<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>Navigating uncertainty: Safety solutions for autonomous vehicle integration into mixed-mode mobility</title>
      <link>https://trid.trb.org/View/2732790</link>
      <description><![CDATA[Uncertainty fundamentally shapes human perception and decision-making, a factor that is becoming increasingly critical as autonomous vehicles (AVs) begin to share physical and social spaces with humans. This perspective paper synthesizes insights from neuroscience, robotics, and behavioral science represent uncertainty and act under it. The authors identify a significant disconnect between low-level mathematical concepts of uncertainty and risk, the uncertainty-aware prediction and planning methods used in robotics, and the high-level psychological uncertainty experienced by humans. Here, the authors conceptualize an integration pathway for mixed-mode mobility: the authors show that all three treat control under partial information as the same two-stage problem – probabilistic inference of the current and future state, followed by a risk-weighted choice of action – and the authors make this shared structure explicit. The authors thus argue that AVs should quantify and calibrate their own uncertainty, select risk metrics that reflect both individual and collective safety, model how their actions shape human uncertainty and behavior, and communicate intent and confidence in ways that support predictable interaction. This synthesis positions psychological uncertainty as a behaviorally relevant variable for AV design and outlines a research agenda for safer, more understandable transport systems.]]></description>
      <pubDate>Thu, 13 Aug 2026 17:03:27 GMT</pubDate>
      <guid>https://trid.trb.org/View/2732790</guid>
    </item>
    <item>
      <title>Mitigating driver confusion and aggression in mixed traffic: Effects of V2V communication and driving style</title>
      <link>https://trid.trb.org/View/2737140</link>
      <description><![CDATA[Drivers in human-driven vehicles (HDVs) can get confused when encountering automated vehicles (AVs) driving so defensively that their behavior differs from what human drivers actually expect. The confusion may potentially provoke aggression toward AVs and jeopardize traffic safety. This study investigated whether a vehicle-to-vehicle (V2V) communication system can help mitigate HDV drivers’ confusion and aggressive driving behavior toward AVs in HDV-AV interaction, considering the driving styles of both HDV drivers and AVs. Forty-eight participants, classified by driving style (defensive, moderate, or aggressive), completed a driving simulator experiment in two blocks (V2V-off vs. V2V-on). In each block, they interacted with aggressive AVs and defensive AVs, respectively. Behavioral indicators of confusion and aggressive driving behavior were recorded from the driving simulator, and subjective confusion was measured via questionnaires. The results showed that compared to the V2V-off condition, interaction under the V2V-on condition significantly reduced HDV drivers’ confusion and mitigated aggressive driving behavior during the interaction. Aggressive AVs that asserted their right-of-way elicited less confusion among HDV drivers than defensive AVs that were more inclined to yield to other vehicles. These findings suggest that V2V communication and aggressive yet rule-compliant AV driving styles help reduce driver confusion and aggressive driving behavior, thereby improving HDV drivers’ experiences and reducing conflict risk during HDV-AV negotiations.]]></description>
      <pubDate>Thu, 13 Aug 2026 17:03:26 GMT</pubDate>
      <guid>https://trid.trb.org/View/2737140</guid>
    </item>
    <item>
      <title>Eco-Driving Strategies in Autonomous and Manual Vehicle Interaction</title>
      <link>https://trid.trb.org/View/2579488</link>
      <description><![CDATA[The interplay between autonomous and manual vehicles in mixed traffic situations is a matter of concern as it may significantly affect the overall performance of the transportation system. Furthermore, two critical issues must be addressed: the transportation system's energy consumption and environmental impact. A more profound comprehension of mixed traffic dynamics, where autonomous and human-driven cars coexist, is necessary to navigate the transition from current conditions to an ecosystem entirely dominated by autonomous vehicles. To tackle these issues, this article aims to develop eco-driving approaches that reduce environmental effects and enhance energy efficiency. The case study under consideration is a roundabout with heavy traffic, and it examines how the total number of vehicles exiting the roundabout varies based on multiple input criteria. As a result, it was noted that the quantity and manner in which autonomous vehicles enter the roundabout from the priority road could affect the number of traditional vehicles that enter the yielding road. Increasing traffic flow in the roundabout can mean less fuel consumed and reduced emissions. To simulate the traffic in the roundabout, a model was developed in the MATLAB® program, and the actors, which are autonomous or classic vehicles characterized by functional characteristics, ran in various scenarios to determine optimal solutions for smoothing the traffic.]]></description>
      <pubDate>Wed, 12 Aug 2026 17:07:35 GMT</pubDate>
      <guid>https://trid.trb.org/View/2579488</guid>
    </item>
    <item>
      <title>A Multi-Lane Cellular Automata Model Considering Connected Automated Vehicle Platoons for Mixed Traffic Flow</title>
      <link>https://trid.trb.org/View/2731833</link>
      <description><![CDATA[Vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) technologies enable connected and automated vehicles (CAVs) to drive in platoons and realize cooperative driving. To investigate the impact of CAVs and platoons on multi-lane mixed traffic flow, this paper proposes a multi-lane cellular automata model considering the self-organized strategy of CAV platoons, which can describe the LC behaviors of CAV platoons. First, different car-following (CF) modes are introduced, and the CF characteristics and the lane-changing (LC) motivations of vehicles in different CF modes are analyzed. Then, based on CF characteristics and LC motivations, CF rules and LC rules for vehicles in different CF modes are designed, and the multi-lane cellular automata model considering the self-organized strategy of CAV platoons is developed. Finally, the impact of the LC behaviors of CAV platoons on the mixed traffic flow is investigated based on the numerical simulation. Numerical simulation results showed that: (1) benefiting from the LC behaviors of CAVs, CAVs can significantly improve traffic capacity and average velocity in the two-lane scenario compared to the single-lane scenario. When the penetration rate (PR) is 80%, the capacity of one lane and average velocity in the two-lane scenario increases by 14.3% and 41.4%, respectively, compared to the single-lane scenario. (2) under the same PR of CAVs, the LC frequency showed a tendency of increasing and then decreasing with the density increase. Besides, as the PR of CAVs increases, the LC frequency decreases. (3) CAVs are significantly more effective in alleviating traffic congestion at a low density than at a high density. (4) when the PR of CAVs is not higher than 40%, the maximum platoon size has almost no effect on traffic capacity and velocity. As the PR of CAVs increases, the effect of maximum platoon size gradually becomes significant.]]></description>
      <pubDate>Wed, 12 Aug 2026 15:14:56 GMT</pubDate>
      <guid>https://trid.trb.org/View/2731833</guid>
    </item>
    <item>
      <title>A Connectivity-Based Real-Time Traffic Prediction Considering Lane-Changing Maneuvers with Application to Eco-Driving Control of Electric Vehicles</title>
      <link>https://trid.trb.org/View/2731694</link>
      <description><![CDATA[Connected vehicles (CVs) exchange information with other CVs and intelligent infrastructure, enhancing traffic state predictions like speed and density. This aids in developing planning and control algorithms for CVs, including eco-driving controls that rely on future traffic conditions. However, predicting traffic states in real-time for the next 10–15 s is challenging, especially with mixed traffic conditions containing CVs and an unknown number of human-driven vehicles (HVs). Lane changes further complicate the problem, especially around vehicles equipped with eco-driving controllers. The slow driving speed of eco-driving vehicles before intersections during red signal phases may prompt other HVs to overtake them, resulting in more frequent lane changes. To address this, we integrate a macroscopic traffic flow model with a microscopic car-following model for traffic prediction. The Payne-Whitham (PW) model is modified to account for the impact of lane changes on the evolution of traffic states. An unscented Kalman filter (UKF) is used to estimate traffic states ahead of the ego vehicle using information from CVs. The algorithm then propagates the PW model to predict future traffic states and computes the trajectory of the immediate preceding vehicle based on these predictions. Using these results, we formulate an eco-driving co-optimization problem for connected and autonomous electric vehicles (CAEVs), taking into account vehicle dynamics, powertrain operation and battery operation. Traffic scenarios from both Simulation of Urban MObility (SUMO) and real-world road tests are used to evaluate the performance of our approach. Results show a reduction in traffic prediction error of up to 35.95% and an improvement in energy efficiency for the ego vehicle by up to 13.14%. Furthermore, our approach consistently benefits the ego vehicle under different CV penetration rates.]]></description>
      <pubDate>Wed, 12 Aug 2026 15:14:55 GMT</pubDate>
      <guid>https://trid.trb.org/View/2731694</guid>
    </item>
    <item>
      <title>Information-Assisted Learning Traffic Control of Multiclass Vehicular Road Networks with Uncertain Capacity</title>
      <link>https://trid.trb.org/View/2731646</link>
      <description><![CDATA[A two-phase Information-Assisted Learning Traffic Control (IALTC) is proposed to enhance a multiclass vehicular network consisting of connected automated vehicles (CAVs) and human-driven vehicles (HDVs) under uncertainty. To effectively capture time-varying vehicular flow, a stochastic multiclass vehicular model can be proposed. For the first phase, a multiclass adaptive traffic signal control is proposed to reduce traffic congestion. For the second phase, a multiclass vehicular route control is provided to enhance traffic efficiency. To effectively reduce computational burden, a novel coevolutionary heuristic can be proposed for a high-dimensional complex vehicular network. Extensive numerical experiments are performed at a real-world city under various kinds of traffic conditions when compared to intelligent traffic control under uncertainty. As it reported, the proposed IALTC can significantly improve traffic efficiency against time-varying disturbance of uncertainty while reducing effect of dimensionality for mixed traffic with various market penetrations of CAVs.]]></description>
      <pubDate>Wed, 12 Aug 2026 15:14:55 GMT</pubDate>
      <guid>https://trid.trb.org/View/2731646</guid>
    </item>
    <item>
      <title>Enhancing Universal Mixed-Autonomy Channel Modeling with Explainable Artificial Intelligence</title>
      <link>https://trid.trb.org/View/2731736</link>
      <description><![CDATA[In the forthcoming transportation landscape, the integration of Connected and Automated Vehicles (CAVs) with traditional human-driven traffic environments presents a multifaceted challenge. In this mixed-autonomy scenario, the coexistence of CAVs and Human-Driven Vehicles (HDVs) necessitates the sharing of road space and resources, all while striving to ensure safety and transportation efficiency. Within this dynamic context, the rapid and accurate prediction of channel quality becomes paramount for ensuring system stability and reliability. However, the inherent complexity and variability of such traffic environments introduce a multitude of interfering factors that conventional channel models struggle to address effectively. Thus, the development of a universal mixed-autonomy channel model that can adapt to diverse conditions and enhance communication quality is of paramount importance. Our proposed channel model, enhanced by Explainable Artificial Intelligence (XAI), encompasses system design of comprehensive mixed-autonomy environments, data collection, Machine Learning (ML) training, feature analysis using SHapley Additive exPlanation (SHAP), and performance validation. This model, underpinned by rigorous data-driven analysis, enables precise and efficient predictions of channel characteristics, offering a flexible and impactful solution that advances the intelligence of mixed-autonom systems and enhances communication reliability.]]></description>
      <pubDate>Wed, 12 Aug 2026 15:14:54 GMT</pubDate>
      <guid>https://trid.trb.org/View/2731736</guid>
    </item>
    <item>
      <title>1D and 2D trajectory optimization in weaving segments under a unified risk field framework: cooperative merging control strategy towards mixed traffic environment</title>
      <link>https://trid.trb.org/View/2709690</link>
      <description><![CDATA[Ramp merging in the mixed traffic environment of weaving segments requires connected and autonomous vehicle (CAV) technologies to achieve precise trajectory control. However, pre-merge one-dimensional trajectory optimization (1DTO), which coordinates longitudinal speeds among multi-vehicles to create merging gaps (global optimization), and lane-changing two-dimensional trajectory optimization (2DTO), which plans precise lateral maneuvers for the merging vehicle (individual optimization), are typically addressed separately. This separation causes each stage to employ independent risk assessment criteria and trajectory optimization objectives, thereby leading to suboptimal merging performance in terms of safety, efficiency, and stability. To overcome these limitations, we propose a unified merging sequence (MS), 1DTO, and 2DTO framework for multi-lane mixed traffic in weaving segments based on a risk field paradigm. First, we introduce a subjective-objective driving risk assessment method: CAVs utilize an objective risk field, while human-driven vehicles (HDVs) employ a subjective field coupling driver cognition. We then developed car-following models (SORFCF-CAV and SORFCF-HDV) to resolve the accuracy deficiencies of the IDM. Furthermore, we design a joint optimization framework integrating MS, 1DTO, and 2DTO. Strategies include: (i) SORFCF-CAV with virtual car-following for 1DTO; (ii) extending 1DTO for cooperative 2DTO via fifth-order polynomials; and (iii) a spatial-temporal risk occupancy map for safety-oriented 2DTO in non-cooperative cases. Extensive experiments demonstrate that the proposed strategy: (i) significantly outperforms multiple baselines in enhancing safety, merging efficiency, and traffic stability across various scenarios; (ii) exhibits a steady upward performance trend as the CAV penetration rate increases; and (iii) maintains excellent real-time computational efficiency even in extremely complex environments.]]></description>
      <pubDate>Wed, 12 Aug 2026 15:14:52 GMT</pubDate>
      <guid>https://trid.trb.org/View/2709690</guid>
    </item>
    <item>
      <title>Dynamic control protocol for connected commercial fleets</title>
      <link>https://trid.trb.org/View/2736788</link>
      <description><![CDATA[Connected commercial fleets (CFs), such as logistics carriers and ride-hailing fleets, are becoming increasingly prevalent in modern transportation systems. Unlike self-interested users (SUs), who attempt to minimize their individual travel costs, CFs aim to minimize fleet-specific operational costs. Simultaneously, a transportation management center (TMC), acting as a system regulator, is tasked with optimizing overall network performance. This paper proposes a dynamic control protocol to guide CFs toward achieving the best possible traffic state (BPTS), characterized by the minimization of the system’s total travel time. We first formulate the BPTS in a mixed traffic environment where SUs and CFs coexist and analyze its properties and implications. A dynamic control protocol framework is then developed, where the TMC broadcasts control signals to guide CFs to update their routing patterns iteratively. The framework is developed in a decentralized approach, which can circumvent the challenges of accessing information from individual fleets. Further, the adaptability of the proposed protocol is demonstrated as it can have adaptive control intensity on CFs and is robust to asynchronous routing updates across SUs and CFs. The proposed framework serves as an analytical foundation for developing control schemes that guarantee the convergence of network flow to the BPTS. Specifically, by exploiting the commercial nature of CFs, we devise toll and subsidy schemes that can achieve revenue neutrality across them. Two notions of revenue neutrality are analyzed. The first is system-wide revenue neutrality, which can be achieved through uniform pricing across all CFs, but may lead to revenue redistribution among them, though the redistribution is quantitatively tied to each CF’s system impact. The second is CF-specific revenue neutrality, which can only be achieved through differentiated pricing, but can minimize public resistance as no CF incurs net costs. Finally, numerical experiments validate the control protocol’s effectiveness and adaptability, as well as the implications of revenue-neutral toll and subsidy schemes.]]></description>
      <pubDate>Wed, 12 Aug 2026 15:14:50 GMT</pubDate>
      <guid>https://trid.trb.org/View/2736788</guid>
    </item>
    <item>
      <title>Optimization of Signalized Intersections in Mixed Traffic: A Coordinated Platoon–Signal Control Method Considering the Backward-Looking Effect</title>
      <link>https://trid.trb.org/View/2703782</link>
      <description><![CDATA[Mixed traffic flows involving connected autonomous vehicles (CAVs) and human-driven vehicles (HDVs) present new opportunities and challenges for signalized intersections. Although intelligent control strategies have been extensively studied for such environments, most existing approaches neglect the backward-looking effect, in which a driver adjusts not only to the preceding vehicle but also in response to the immediate follower. This omission limits the effectiveness of platoon-based control in mixed traffic. To address this gap, a coordinated platoon–signal control method incorporating a backward-looking effect (CPSC-BLE) is proposed. The framework integrates bidirectional vehicle interactions into platoon trajectory planning and couples them with adaptive signal timing, linking microscopic platoon behavior with macroscopic signal optimization. The approach enhances platoon coherence, improves green time utilization, and mitigates stop-and-go oscillations. Simulation results demonstrate that the proposed CPSC-BLE framework effectively smooths vehicle trajectories, reduces travel delays, and lowers fuel consumption compared with conventional control strategies. These findings highlight the potential of control strategies informed by the backward-looking effect to improve both efficiency and stability in mixed traffic intersections.]]></description>
      <pubDate>Mon, 10 Aug 2026 11:16:49 GMT</pubDate>
      <guid>https://trid.trb.org/View/2703782</guid>
    </item>
    <item>
      <title>Post-congestion recovery optimization for mixed traffic road networks with uncertain demand</title>
      <link>https://trid.trb.org/View/2702678</link>
      <description><![CDATA[To effectively recover road network functionality loss from traffic congestion, a post-congestion recovery optimization (PCRO) is proposed. For mixed traffic of connected and autonomous vehicles (CAVs) and human-driven vehicles (HDVs) under uncertainty, an agent-based reinforcement learning is given to restore signal-controlled road network functionality loss in the aftermath of congestion. Compared to existing resilience-based road network control, a learning-based recovery optimization algorithm (LROA) is given to minimize conventional “resilience triangle” in the aftermath of congestion. A recovery mutation optimizer is given to reduce recovery cost following congestion. A recovery crossover optimizer is also given to increase diverse search of solutions. Numerical experiments are performed using real-world cities to investigate the efficiency of recovery (EOR) for various market penetrations of mixed traffic. Computational comparisons for EOR and recovery time are made using large-scale traffic grids under various kinds of uncertainty budget. As it reported, the proposed LROA can effectively restore urban road network functionality loss while suffering from relatively less recovery overhead compared to other alternatives.]]></description>
      <pubDate>Fri, 07 Aug 2026 09:21:41 GMT</pubDate>
      <guid>https://trid.trb.org/View/2702678</guid>
    </item>
    <item>
      <title>From Safety-I to Safety-II: Longitudinal Control Strategies for Autonomous Vehicles Based on Risk Homeostasis Theory</title>
      <link>https://trid.trb.org/View/2702258</link>
      <description><![CDATA[Although Safety-Ⅰ measures can help autonomous vehicles mitigate risks, they often introduce new secondary risks. For this reason, current autonomous vehicles (AVs) frequently face a dilemma between preventing rear-end collisions and avoiding being rear-ended. To tackle this, this study proposes a Safety-II category Steady-state Risk Control (SRC) strategy to ensure safety resilience in longitudinal control and enhance adaptability within mixed traffic flows. The strategy indirectly characterizes risk by evaluating drivers' risk prevention capabilities, moving beyond reliance on traditional traffic conflict techniques. It further explores drivers’ adaptive mechanisms to uncertainty through steady-state risk theory, introducing a Safety-II paradigm for longitudinal control in autonomous driving. Under this framework, longitudinal trajectories are planned based on personalized risk anticipation, and an SRC strategy is developed using a linear time-varying model predictive control algorithm. By replacing conventional Safety-I boundary constraints on state and control variables, SRC employs an efficient analytical solution. Finally, simulation experiments are conducted with variables such as the lead vehicle’s speed range and emergency braking deceleration, using the autonomous emergency braking (AEB) system as the representative implementation of the Safety-I category for comparison. Results show that while the AEB system’s collision rate reaches 41.67%, the SRC strategy consistently achieves safe, smooth, and reliable braking. Additionally, SRC effectively reduces the deceleration required when following human-driven vehicles, substantially lowering the risk of rear-end collisions and improving coordination within mixed traffic flows.]]></description>
      <pubDate>Fri, 07 Aug 2026 09:21:40 GMT</pubDate>
      <guid>https://trid.trb.org/View/2702258</guid>
    </item>
    <item>
      <title>Uncertainty-aware and safety-enhanced management of CAVs for safer mixed traffic</title>
      <link>https://trid.trb.org/View/2752000</link>
      <description><![CDATA[This project focuses on enhancing the safety of connected and autonomous vehicles (CAVs) operating within complex mixed traffic environments, where both human-driven vehicles (HDVs) and CAVs coexist. In such scenarios, CAVs are subject to multiple sources of uncertainty, including unpredictable human behavior, incomplete or delayed communication, and potential cyber threats. To address these challenges in a systematic and comprehensive way, the project concentrated on two principal objectives. The first was to develop models and techniques for perceiving and quantifying uncertainties that arise in mixed traffic. The second was to establish adaptive and robust operational control strategies for CAVs that can enhance safety under uncertain conditions.]]></description>
      <pubDate>Fri, 07 Aug 2026 08:35:15 GMT</pubDate>
      <guid>https://trid.trb.org/View/2752000</guid>
    </item>
    <item>
      <title>Optimal coordination methods for autonomous vehicles in mixed traffic</title>
      <link>https://trid.trb.org/View/2751953</link>
      <description><![CDATA[Connected and Automated Vehicles (CAVs) are projected to dominate traffic roads in the future due to their potential advantages in efficiency and safety. CAVs are equipped with sensors and onboard computers that allows them to perform coordination. The transition toward fully autonomous era will see a gradual replacement of legacy Human-Driven Vehicles (HDVs) creating mixed traffic environments. In such environments, the presence of HDVs can pose challenges to CAVs due to their uncertain behaviors and intentions. The particular concern of CAVs-HDVs interactions occurs at traffic intersections, where these road segments are responsible for the highest share of traffic jams and fatalities. Additionally, vehicle coordination in mixed traffic involves computationally difficult problems that cannot be solved in a tractable way. This thesis presents optimization-based coordination strategies which builds upon mixed-platooning scheme and heuristic approaches. By utilizing the CAVs presence, the platooning strategy is implemented to partially control the HDVs. To retrieve initial intersection crossing order, a feasibility-enforcing Alternating Direction Methods of Multipliers (ADMM) is employed. Furthermore, an optimization-based heuristic is developed to efficiently evaluate re ordering scenarios. The heuristic employs constraint-feasibility check and cost comparison techniques. Next, in an economic optimal coordination scenario, a sensitivity-based heuristic is implemented to further reduce computational loads by approximating Nonlinear Program (NLP) solutions. The numerical results demonstrate that these heuristics can achieve near-optimal solutions and be better than the alternatives while can be hundred times faster than the Mixed-Integer Program (MIP) solvers.]]></description>
      <pubDate>Fri, 07 Aug 2026 08:34:28 GMT</pubDate>
      <guid>https://trid.trb.org/View/2751953</guid>
    </item>
    <item>
      <title>Enhancing reinforcement learning-based adaptive traffic signal control in emerging mixed traffic environments through CAV data: A simulation study considering driver behaviour</title>
      <link>https://trid.trb.org/View/2725144</link>
      <description><![CDATA[In recent scholarly discourse, it has been noted that connected and automated vehicles (CAVs) have offered substantial developmental potential and a variety of implementation possibilities for the refinement and advancement of adaptive traffic signal control (ATSC). However, as the market penetration rate of CAVs is still relatively low, it is essential to consider the use of existing, cost-effective detectors that can form an integral component of the ATSC system. Additionally, it is crucial to consider drivers' behaviours in the context of emerging mixed traffic environments in order to reflect the realities of traffic flow in simulations due to the distinction between human-driven vehicles and CAVs. To address these issues, an ATSC algorithm was proposed to optimize signal timing to improve safety and operational performance at isolated intersections. The proposed algorithm leveraged real-time Q-learning with loop detector and CAV data to obtain optimized green time, while a driven-behaviour model was introduced to describe human factors in mixed traffic environments. Numerical studies were conducted using simulation of urban mobility (SUMO) to evaluate algorithm performance and investigate the influence of different factors. The results indicate that the proposed algorithm has significant practical value in simultaneously improving safety with a demonstrated reduction in the conflict rate ranging from 28.6% to 72.7% and operational efficiency with a drop in the waiting time ranging from 12.6% to 61.4%, compared to traffic-actuated control. Moreover, it is low-cost and adaptable, and can be continuously updated with real-time driving data while also serving as a layer in next-generation high-definition maps.]]></description>
      <pubDate>Mon, 03 Aug 2026 09:23:54 GMT</pubDate>
      <guid>https://trid.trb.org/View/2725144</guid>
    </item>
  </channel>
</rss>