy vehicles and those following them showed higher likelihoods of compliance. However, the time of day or day of week had no significant influence on drivers’ speeding behavior, indicating consistent traffic interactions and compliance behaviors throughout the week.  This study identifies key factors influencing speeding behavior in shared spaces and provides insights for identifying countermeasures and promoting safer interactions.  The findings can help urban planners and policymakers set appropriate speed limits, develop better shared space designs, and enhance safety for all users, particularly those who are the most vulnerable.]]></description>
      <pubDate>Wed, 25 Mar 2026 11:43:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2647963</guid>
    </item>
    <item>
      <title>Integrated Freeway Traffic Control Using Q-Learning With Adjacent Arterial Traffic Considerations</title>
      <link>https://trid.trb.org/View/2561833</link>
      <description><![CDATA[Numerous studies have shown the effectiveness of intelligent transportation system techniques such as variable speed limit (VSL), lane change (LC) control, and ramp metering (RM) in freeway traffic flow control. The integration of these techniques has the potential to further enhance the traffic operation efficiency of both freeway and adjacent arterial networks. In this regard, we propose a freeway traffic control (FTC) strategy that coordinates VSL, LC, RM actions using a Q-learning (QL) framework which takes into account arterial traffic characteristics. The signal timing and demands of adjacent arterial intersections are incorporated as state variables of the FTC agent. The FTC agent is initially trained offline using a single-section road network, and subsequently deployed online in a connected freeway and arterial simulation network for continuous learning. The arterial network is assumed to be regulated by a traffic-responsive signal control strategy based on a cycle length model. Microscopic simulations demonstrate that the fully-trained FTC agent provides significant reductions in freeway travel time and the number of stops in scenarios with traffic congestion. It clearly outperforms an uncoordinated FTC and a decentralized feedback control strategy. Even though the FTC agent does not control the arterial traffic signals, it leads to shorter average queue lengths at arterial intersections by taking into account the arterial traffic conditions in controlling freeway traffic. These results motivate a future research where the QL framework will also include the control of arterial traffic signals.]]></description>
      <pubDate>Mon, 23 Mar 2026 17:14:34 GMT</pubDate>
      <guid>https://trid.trb.org/View/2561833</guid>
    </item>
    <item>
      <title>Study on Shape of Speed Humps According to Speed Limits Using Riding Experiments and Vehicle Vibration Simulation</title>
      <link>https://trid.trb.org/View/2669854</link>
      <description><![CDATA[Current technical standards in Japan specify detailed speed hump shapes for roads with a speed limit of 30 km/h; however, there are no technical standards for roads with a speed limit of 40 km/h. In this study, an experiment was conducted to determine the optimal hump shape for roads with a speed limit of 40 km/h. In the driving experiment, the acceleration of a passenger car passing over a hump was measured, and the discomfort of the subject was evaluated using a questionnaire. The jerk was calculated by differentiating the acceleration over time and was used to evaluate the discomfort. In the vehicle vibration simulation, a MATLAB Simulink model developed by Japan Automotive Model-Based Engineering was used to analyze the vehicle vibration. The authors identified a hump shape that causes the same level of discomfort at 40 km/h as at 30 km/h.]]></description>
      <pubDate>Mon, 23 Mar 2026 15:21:00 GMT</pubDate>
      <guid>https://trid.trb.org/View/2669854</guid>
    </item>
    <item>
      <title>Acceptability of Traveling Vehicle Mass Management on Residential Roads</title>
      <link>https://trid.trb.org/View/2669837</link>
      <description><![CDATA[To reduce the damage caused by traffic accidents involving pedestrians and bicycles, it is important to implement measures to control vehicle mass and speed. In particular, there is significance in understanding the acceptability of speed limit policies and route change policies considering vehicle mass. This study aimed to investigate the acceptability of vehicle mass management on residential roads. The survey used a crowdsourcing service and targeted 1,000 licensed drivers living in Japan. The results showed that drivers were significantly accepting speed changes based on vehicle mass, and pedestrians were significantly accepting measures implemented near their homes. In addition, the intention to comply with speed limits when measures are implemented based on vehicle mass was highest for penalties for non-compliance > increased premiums for non-compliance > reduced premium for compliance > awards for compliance. Therefore, regarding policy-based dissemination, reducing insurance premiums for drivers who obey the speed limit is the most effective measure for managing vehicle mass.]]></description>
      <pubDate>Mon, 23 Mar 2026 15:21:00 GMT</pubDate>
      <guid>https://trid.trb.org/View/2669837</guid>
    </item>
    <item>
      <title>MoDOT Work Zone Speed Study</title>
      <link>https://trid.trb.org/View/2680122</link>
      <description><![CDATA[Management of work zone speeds and ensuring driver compliance with work zone speed limits play an important role in reducing the number and severity of work zone crashes. The objective of this research study is to assess speeds driven by motorists in Missouri freeway work zones, including average speeds, 85th percentile speeds, maximum speeds, and levels of work zone speed limit compliance and noncompliance. The research methodology to meet this objective includes a literature review and field study to collect and measure work zone speed data. The field study included the measurement and analysis of speeds (with and without a work zone) for almost 5.5 million vehicles at five interstate work zones in Missouri. Probe data from HERE were also analyzed, and crashes corresponding to the dates and locations of the data collection were reviewed. Results from the literature review indicate that previous studies generally found various levels of speed limit compliance in work zones. The crash review identified four crashes across all sites during the time of the data collection, one of which was due to excessive speed. Overall, results from the analysis of field data and HERE data indicate prevalent speeding in Missouri work zones. While vehicle speeds were lower with the work zone compared to non-work zone conditions, speed variation with the work zone in place also increased. The presence of workers in the closed lane separated by channelizers on I-44 was associated with lower speeds and greater speed limit compliance. Possible strategies to reduce speeds and improve speed limit compliance in Missouri work zones could include law enforcement presence, speed feedback trailers, public outreach campaigns, and reviewing existing policies on setting work zone speed limits.]]></description>
      <pubDate>Mon, 23 Mar 2026 08:34:48 GMT</pubDate>
      <guid>https://trid.trb.org/View/2680122</guid>
    </item>
    <item>
      <title>Simulation Verification of Dynamic Speed Limit Control Method for Continuous Downhill Sections of Expressway</title>
      <link>https://trid.trb.org/View/2613309</link>
      <description><![CDATA[Focusing on the issue of how to calculate reasonable speed limits based on real-time changing traffic flow and intervene in traffic operation status when traffic accidents or reduced capacity occur on continuous downhill sections of highways, taking into account factors such as road alignment and meteorological environment, a dynamic speed limit model for continuous downhill sections of highways is proposed. This model is of great significance for improving the safety and traffic efficiency of highways under adverse conditions, helping to alleviate traffic congestion and reduce accident risks. The novelty of this study lies in the comprehensive consideration of multidimensional factors such as road alignment and meteorological environment, achieving dynamic adjustment of speed limit values. Analyze the VISSIM simulation data of continuous downhill traffic flow operation on the Chongqing section of the G65 Baomao Expressway, compare the analysis results of travel time, delay time, average speed, and other indicators in fixed speed limit and dynamic speed limit scenarios, and verify the effectiveness of the dynamic speed limit control method. The results show that in a rainy and foggy environment, when traffic accidents occur upstream of the slope bottom section of the continuous downhill section of the expressway, the dynamic speed limit on the continuous downhill section of the expressway reduces the total travel time of vehicles by 11.39%, the total delay time reduces by 30.51%, and the average speed increases by 12.97% compared to the fixed speed limit. The dynamic speed limit control method can better reduce traffic congestion and evacuation time and improve the traffic efficiency of the section. This study fills the gap in the current traffic management field regarding speed limit strategies for continuous long downhill sections, providing strong theoretical support and practical guidance for the safety and efficiency management of future highways.]]></description>
      <pubDate>Fri, 20 Mar 2026 14:10:52 GMT</pubDate>
      <guid>https://trid.trb.org/View/2613309</guid>
    </item>
    <item>
      <title>From prediction to explanation: A machine learning and causal mediation framework for roadway crash risk with connected vehicle data</title>
      <link>https://trid.trb.org/View/2633646</link>
      <description><![CDATA[Traditional safety analysis often relies on static roadway attributes and crash frequencies, lacking insight into the behavioral mechanisms through which the roadway environment influence crash occurrence. To address this gap, this study proposes a novel machine learning–guided causal framework that integrates crash risk classification with causal mediation analysis to uncover the behavioral pathways linking road environment factors to crash risk. First, an ensemble learning framework is developed to classify high-risk road segments using connected vehicle (CV) data, where a double-layer meta-soft voting model achieves the best performance (AUC = 0.879; F1 = 0.655). Second, a Double Machine Learning (DML)–based mediation analysis is employed to quantify the indirect effects of operating speed and speed deviation in transmitting the impact of contextual features (e.g., speed limit, sidewalk coverage, building density) on crash risk. The findings demonstrate that operating speed and speed deviation significantly mediate the effects of posted speed limits, whereas abrupt driving maneuvers (e.g., hard braking) do not serve as structural mediators. Notably, the strength and structure of these mediation pathways vary across functional road classes, highlighting spatial heterogeneity in behavioral responses. The results support a shift from reactive, regulation-centric strategies to behavior-aware safety interventions informed by CV data. Practical recommendations include incorporating CV-derived metrics into real-time safety monitoring and prioritizing adaptive speed controls on collector and local roads. By bridging predictive analytics and causal inference, this study enhances the methodological toolkit for traffic safety research and contributes to a greater understanding of how roadway design, driver behavior, and crash risk interact through quantifiable mechanisms.]]></description>
      <pubDate>Tue, 10 Mar 2026 09:56:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2633646</guid>
    </item>
    <item>
      <title>Meta-Reinforcement Learning with Hypernetworks for Variable Speed Limit Control under Adverse Weather and Work Zones</title>
      <link>https://trid.trb.org/View/2675553</link>
      <description><![CDATA[Variable speed limits (VSL) have been widely implemented to alleviate highway congestion and enhance operational efficiency. However, most existing studies focus on fixed traffic scenarios, making them inadequate when addressing uncertainties such as fluctuating traffic flows, extreme weather conditions, and construction-induced closures. Consequently, traditional VSL control strategies exhibit limited adaptability and generalization capability in unfamiliar scenarios. To overcome these limitations, this paper proposes a VSL control strategy based on Meta-Reinforcement Learning (Meta-RL) and Multi-Agent Proximal Policy Optimization (MAPPO) (Meta-MAPPO). This method leverages the meta-learning mechanism of Meta-RL and integrates a Hypernetwork module to dynamically adjust the network parameters of the control policy. By doing so, it adapts to diverse traffic scenarios and environmental disturbances, facilitating rapid policy transfer across scenarios and enhancing control performance. The training results demonstrate that Meta-MAPPO achieves faster convergence and superior model performance than MAPPO and Meta Multi-Agent Soft Actor-Critic (Meta-MASAC). Simulation experiments reveal that, compared with traditional feedback control methods and conventional multi-agent RL approaches, Meta-MAPPO exhibits significant advantages in unseen scenarios: it effectively mitigates traffic congestion and substantially reduces total travel time. The findings provide a more applicable solution for the practical implementation of VSL and offer valuable insights for further exploration of multi-agent methodologies in intelligent transportation systems.]]></description>
      <pubDate>Mon, 02 Mar 2026 13:29:09 GMT</pubDate>
      <guid>https://trid.trb.org/View/2675553</guid>
    </item>
    <item>
      <title>Evaluation of the safety improvement effects and adaptability of speed limit measures on downhill curved sections of mountainous freeways</title>
      <link>https://trid.trb.org/View/2659613</link>
      <description><![CDATA[Downhill curved segments of mountainous freeways are high-risk locations due to the combined effects of longitudinal potential energy and lateral centrifugal forces, and speed limit optimization is a key measure for mitigating crash risk on such segments. However, conventional speed limit settings often rely on uniform standards and fail to adequately account for the combined influences of roadway geometry, slope, traffic conditions, and weather, resulting in heterogeneous safety outcomes across different road environments. This study employs a Causal Forest model with explicitly incorporated quarterly time variables, complemented by a Difference-in-Differences (DID) model, to evaluate the safety effectiveness of speed limit optimization on downhill curved segments of the Guidu Freeway. Empirical results indicate that speed limit measures significantly reduce crash risk, with the Causal Forest model estimating an average treatment effect (ATE) of −0.203 (95% confidence interval: −0.213 to −0.193), demonstrating high precision and robustness and outperforming the DID model in estimation stability. Heterogeneity analysis further reveals that the safety benefits are most pronounced on segments with relatively mild horizontal curvature, low curvature variability, and moderate downhill slopes, as well as under moderate traffic volumes (approximately 7,500–9,000 vehicles/day), while higher truck proportions weaken the effectiveness of the measures. In contrast, fog frequency exerts a relatively limited moderating effect, as treatment effects remain negative across different fog conditions. Overall, the findings confirm that speed limit optimization can substantially improve safety on downhill curved segments of mountainous freeways and highlight the importance of accounting for roadway geometry and traffic composition when designing targeted speed management strategies.]]></description>
      <pubDate>Wed, 25 Feb 2026 13:58:58 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659613</guid>
    </item>
    <item>
      <title>Multi-Objective Optimisation of a Variable Speed Limit Control Strategy in a Tunnel Maintenance Work Zone of the Mountain Highway</title>
      <link>https://trid.trb.org/View/2643350</link>
      <description><![CDATA[Variable Speed Limit (VSL) control is essential for managing highway tunnel maintenance work, as it adjusts speed limits based on road conditions to regulate traffic flow. Developing a VSL control strategy that balances traffic efficiency and safety during maintenance can be challenging. This paper addresses this issue by proposing a VSL control strategy based on Model Predictive Control (MPC) that considers the spatial characteristics of traffic flow in a tunnel maintenance work zone. The strategy aims to minimise total travel time, reduce speed variance, and maximise traffic flow through a multi-objective optimisation approach using a Non-dominated Sorting Genetic Algorithm II (NSGA-II). With the Qinling Tiantai Mountain Tunnel selected as the experimental object, a simulation section is constructed based on the SUMO model with the measured data, and a comparative experiment of different speed limit control cycles in the maintenance work zone is designed. The results show that the method of this paper can effectively reduce the total travel time under the influence of maintenance operations by more than 17.5%, reduce the standard deviation of speed by about 22.1%, and enhance the traffic volume by about 7.8%, which can effectively improve the efficiency of road access and safety level.]]></description>
      <pubDate>Tue, 24 Feb 2026 09:01:00 GMT</pubDate>
      <guid>https://trid.trb.org/View/2643350</guid>
    </item>
    <item>
      <title>Prioritizing residential area for traffic policy by utilizing passive data</title>
      <link>https://trid.trb.org/View/2647790</link>
      <description><![CDATA[Expansion of roads with 30 km/h speed limits are planned to make citizen’s lives safer. As for Japan, the Zone30/30Plus (Z30) policy has been introduced for many years and the necessity of such traffic policies is increasing now. Although local governments need to identify and prioritize places where such limitations effectively work, currently their decisions rely on simple criteria. In this study, we propose the prioritizing scoring method based on current Z30 area features by utilizing passive data. We utilize passive data including floating car data (FCD) to make a feature vector for each standard mesh. The feature vector for each mesh consists of not only geographic data but also the FCD like sudden deacceleration rate (SDR) on narrow roads in residential areas and so on. The LightGBM classifier is used to classify prioritizing areas and cross entropy is used evaluation metric. We apply the method to prioritize next Z30 mesh candidates in Gifu-city, Japan. As training data, we annotated labels to meshes: Z30 meshes as high priority areas, and low importance meshes as low priority areas. The proposed model reveals Vehicle-Kilometers Traveled and population density under 15 years old are high importance features, but SDR is relatively lower. It identifies that existing Z30s have the possibility that have not been considered SDR as high risky driving behavior. The prioritizing result of the candidates shows that the nine highest prioritized meshes are not only near the existing Z30s but also a little further away.]]></description>
      <pubDate>Fri, 20 Feb 2026 15:28:25 GMT</pubDate>
      <guid>https://trid.trb.org/View/2647790</guid>
    </item>
  </channel>
</rss>