<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>Efficient Directed Hypergraph Network for Unsupervised Traffic Anomaly Detection</title>
      <link>https://trid.trb.org/View/2685726</link>
      <description><![CDATA[Anomaly detection in traffic flow is crucial for ensuring the safety and stability of intelligent transportation systems. However, many transformer-based deep learning models suffer from extremely high computational complexity, making them unsuitable for real-time anomaly detection in resource-constrained terminal devices. Therefore, this article presents an efficient and fully unsupervised framework for traffic anomaly detection, termed the directed hypergraph message passing network (DHMPN). By integrating a directed hypergraph-based message passing module with bidirectional gated linear units (Bi-GLUs), DHMPN effectively captures complex spatiotemporal dependencies while maintaining low computational overhead, thereby addressing the practical demands of real-time anomaly detection. To enable accurate anomaly identification, the learned traffic representations are further modeled using a conditional normalizing flow, which facilitates precise density estimation and probabilistic anomaly scoring. Extensive experiments on real-world traffic benchmark datasets demonstrate that DHMPN significantly outperforms both traditional machine learning approaches and state-of-the-art graph-based deep learning models in anomaly detection tasks. Moreover, DHMPN achieves competitive performance in traffic forecasting, further validating the effectiveness of the proposed spatiotemporal encoding architecture.]]></description>
      <pubDate>Tue, 30 Jun 2026 17:03:42 GMT</pubDate>
      <guid>https://trid.trb.org/View/2685726</guid>
    </item>
    <item>
      <title>Real-World Deployment and Assessment of a Multiagent Reinforcement Learning-Based Variable-Speed-Limit Control System</title>
      <link>https://trid.trb.org/View/2685725</link>
      <description><![CDATA[This article presents the first field deployment of a multiagent reinforcement learning (MARL)-based variable-speed-limit (VSL) control system on Interstate 24 (I-24) near Nashville, TN, USA. We design and demonstrate a full pipeline from training MARL agents in a traffic simulator to a field deployment on a 17-mi segment of I-24 encompassing 67 VSL controllers. The system was launched on 8 March 2024 and has made approximately 35 million decisions on 28 million trips in six months of operation. We apply an invalid action masking mechanism and several safety guards to ensure real-world constraints. The MARL-based implementation operates up to 98% of the time, with the safety guards overriding the MARL decisions for the remaining time. We evaluate the performance of the MARL-based algorithm in comparison to a previously deployed non-RL VSL benchmark algorithm on I-24. The results show that the MARL-based VSL control system achieves a superior performance.]]></description>
      <pubDate>Tue, 30 Jun 2026 17:03:42 GMT</pubDate>
      <guid>https://trid.trb.org/View/2685725</guid>
    </item>
    <item>
      <title>Coordinated Decision Making for High-Speed Railway Train Timetable Rescheduling and Trajectory Control: Architecture, Algorithms, Simulation, and Applications</title>
      <link>https://trid.trb.org/View/2685724</link>
      <description><![CDATA[During emergency response in high-speed railway operations, dispatchers and drivers currently rely on individual experience for decision making, lacking effective coordination between train timetable rescheduling and trajectory control. This results in a train timetable with insufficient precision, failing to provide a global train trajectory, and ultimately making it difficult to handle train delays caused by emergencies promptly. To address this practical problem, this article constructs a novel architecture and proposes a real-time algorithm for coordinated decision making for train timetable rescheduling and trajectory control (CDM-TTRTC). The simulation and application experiments show that compared to the noncoordinated method using manual experience, the proposed CDM-TTRTC algorithm can reduce the total train delay by 17.18% and total energy consumption by 5.82%. In addition, it can generate a train timetable and multitrain trajectory within 3.49 s, providing dispatchers and drivers with more reasonable and efficient decision support.]]></description>
      <pubDate>Tue, 30 Jun 2026 17:03:42 GMT</pubDate>
      <guid>https://trid.trb.org/View/2685724</guid>
    </item>
    <item>
      <title>Urban Vehicle Trajectory Dataset Based on Drone Videos</title>
      <link>https://trid.trb.org/View/2685723</link>
      <description><![CDATA[Along with the advancement of lightweight sensing and processing technologies, drones become powerful tools for traffic data collection. This article proposes a learning-based vehicle tracking framework from drone videos, addressing key challenges such as camera instability and dynamic lighting conditions. A dynamic keyframe adaptation strategy and a lighting mask are incorporated to enhance robustness. The method is validated using drone videos covering the transition from day to night over a 380-m corridor with three intersections. Approximately 5,000 vehicle trajectories were extracted at 10 Hz, capturing the formation and dissipation of the evening rush hour. This dataset is unique in its duration, signal timing information, and corridor-level coverage, making it the first publicly available resource of its kind. Experiments demonstrate the high accuracy of the approach, achieving a precision of 0.983 and a recall of 0.996. The labeled vehicle datasets, code, and resulting trajectory data are publicly available to support further research in traffic analysis and digital twin systems.]]></description>
      <pubDate>Tue, 30 Jun 2026 17:03:42 GMT</pubDate>
      <guid>https://trid.trb.org/View/2685723</guid>
    </item>
    <item>
      <title>Toward Efficient Utilization of Low-Altitude Airspace: A Unified Approach Integrating Architecture Frameworks and Operations Research</title>
      <link>https://trid.trb.org/View/2685722</link>
      <description><![CDATA[This article presents a unified approach that integrates the unified architecture framework (UAF) with operations research to automate design and optimization of low-altitude airspace systems of systems. We extend the UAF domain metamodel with lightweight stereotypes within strategic, operational, service, resource, and actual resource views. An optimization bridge view generates solver-neutral mixed-integer linear programming models that minimize mission time while enforcing explicit energy budget and safety separation constraints and feeds the optimization results back into the architecture for iterative refinement. We validate the methodology on a 1,000-case urban logistics scenario by formulating a multidepot heterogeneous fleet vehicle routing problem (MDHFVRP) directly from the architecture models. The baseline architecture yields a mean operating time of 23.32 min, meeting the service target in 72.75% of cases. Introducing a moving-depot extension and solving the resulting moving MDHFVRP with a gradient-guided large-neighborhood search reduce the mean to 21.20 min, achieving the target in 96.09% of scenarios at a median solve time of 10.88 s. The coupled pipeline preserves full traceability from strategic goals to detailed optimization outputs and supports rapid tradeoff analysis and bottleneck diagnosis.]]></description>
      <pubDate>Tue, 30 Jun 2026 17:02:36 GMT</pubDate>
      <guid>https://trid.trb.org/View/2685722</guid>
    </item>
    <item>
      <title>Understanding Trust and Fatigue Under Transparency Regulation in Air Traffic Control: A Multimodal Approach</title>
      <link>https://trid.trb.org/View/2685721</link>
      <description><![CDATA[The integration of artificial intelligence and automation into safety-critical domains, such as air traffic management (ATM), raises new challenges in managing operators’ trust and fatigue under high-workload conditions. Although transparency regulation has been identified as a key factor shaping human–automation interaction, prior work has largely focused on driving or monitoring tasks. Little attention has been paid to managing complex work, such as air traffic control. Moreover, trust and fatigue are typically examined in isolation, with limited understanding of their dynamic interplay in human–machine collaboration. This article introduces a transparency-regulated ATM simulation platform that allows three fixed transparency levels (low, mid, and high) and a user-switchable (mix) mode, enabling controlled investigation of effects on operators’ trust and fatigue. Multimodal data were collected from eye tracking, electroencephalography, and system status logs under varying transparency and workload conditions. By applying machine learning and deep learning approaches, we compare unimodal and multimodal prediction of trust and fatigue. The results show that increasing transparency enhances operators’ understanding, trust, and willingness to rely on the system, while multimodal fusion achieves superior predictive accuracy compared with single-modality inputs. The findings reveal a positive but nonlinear coupling between trust and fatigue, suggesting that adaptive transparency can balance operators’ reliance and cognitive effort. In particular, temporal deep models exhibit strong sensitivity to eye tracking features. Overall, this article contributes a unified framework linking transparency regulation, multimodal state estimation, and adaptive interface design, offering theoretical and practical insights for building resilient ATM automation systems that maintain appropriate trust while mitigating fatigue risks.]]></description>
      <pubDate>Tue, 30 Jun 2026 17:02:36 GMT</pubDate>
      <guid>https://trid.trb.org/View/2685721</guid>
    </item>
    <item>
      <title>Automatic Lane Change Integrating Human Driving Experience Through a Two-Level Decision-Making Approach</title>
      <link>https://trid.trb.org/View/2685720</link>
      <description><![CDATA[Lane change is one of the basic and pivotal behaviors in autonomous vehicle driving that affects driving efficiency and safety. However, current lane change strategies lack the ability of timely adjustment and flexible decision making in response to the mixed traffic environment where autonomous and human-driven vehicles coexist. To address the issue, this article proposes a two-level decision-making strategy comprising an upper lane selection layer and a lower-trajectory learning layer for automatic lane change, which incorporate human driving experiences to achieve humanlike performance. The upper lane selection layer refrains from predefined driving styles but utilizes a convolutional neural network–bidirectional gated recurrent unit (CNN-BiGRU) network to capture the driving styles of both the ego vehicle and the surrounding vehicles. This layer selects the optimal lane by comprehensively considering the driving styles and traffic impact factors in the current scenario. The lower-trajectory learning layer’s trajectory generation module optimizes candidate trajectories based on the selected lane from the upper layer. The lane selection employs maximum entropy inverse reinforcement learning (MaxEnt IRL) through maximizing the cumulative reward, enhancing the probability of selecting humanlike trajectories. Evaluation results indicate that the proposed method can effectively learn a humanlike lane-changing strategy, which improves vehicle adaptability in complex traffic environments. The proposed method achieves 95.42% accuracy of lane selection and 0.788 human similarity of trajectory imitation.]]></description>
      <pubDate>Tue, 30 Jun 2026 17:02:36 GMT</pubDate>
      <guid>https://trid.trb.org/View/2685720</guid>
    </item>
    <item>
      <title>Scalable Passenger Detection Using Smartphone–Bus Implicit Interactions</title>
      <link>https://trid.trb.org/View/2672988</link>
      <description><![CDATA[Intelligent transportation systems (ITSs) are important for mobility as a service, enabling seamless access across various transport networks and fair revenue sharing. However, current user sensing technologies like walk in/walk out (WIWO) and check in/check out (CICO) face scalability issues. WIWO and CICO depend on fixed infrastructure to cover large dynamic passenger environments, making their large-scale deployment challenging and expensive. These limitations hinder effective analysis, optimization, and revenue sharing in ITSs. To address these issues, we build on the concept of implicit be-in/be-out (BIBO) smartphone sensing and classification, introducing a platform that collects Bluetooth Low Energy (BLE) signals from devices on buses and GPS data from both buses and smartphones. We propose a cause–effect multitask Wasserstein autoencoder (CEMWA) architecture to train a model using GPS features and BLE signals as mutual pseudolabels. CEMWA integrates various frameworks around Wasserstein autoencoders and neural networks, providing a validated latent space representation of users’ smartphones within the transport system. This representation facilitates BIBO clustering via density-based spatial clustering of applications with noise. Our comparative study of CEMWA’s architecture and benchmarking against best-in-class supervised methods reveals that, while Extreme Gradient Boosting and the random forest are robust to label noise, CEMWA’s design inherently handles label noise, achieving the best performance, with an 88% F1 score in a BIBO scenario.]]></description>
      <pubDate>Wed, 24 Jun 2026 13:22:06 GMT</pubDate>
      <guid>https://trid.trb.org/View/2672988</guid>
    </item>
    <item>
      <title>Spatiotemporal Graph Mixture of Experts for Highway Traffic Flow Prediction</title>
      <link>https://trid.trb.org/View/2672987</link>
      <description><![CDATA[With excellent learning ability, the pretrained large model is challenging the mainstream traffic prediction paradigm. However, the pretraining process of large spatiotemporal models still faces the problems of high training cost and fixed graph size limitation, which hinders the practical application of more flexible prediction models in intelligent transportation systems. To address these challenges, this article proposes the Spatiotemporal Graph Mixture of Experts (STGMoE), a novel framework that integrates dynamic graph message passing with an MoE mechanism. The proposed STGMoE framework takes multivariate time-series data as input and enables efficient conditional computation and flexible topological adaptation, ultimately facilitating accurate spatiotemporal feature extraction for downstream traffic prediction tasks. Experiments on the California PeMS and Beijing datasets demonstrate that the model outperforms mainstream methods in fully supervised prediction and zero-shot prediction, validating its generalization capability in complex and dynamic traffic environments.]]></description>
      <pubDate>Wed, 24 Jun 2026 13:22:06 GMT</pubDate>
      <guid>https://trid.trb.org/View/2672987</guid>
    </item>
    <item>
      <title>Scene-to-Scene Microscopic Traffic Dynamics Deduction: Integrating Simulation, Prediction, and Real-Time Monitoring</title>
      <link>https://trid.trb.org/View/2672986</link>
      <description><![CDATA[Microscopic traffic dynamics deduction, capable of reconstructing and predicting traffic states at 0.1–0.5-s temporal and 0.1–1-m spatial granularity with limited information, constitutes a critical foundation for traffic control and planning. Conventional deduction methods based on analytical car following models are oversimplified in parameters, and thus, they inadequately capture complex traffic dynamics, while higher-dimensional parametric deep learning-based methods suffer from poor iteration speed. As a compromise between speed and modeling capability, this article proposes a scene-to-scene autoregressive framework that fuses simulation, data-driven prediction, and real-time monitoring for microscopic traffic dynamics deduction. The methodology implements scene-level autoregressive deduction cycles rather than agent-based modeling while enhancing real-time accuracy through integration of connected vehicle (CV) future information. Evaluations using the International, Adversarial, and Cooperative Motion dataset demonstrate that the proposed simulation framework achieves comparable accuracy in a reasonable runtime. Real-time CV information incorporation is also proved to be effective for further accuracy improvements.]]></description>
      <pubDate>Wed, 24 Jun 2026 13:22:06 GMT</pubDate>
      <guid>https://trid.trb.org/View/2672986</guid>
    </item>
    <item>
      <title>A Structure-Aware Lane Graph Transformer Model for Vehicle Trajectory Prediction</title>
      <link>https://trid.trb.org/View/2672985</link>
      <description><![CDATA[Accurate prediction of future trajectories for surrounding vehicles is vital for the safe operation of autonomous vehicles. This study proposes a Lane Graph Transformer (LGT) model with structure-aware capabilities. Its key contribution lies in encoding the map topology structure into the attention mechanism. To address variations in lane information from different directions, four relative positional encoding (RPE) matrices are introduced to capture the local details of the map topology structure. Additionally, two shortest path distance (SPD) matrices are employed to capture distance information between two accessible lanes. The prediction results of the Argoverse 2 dataset indicate that the proposed LGT model can decrease the minimum final displacement error (minFDE6) metric by 60.73% compared to the nearest neighbor model and reduce the b-minFDE6 by 2.65% compared to the baseline LaneGCN model. Furthermore, ablation experiments demonstrated that the consideration of map topology structure led to a 4.24% drop in the b-minFDE6 metric, validating the effectiveness of this model. Our code is publicly available at: https://github.com/dongcaiyin/LGT2024.]]></description>
      <pubDate>Wed, 24 Jun 2026 13:22:06 GMT</pubDate>
      <guid>https://trid.trb.org/View/2672985</guid>
    </item>
    <item>
      <title>PODAR: A Collision Risk Model Offering Valid Signals for Vehicular Interactions</title>
      <link>https://trid.trb.org/View/2672984</link>
      <description><![CDATA[Acquiring valid signals for collision risk during driving is essential for the design of safety assistance or self-driving systems. Currently, there is a gap in accessible models that offer rational alerts for diverse driving scenarios. This article introduces a generalized, yet concise framework called the potential damage risk (PODAR) model for estimating collision risk and issuing warnings of hazard cases. The PODAR model is devised by connecting collision risk with potential collision damage across both spatial and temporal dimensions in a meaningful physical way, which includes four key components: trajectory prediction, damage estimation, spatiotemporal attenuation, and attention simulation. An empirical model featuring six adjustable parameters is presented and calibrated using a publicly available dataset for validation. With predefined fixed risk thresholds, the PODAR model demonstrates the ability to issue valid warnings for potential collisions in both longitudinal and lateral directions, negating the need for manual driving situation classification. The study investigates the performance of the PODAR model in a range of dynamic driving situations through numerical simulations, such as side-pass, car-following, and an unsignaled left turn. Additionally, three demonstrative cases derived from the InD dataset, which features realistic driving scenarios, are also presented. The results reveal that the PODAR model is effective in estimating risk and detecting collisions, providing reliable signals for potential collisions. In addition, the PODAR model, as a generalized framework, has the ability to incorporate existing metrics and exhibits impressive scalability to integrate new advancements in trajectory prediction and human-like risk perception, thanks to its modular structure.]]></description>
      <pubDate>Wed, 24 Jun 2026 13:22:06 GMT</pubDate>
      <guid>https://trid.trb.org/View/2672984</guid>
    </item>
    <item>
      <title>The Role of Integrity Monitoring in Connected and Automated Vehicles: Current State of Practice and Future Directions</title>
      <link>https://trid.trb.org/View/2625413</link>
      <description><![CDATA[Positioning integrity refers to the trust in the performance of a navigation system. Accurate and reliable position information is needed to meet the requirements of connected and automated vehicle applications, particularly in safety-critical scenarios. Receiver autonomous integrity monitoring (IM) and its variants have been widely studied for global navigation satellite system-based vehicle positioning, often fused with kinematic (e.g., odometry) and perception sensors (e.g., cameras). However, IM for cooperative positioning solutions that leverage vehicle-to-everything (V2X) communication has received comparatively limited attention. This article reviews existing research in the field of positioning IM and identifies various research gaps. Particular attention has been placed on identifying research that highlights cooperative-IM methods. It also examines key automotive safety standards and public V2X datasets to map current research priorities and uncover critical gaps. Finally, the article outlines promising future directions, highlighting research topics aimed at advancing and benchmarking positioning integrity.]]></description>
      <pubDate>Mon, 23 Feb 2026 11:23:12 GMT</pubDate>
      <guid>https://trid.trb.org/View/2625413</guid>
    </item>
    <item>
      <title>A Review of Trajectory Planning and Tracking Methods for the Tractor-Trailer System</title>
      <link>https://trid.trb.org/View/2625412</link>
      <description><![CDATA[Autonomous tractor-trailer systems (TTSs) are important carriers in intelligent logistics because of their large and flexible cargo capacities. As one TTS contains multiple cars that are connected with rigid articulations, its states and characteristics are much more complicated than those of a single-body vehicle, which brings great challenges for trajectory planning and tracking control methods. Therefore, we first analyze the kinematic and dynamic features of TTSs and then review the corresponding solutions in multiple modules, from parameter estimation, to model construction, to trajectory planning, and finally to trajectory tracking control modules. As there are several reviews on trajectory planning and tracking control methods of single-body vehicles, except for classifying the literature with techniques, we highlight the adjustment in the techniques due to TTSs’ complex characteristics. There are also abundant emerging methods applicable to TTSs specifically, which are supplemented in this work.]]></description>
      <pubDate>Mon, 23 Feb 2026 11:23:12 GMT</pubDate>
      <guid>https://trid.trb.org/View/2625412</guid>
    </item>
    <item>
      <title>MTRCP: Multimodal Two-Level Fusion Architecture for Roadside Cooperative Perception</title>
      <link>https://trid.trb.org/View/2625411</link>
      <description><![CDATA[With the rapid development of self-driving technologies, autonomous driving still faces challenges because of the complexity of traffic environments, making accurate and stable environmental perception crucial. Roadside units (RSUs) can significantly enhance the perception range of autonomous vehicles, effectively addressing blind spots and improving traffic safety. This article proposes the Multimodal Two-Level Fusion Architecture for Roadside Cooperative Perception, a novel framework that leverages RSUs to enable comprehensive and over-the-horizon perception capabilities. We fuse point clouds and images at the first level to generate local detection results and then perform a second-level fusion to integrate these local results, producing full-area perception. Experimental validation with the DAIR-V2X-seq dataset and data collected at the China Telecom Smart Grid Test Park demonstrates the effectiveness and feasibility of the proposed cooperative perception architecture.]]></description>
      <pubDate>Mon, 23 Feb 2026 11:23:12 GMT</pubDate>
      <guid>https://trid.trb.org/View/2625411</guid>
    </item>
  </channel>
</rss>