<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>Vehicle Actuated Signal Control System for Mixed Traffic Conditions</title>
      <link>https://trid.trb.org/View/2113562</link>
      <description><![CDATA[Actuated signal control (ASC) works based on vehicle actuations that utilize vehicle headway or count for signal control. However, under mixed traffic conditions, it is nearly impossible to obtain such data from all the vehicles in the traffic stream. Under such scenarios, the average delay of vehicles obtained from a representative sample of vehicles can be used as an input for signal control. This study evaluated the effectiveness of RFID sensors for real-time delay estimation where the average approach delay obtained from RFID sensors was used as the control variable for the working of an actuated signal control system at an isolated intersection. Based on the simulation results, it was observed that a penetration rate of 80% of total car volume in the traffic stream would effectively represent a vehicle actuated system that works based on delay from all vehicles in the traffic stream along with better performance in terms of percentage reduction in overall intersection delay.]]></description>
      <pubDate>Tue, 24 Feb 2026 08:30:16 GMT</pubDate>
      <guid>https://trid.trb.org/View/2113562</guid>
    </item>
    <item>
      <title>Study on the Spatiotemporal Characteristics of Pedestrians’ Secondary Crossing Behavior: Trajectory Feature Analysis Based on Deep Learning</title>
      <link>https://trid.trb.org/View/2613111</link>
      <description><![CDATA[This study analyzes the spatiotemporal characteristics of pedestrian secondary crossing behavior, focusing on the impact of traffic flow at signalized intersections. By examining the mechanism, steps, and key influencing factors, it employs CNN for spatial feature extraction and LSTM for temporal analysis of pedestrian trajectories. Video data collected via drones at the Nanjing Road and Gongqing Road intersection were processed using Tracker software. The results indicate that during peak hours, pedestrians exhibit smaller strides, slower speeds, and greater trajectory deviations, forming snake-like or arc patterns. In contrast, flat peak periods show larger strides, faster speeds, and fewer deviations. The proposed model outperforms others in the ETH and UCY data sets, achieving the lowest MAE, RMSE, and MSE. The findings offer valuable insights for improving pedestrian safety and efficiency in urban traffic planning.]]></description>
      <pubDate>Fri, 20 Feb 2026 15:28:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/2613111</guid>
    </item>
    <item>
      <title>Learning in practice: reinforcement learning-based traffic signal control augmented with actuated control</title>
      <link>https://trid.trb.org/View/2627356</link>
      <description><![CDATA[Most Reinforcement Learning (RL) based Traffic Signal Control (TSC) models are trained in simulation platforms, which inevitably suffer from the performance degradation after deployment due to the mismatch between the traffic simulator and the real-world traffic system. Toward the real-world training of TSC agents, this study integrates the actuated control into the RL-based TSC framework as a defense mechanism, enabling the traffic system to remain resilient to suboptimal actions of agent during the real-world training process. The introduction of actuated control can significantly reduce the green time wastes due to unreasonable timing plans. The numerical results demonstrate that the proposed approach can reduce interferences to the traffic system operation during the real-world training of TSC agents, particularly at the early stage of agent learning, thereby promoting the practical deployment of RL-based TSC models. Meanwhile, agents can converge to better signal policies with the help of defense mechanism.]]></description>
      <pubDate>Thu, 05 Feb 2026 16:39:49 GMT</pubDate>
      <guid>https://trid.trb.org/View/2627356</guid>
    </item>
    <item>
      <title>Inference of signal phase and timing with low penetration rate vehicle trajectories</title>
      <link>https://trid.trb.org/View/2597133</link>
      <description><![CDATA[Traffic signals are a crucial component of urban traffic networks, and signal phase and timing (SPaT) information serves as an essential input for various urban traffic operational applications. Obtaining SPaT information on a large scale is challenging due to the diversity of traffic signal controllers from different manufacturers and jurisdictions. With the advent of broadly defined connected vehicles, vehicle trajectories can be leveraged to estimate SPaT information since they are directly controlled by traffic signals. Although some existing studies have proposed methods for estimating SPaT information using vehicle trajectory data, most are limited to fixed-time traffic signals. To address this limitation, this paper proposes a suite of SPaT inference algorithms applicable to both fixed-time and responsive signals. With only low penetration rate vehicle trajectory data as input, the inference program can estimate the complete SPaT information for traffic signals with fixed cycle lengths and the average cycle/splits for those with time-varying cycle lengths. The proposed method is validated through case studies at real-world intersections.]]></description>
      <pubDate>Mon, 24 Nov 2025 15:30:52 GMT</pubDate>
      <guid>https://trid.trb.org/View/2597133</guid>
    </item>
    <item>
      <title>Explainable reinforcement learning for improved traffic signal control</title>
      <link>https://trid.trb.org/View/2604587</link>
      <description><![CDATA[Reinforcement learning has become a popular approach for traffic signal control, but its complexity often hinders practical application. To improve this, we propose a deep Q-network framework with an attention mechanism inspired by how traffic police manage intersections. This model aggregates vehicle data directly, avoiding the need for lane-based structures, and shows state-of-the-art performance across various scenarios. On a public dataset, it outperformed previous methods, achieving a 44% reduction in travel time and over 50% fewer queue lengths, compared to fixed-time control. Additionally, on a self-collected dataset, it improved the average travel time by 17.3% and queue length by 12% during peak hours. The method balances travel time, delay, and throughput while adapting to various traffic patterns, enhancing its effectiveness for traffic signal optimization. By visualizing attention weights on key vehicles, we provide transparency in decision-making, fostering trust among traffic agencies and the public.]]></description>
      <pubDate>Mon, 24 Nov 2025 10:23:28 GMT</pubDate>
      <guid>https://trid.trb.org/View/2604587</guid>
    </item>
    <item>
      <title>Traffic-Responsive Systems Through a Multidimensional State-Driven Approach</title>
      <link>https://trid.trb.org/View/2604109</link>
      <description><![CDATA[This paper presents a novel traffic-responsive control mechanism based on a multidimensional state representation. Traditional traffic-responsive systems often rely on oversimplified, one-dimensional representations of traffic conditions, which often result in suboptimal signal-timing decisions because of the loss of valuable network dynamics. Our study introduces a comprehensive multidimensional network-state representation, offering a more detailed and accurate reflection of prevailing traffic conditions. Utilizing K-means clustering, we identified and analyzed 16 distinct traffic states over a year on a 7.2?mi coordinated arterial in Delaware. This approach highlights the limitations of current one-dimensional systems and demonstrates the advantages of multidimensional representations for selecting signal-timing plans that better match actual traffic conditions. Key findings show that existing systems not only are time-intensive to set up and adjust but also prioritize tuning derived boundary measures over aligning with dominant traffic patterns. Our analysis reveals that multidimensional network representation can significantly reduce the setup time and improve the responsiveness and performance of the controlling mechanism. This advanced logic can be seamlessly integrated into existing advanced traffic-management systems (ATMS), providing a straightforward pathway for implementation and meaningful improvements in urban traffic management. The study concludes with recommendations for further research and potential enhancements to current traffic-responsive systems using this multidimensional approach.]]></description>
      <pubDate>Fri, 26 Sep 2025 16:33:17 GMT</pubDate>
      <guid>https://trid.trb.org/View/2604109</guid>
    </item>
    <item>
      <title>Guidelines for Implementing Traffic Responsive Mode in TxDOT Closed-Loop Traffic Signal Systems</title>
      <link>https://trid.trb.org/View/2539989</link>
      <description><![CDATA[This report provides guidelines and procedures for setting up a closed-loop traffic signal system to operate in a traffic responsive mode. It provides specific procedures for determining when two traffic signals should be coordinated. It also provides specific guidelines on when a closed-loop signal system should operate in a traffic responsive mode versus a time-of-day mode. Procedures are also provided for determining the thresholds that are needed to set up a system to operate in a traffic responsive mode. Finally, recommendations are provided on where to place system detectors to support the operation of a closed-loop signal system in a traffic responsive mode.]]></description>
      <pubDate>Tue, 29 Apr 2025 16:10:26 GMT</pubDate>
      <guid>https://trid.trb.org/View/2539989</guid>
    </item>
    <item>
      <title>Traffic signal priority (TSP) : final report : activity 5</title>
      <link>https://trid.trb.org/View/2534244</link>
      <description><![CDATA[The purpose of the TSP pilot is to test the deployment of a Traffic Signal Priority service that fulfils compatibility and interoperability in all parts of the ecosystem: vehicles, backend/“cloud” and roadside. Such compatibility is defined as compliance to applicable C-Roads documents, and all their underlying specifications and standards, wherever possible and necessary. Furthermore, the purpose is to reach a shared understanding of how the TSP service should be deployed, what architectural design choices are required, which standards and specifications are applicable, and what is not prescribed in these and must be designed within the framework of the pilot work. Another purpose is to get a common understanding of which stakeholders and actors are involved and how technical and financial responsibilities should be distributed when establishing a TSP service that can exist in a sustainable business model. The objective for the TSP pilot is to develop and demonstrate deployable infrastructure for a TSP service in a cross-domain environment between the emerging C-ITS field and the current, as well as future, PT, and traffic planning domains.]]></description>
      <pubDate>Fri, 04 Apr 2025 15:15:37 GMT</pubDate>
      <guid>https://trid.trb.org/View/2534244</guid>
    </item>
    <item>
      <title>Assessing effectiveness of intersection conflict warning system on driving performance under obstructed line of sight at unsignalized intersection</title>
      <link>https://trid.trb.org/View/2510604</link>
      <description><![CDATA[Intersection Conflict Warning System (ICWS) is an Intelligent Transportation System (ITS) technology that has been recognized as a solution to reduce crashes at unsignalized intersections. It consists of activated warning signs and sensors that detect vehicles approaching an intersection, transmitting a warning signal to potentially conflicting vehicles on other approaches. The current study examines the effect of ICWS on drivers driving performance while approaching an unsignalized intersection under obstructed line of sight. Four scenarios were developed to evaluate the effectiveness of ICWS. Driving performance measures such as mean and standard deviation of speed and deceleration, and driver factors such as age and number of driving days per week were analyzed using repeated measures ANOVA. Furthermore, duration variables such as response time and speed reduction time were modelled using Weibull Accelerated Failure Time (AFT) duration model. The study insights showed statistical differences among the four scenarios for all driving performance measures. The developed model revealed that with activated ICWS, drivers exhibited longer speed reduction times and shorter response times. This implies that with the activated ICWS, drivers managed to respond to the conflicting vehicle beforehand, resulting in less abrupt braking behavior and collision avoidance at the intersection. The study highlights the significance of ICWS and will assist traffic engineers and road safety authorities in designing and implementing ICWS at unsignalized intersections in developing world traffic.]]></description>
      <pubDate>Tue, 18 Mar 2025 15:48:12 GMT</pubDate>
      <guid>https://trid.trb.org/View/2510604</guid>
    </item>
    <item>
      <title>The lost art of crash investigation</title>
      <link>https://trid.trb.org/View/2509240</link>
      <description><![CDATA[Austroads’ original Treatment of Crash Locations guide in 2004 made the point that crash countermeasures are not general; each one needs to target a specific type of contributing factor or crash cause. This understanding is now largely lost. The site of Victoria’s first side-road-activated reduced speed limit signs is investigated. This treatment’s aim of reducing crash severities was not achieved. The author’s investigation concludes the main reason for this is that the likely crash causes were not identified. An alternative, low-cost treatment for the intersection is described. It is concluded that the most effective way to reduce crash severities can simply be to eliminate the crash causes.]]></description>
      <pubDate>Thu, 13 Feb 2025 09:06:26 GMT</pubDate>
      <guid>https://trid.trb.org/View/2509240</guid>
    </item>
    <item>
      <title>Time-to-Green Predictions for Fully-Actuated Signal Control Systems With Supervised Learning</title>
      <link>https://trid.trb.org/View/2402019</link>
      <description><![CDATA[Recently, efforts have been made to standardize signal phase and timing (SPaT) messages. These messages contain signal phase timings of all signalized intersection approaches. This information can thus be used for efficient motion planning, resulting in more homogeneous traffic flows and uniform speed profiles. Despite efforts to provide robust predictions for semi-actuated signal control systems, predicting signal phase timings for fully-actuated controls remains challenging. This paper proposes a time series prediction framework using aggregated traffic signal and loop detector data. The authors utilize state-of-the-art machine learning models to predict future signal phases’ duration. The performance of a Linear Regression (LR), Random Forest (RF), a light gradient-boosting machine (LightGBM), a bidirectional Long-Short-Term-Memory neural network (BiLSTM) and a Temporal Convolutional Network (TCOV) are assessed against a naive baseline model. Results based on an empirical data set from a fully-actuated signal control system in Zurich, Switzerland, show that state of the art machine learning models outperform conventional prediction methods.]]></description>
      <pubDate>Wed, 06 Nov 2024 16:48:45 GMT</pubDate>
      <guid>https://trid.trb.org/View/2402019</guid>
    </item>
    <item>
      <title>Predicting the Future Signalization of Traffic-Actuated Signals Using Extreme Gradient Boosting</title>
      <link>https://trid.trb.org/View/2447277</link>
      <description><![CDATA[Stops, braking, and acceleration maneuvers at traffic signals cause high fuel consumption and emission levels. Green light optimized speed advisory (GLOSA) can help to reduce a proportion of such unnecessary vehicle maneuvers. For this, GLOSA systems require reliable switching time estimations as input. However, estimating the switching times of traffic-actuated signals can be challenging. The signalization of traffic-actuated lights is adjusted to match the current traffic. Based on green-time requests, the status of signals can change with almost no lead time. This paper presents an approach for predicting the signalization of traffic-actuated signals. We exploit the limited nature of the space for switched signal state combinations at intersections, and express combinations of motorized traffic-related signal states as one feature to depict the motorized traffic signalization state (MTSSt) at an intersection. Predicting MTSSt-switches allows later determination of the switching times of individual signals. To conduct the predictions, the machine learning method “extreme gradient boosting” was used. A three-step methodology—data preparation, tuning the prediction procedure, and testing the approach—was applied and evaluated on the historical data of four traffic-actuated signalized intersections. The results showed that within a period of the next 30?s, signal changes were predicted with an overall precision and sensitivity of about 95% and an average mean absolute error of less than 1.1?s. In this period, the sequence of switched signals was predicted accurately to the second, without any deviation, in, on average, over 82% of cases.]]></description>
      <pubDate>Mon, 04 Nov 2024 08:39:41 GMT</pubDate>
      <guid>https://trid.trb.org/View/2447277</guid>
    </item>
    <item>
      <title>Multi-level traffic-responsive tilt camera surveillance through predictive correlated online learning</title>
      <link>https://trid.trb.org/View/2417747</link>
      <description><![CDATA[In urban traffic management, the primary challenge of dynamically and efficiently monitoring traffic conditions is compounded by the insufficient utilization of thousands of surveillance cameras along the intelligent transportation system. This paper introduces the multi-level Traffic-responsive Tilt Camera surveillance system (TTC-X), a novel framework designed for dynamic and efficient monitoring and management of traffic in urban networks. By leveraging widely deployed pan–tilt-cameras (PTCs), TTC-X overcomes the limitations of a fixed field of view in traditional surveillance systems by providing mobilized and 360-degree coverage. The innovation of TTC-X lies in the integration of advanced machine learning modules, including a detector–predictor–controller structure, with a novel Predictive Correlated Online Learning (PiCOL) methodology and the Spatial–Temporal Graph Predictor (STGP) for real-time traffic estimation and PTC control. The TTC-X is tested and evaluated under three experimental scenarios (e.g., maximum traffic flow capture, dynamic route planning, traffic state estimation) based on a simulation environment calibrated using real-world traffic data in Brooklyn, New York. The experimental results showed that TTC-X captured over 60% total number of vehicles at the network level, dynamically adjusted its route recommendation in reaction to unexpected full-lane closure events, and reconstructed link-level traffic states with best MAE less than 1.25 vehicle/hour. Demonstrating scalability, cost-efficiency, and adaptability, TTC-X emerges as a powerful solution for urban traffic management in both cyber–physical and real-world environments.]]></description>
      <pubDate>Mon, 16 Sep 2024 09:00:38 GMT</pubDate>
      <guid>https://trid.trb.org/View/2417747</guid>
    </item>
    <item>
      <title>Automatic Signal Retiming for Large Scale Networks with Vehicle Trajectory Data</title>
      <link>https://trid.trb.org/View/2425176</link>
      <description><![CDATA[Traffic signal optimization is known to be a cost-effective method for reducing congestion and energy consumption in urban areas without changing physical road infrastructure. However, due to the high installation and maintenance costs of detection systems, most intersections in practice are controlled by fixed-time traffic signals that rely on manual data collection and are not regularly optimized. Readily available vehicle trajectory data offers unprecedented opportunities for a more efficient use of existing infrastructure and resources. The recently developed OSaaS (Optimizing Signals as a Service) system uses vehicle trajectory data as the only input to optimize traffic signals. OSaaS allows us to easily monitor traffic performance, diagnose signal timing issues, and optimize signal timing parameters. However, to put OSaaS into practice, an automated process needs to be developed so that manual effort can be minimized. For example, traffic flow parameters such as saturation flow rate and free-flow speed can be calibrated automatically by using historical vehicle trajectory data. Therefore, the project will further develop OSaaS into a data-driven automatic signal retiming system that will update signal timing parameters for fixed-time and coordinated-actuated signalized intersections on an iterative basis (i.e., bi-weekly, monthly).]]></description>
      <pubDate>Wed, 04 Sep 2024 17:22:27 GMT</pubDate>
      <guid>https://trid.trb.org/View/2425176</guid>
    </item>
    <item>
      <title>Effective trigger speeds for vehicle activated signs on 20 mph roads in rural areas</title>
      <link>https://trid.trb.org/View/2378026</link>
      <description><![CDATA[]]></description>
      <pubDate>Thu, 09 May 2024 08:43:34 GMT</pubDate>
      <guid>https://trid.trb.org/View/2378026</guid>
    </item>
  </channel>
</rss>