<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/common/TRIS Suite/feeds/RSS.aspx?s=PHNlYXJjaD48cGFyYW1zPjxwYXJhbSBuYW1lPSJkYXRlaW4iIHZhbHVlPSJhbGwiIC8%2BPHBhcmFtIG5hbWU9InN1YmplY3Rsb2dpYyIgdmFsdWU9Im9yIiAvPjxwYXJhbSBuYW1lPSJ0ZXJtc2xvZ2ljIiB2YWx1ZT0ib3IiIC8%2BPHBhcmFtIG5hbWU9ImxvY2F0aW9uIiB2YWx1ZT0iMCIgLz48L3BhcmFtcz48ZmlsdGVycz48ZmlsdGVyIGZpZWxkPSJpbmRleHRlcm1zIiB2YWx1ZT0iJnF1b3Q7UmVhbCB0aW1lIGluZm9ybWF0aW9uJnF1b3Q7IiBvcmlnaW5hbF92YWx1ZT0iJnF1b3Q7UmVhbCB0aW1lIGluZm9ybWF0aW9uJnF1b3Q7IiAvPjwvZmlsdGVycz48cmFuZ2VzIC8%2BPHNvcnRzPjxzb3J0IGZpZWxkPSJwdWJsaXNoZWQiIG9yZGVyPSJkZXNjIiAvPjwvc29ydHM%2BPHBlcnNpc3RzPjxwZXJzaXN0IG5hbWU9InJhbmdldHlwZSIgdmFsdWU9InB1Ymxpc2hlZGRhdGUiIC8%2BPC9wZXJzaXN0cz48L3NlYXJjaD4%3D" 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>Develop an AI-Based Dynamic Alternative Routing for Commercial Vehicles During Disruptions</title>
      <link>https://trid.trb.org/View/2796544</link>
      <description><![CDATA[This project will develop, implement, and validate a secure Artificial Intelligence (AI)-based dynamic alternative routing prototype for commercial vehicles, including standard freight and oversize/overweight (OS/OW) vehicles, operating under disruptive conditions across Texas freight corridors. The research will design a real-time, disruption-responsive framework that integrates traffic, weather, construction, security incidents, border congestion, and delivery constraints to generate feasible, performance-optimized alternative routes. The project will formulate a multi-objective constrained routing framework that optimizes operational performance metrics, including travel time, cost impacts, and safety exposure. The problem will be solved using Pareto-efficient route generation and weighted aggregation, with performance evaluated relative to static detour and permit-only routing. Demonstrations will use representative Texas scenarios, including border crossings, ports, and major interstate closures. Outcomes will strengthen freight resilience, improve reliability, reduce disruption-related losses, and enhance safety during high-impact events.]]></description>
      <pubDate>Wed, 04 Nov 2026 15:46:49 GMT</pubDate>
      <guid>https://trid.trb.org/View/2796544</guid>
    </item>
    <item>
      <title>Joint State Estimation of Real-Time Transit Travel Time and Reliability Bounds</title>
      <link>https://trid.trb.org/View/2796254</link>
      <description><![CDATA[Uncertainty in bus travel times because of congestion, signal delays, dwell times, and data gaps poses significant challenges for passengers and operators. Existing real-time information systems primarily disseminate point estimates of arrival times, which fail to convey uncertainty, undermining passenger trust and complicating operational planning. This study develops a hazard-based framework for the joint real-time estimation of bus travel time and its reliability bounds to address these limitations. The approach leverages accelerated failure time (AFT) models to dynamically update mean and variability estimates while handling censored observations from incomplete Global Positioning System bus trajectories. Among alternative parametric forms evaluated using multi-criteria performance metrics and the technique for order preference by similarity to ideal solution (TOPSIS) ranking method, the log-normal AFT model applied to pace (travel time per unit distance) delivers the most reliable predictions, achieving near-nominal coverage, narrower intervals, and interpretable hazard structures aligned with real-world transit dynamics. Comparative analysis against alternative regression benchmarks confirmed that ignoring the dependence between mean and variability leads to biased reliability estimates. Empirical insights highlight pronounced spatial and temporal heterogeneity, with congestion during peak hours and route-specific factors significantly shaping uncertainty. Sensitivity analysis underscored the operational significance of reliability management: a 30% reduction in median travel time produced ∼21% improvements in both mean travel time (∼17 min) and reliability interval width (∼9 min). In comparison, a 30% reduction in variability lowered interval width by ∼9% (∼4 min). These findings establish the hazard-based framework as a robust, interpretable basis for delivering reliability-aware traveler information and supporting data-driven operational strategies in heterogeneous urban transit environments.]]></description>
      <pubDate>Tue, 03 Nov 2026 11:46:54 GMT</pubDate>
      <guid>https://trid.trb.org/View/2796254</guid>
    </item>
    <item>
      <title>Evaluating safety resilience in urban roadway network: Investigating the impact of different traffic control measures</title>
      <link>https://trid.trb.org/View/2772155</link>
      <description><![CDATA[The resilience of urban roadway network is crucial for maintaining effective mobility during disruptions. However, traffic safety has received limited attentions in the domain of resilience assessment. The study introduces the concept of safety resilience, which integrates traffic safety consideration into resilience research. Unlike traditional resilience that primarily focuses on traffic efficiency metrics, safety resilience is defined as a network ability to maintain and restore safety performance under disturbances by evaluating real-time traffic risk. The study presents the evaluation of safety resilience based on traffic conflicts at intersections and on roadways and explores the impact of different traffic control measures, including lane control, signal control, and connectivity improvement, on both traffic safety and efficiency. The results demonstrate that the proposed Safety Resilience Index (SRI) provides an effective means to assess network safety resilience by capturing the trade-off between safety and efficiency. Lane restrictions are found to be more suitable for road segments with high safety risk, while lane widenings are more effective in mitigating severe congestion. Signal control can enhance safety resilience but increase travel time and rear-end conflicts on roadways. Although connectivity improvement can theoretically enhance resilience from the topological perspective, it may result in worse overall network safety and efficiency. These findings underscore the need for a balanced approach that integrates both safety and efficiency in enhancing urban network resilience.]]></description>
      <pubDate>Thu, 29 Oct 2026 16:42:57 GMT</pubDate>
      <guid>https://trid.trb.org/View/2772155</guid>
    </item>
    <item>
      <title>Safety analysis of connected and automated vehicle platoon under communication disturbances</title>
      <link>https://trid.trb.org/View/2784546</link>
      <description><![CDATA[Connected and automated vehicles (CAVs) rely on vehicle-to-vehicle (V2V) communication to exchange real-time information and enable cooperative platooning. However, V2V communication among vehicles may be affected by factors such as hardware failures, packet loss, and cyberattacks, which can lead to communication failures or delays and consequently impair the stability and safety of vehicle operations. To address this issue, a dynamic weighting and long short-term memory (LSTM)-based CAV platoon control strategy (DWLC) is proposed, which integrates dynamic acceleration weighting with an LSTM-based prediction model. The dynamic weighting adaptively adjusts the acceleration weights of three predecessors according to communication topology changes, whereas the LSTM predicts the acceleration of the immediately predecessor to compensate for communication failures or delays, thereby mitigating communication disturbances. In the simulation experiments, the randomness of V2V communication failures is taken into account, and the experiments are conducted under different communication delays. The stability and safety of the CAV platoon under varying communication delays are investigated. The results demonstrate that the proposed DWLC can effectively mitigate the adverse effects caused by communication failures and delays. These findings provide useful insights for the practical deployment of CAV platoons in communication-disturbed environments.]]></description>
      <pubDate>Thu, 29 Oct 2026 16:42:57 GMT</pubDate>
      <guid>https://trid.trb.org/View/2784546</guid>
    </item>
    <item>
      <title>Prediction-driven police deployment for faster traffic accident response: A two-stage framework</title>
      <link>https://trid.trb.org/View/2784545</link>
      <description><![CDATA[According to the World Health Organization, road traffic accidents contribute to approximately 1.3 million deaths annually, posing a global public safety challenge. Current deployment strategies for traffic police face difficulties in balancing accident prevention and real-time response, leading to inefficiencies. This study proposes a two-phase framework for traffic police dispatch, integrating pre-deployment and dynamic emergency response. In the pre-deployment phase, a deep learning model using accident data from Yinzhou District, Ningbo City (April 2020 to October 2021) identifies high-risk zones—defined as statistically significant spatial clusters of high accident frequency—for police positioning. The dynamic dispatch phase utilizes a real-time optimization algorithm based on the golden hour (≤10 min) to reduce response times. Experimental results show a 28.71% improvement in average response time (from 5.54–7.21 min to 4.52 min) and an 85.43% police utilization rate, outperforming baseline methods. This approach improves response efficiency and enhances officer utilization. The framework demonstrates potential scalability, offering insights for improving road safety in urban settings with similar characteristics.]]></description>
      <pubDate>Thu, 29 Oct 2026 16:42:57 GMT</pubDate>
      <guid>https://trid.trb.org/View/2784545</guid>
    </item>
    <item>
      <title>Real-time joint prediction of vehicle evasive patterns and rear-end conflict risk for expressways</title>
      <link>https://trid.trb.org/View/2784541</link>
      <description><![CDATA[Traffic safety remains a critical priority within urban transportation systems, and real-time safety analysis is essential for timely risk identification and proactive intervention. Most existing studies on conflict prediction have examined the effects of traffic conditions, vehicle status, and geometric factors on conflict risk. However, driver behaviors, especially conflict evasive behaviors, also play a crucial role. To address this gap, this study analyzed vehicle evasive patterns during rear-end conflicts. An improved K-Means clustering algorithm was applied to identify six evasive patterns under both high- and low-risk conflict conditions. Key influencing factors included roadway and traffic characteristics, following- and leading-vehicle attributes, and non-conflict driving behaviors under normal driving conditions. Following variable selection, a two-level Nested Logit (NL) model was established to jointly predict evasive patterns and conflict risk levels, achieving predictive accuracy above 0.70 and AUC greater than 0.90. Key findings revealed that braking behavior under non-conflict conditions was strongly correlated with subsequent evasive responses, whereas congested traffic conditions tended to delay driver reactions. Leading-vehicle characteristics, such as speed, acceleration, and headway, significantly influenced following-vehicle responses. These findings suggest that incorporating evasive driving patterns into conflict risk prediction can provide a more comprehensive and individualized understanding of rear-end conflicts on expressways.]]></description>
      <pubDate>Thu, 29 Oct 2026 16:42:57 GMT</pubDate>
      <guid>https://trid.trb.org/View/2784541</guid>
    </item>
    <item>
      <title>A Multi-Agent Framework for AI-Generated Content Caching in Internet of Vehicles Networks</title>
      <link>https://trid.trb.org/View/2790463</link>
      <description><![CDATA[As Internet of Vehicles (IoV) networks in urban autonomous driving environments increasingly incorporate generative artificial intelligence (GAI) for real-time monitoring and management of autonomous vehicle fleets, ensuring timely and efficient delivery of artificial intelligence-generated content (AIGC) is essential for maintaining seamless traffic operations and mobility services. This paper tackles the multi-objective challenge of minimizing age of information (AoI), ensuring high inference accuracy, and optimizing energy use under constrained edge computing resources by introducing a novel multi-agent reinforcement learning framework for multi-objective tasks (MARMOT). Leveraging the multi-agent twin delayed deep deterministic policy gradient (MA-TD3) algorithm, MARMOT jointly optimizes content caching, uplink power allocation, and GAI inference placement in multi-access edge computing enabled IoV networks. The proposed framework integrates autoencoder-based state compression with a multi-head critic architecture, enabling scalable and efficient learning among edge nodes. Simulation results confirm that MARMOT significantly outperforms state-of-the-art baselines such as multi-agent deep deterministic policy gradient and standard MA-TD3, achieving reduced AoI and AoI violation probability, superior inference accuracy, and enhanced energy efficiency across diverse autonomous vehicle fleet deployment scenarios.]]></description>
      <pubDate>Wed, 28 Oct 2026 16:47:27 GMT</pubDate>
      <guid>https://trid.trb.org/View/2790463</guid>
    </item>
    <item>
      <title>AAMSim: a comprehensive simulator for advanced air mobility operations and planning</title>
      <link>https://trid.trb.org/View/2728074</link>
      <description><![CDATA[Advanced Air Mobility (AAM) is emerging as a transformative solution to bypass surface congestion and provide an expeditious alternative for passenger mobility and freight transport. The efficient operation of AAM systems hinges on the deployment of adaptable operational strategies and optimization algorithms that can be developed and tested in a realistic, integrable simulation environment. However, existing AAM simulation platforms exhibit significant limitations, tending to treat narrow subproblems (e.g., corridor planning, tactical deconfliction) and give limited attention to system-wide performance. Furthermore, existing tools fail to model passenger and electric Vertical Takeoff and Landing vehicles (eVTOLs) behavior dynamics within vertiports and they rarely support eamless coupling with external algorithms.We introduce AAMSim, an AnyLogic-based, multi-agent platform that (i) generate custom AAM networks and demand patterns from external files; (ii) microsimulates passenger flows (check-in, queues, boarding) and eVTOL processes (landing, deboarding, charging, boarding, takeoff) at vertiports; (iii) exposes APIs for bidirectional data exchange with external optimization modules; and (iv) provides real-time performance dashboards at system and vertiport levels.In a case study of the Greater Tampa Bay region (30 vertiports, two layouts), we evaluated an early-takeoff policy and an eVTOL rebalancing algorithm across five hours and 4,615 passengers. Used together, the strategies reduced passenger reneging from 48.52% to 38.72% without degrading per-flight productivity (deadhead ≈ 11.20%, ∼2 passengers/flight), and improved waiting-time metrics network-wide.AAMSim closes key gaps in current AAM modeling and offers a versatile decision-support testbed for operators, service providers, researchers, and policymakers—advancing the design of more efficient, reliable AAM systems.]]></description>
      <pubDate>Thu, 22 Oct 2026 15:52:10 GMT</pubDate>
      <guid>https://trid.trb.org/View/2728074</guid>
    </item>
    <item>
      <title>Research on the Integrated Vehicle-Road-Cloud Dynamic Cognitive Map Model and Key Technologies</title>
      <link>https://trid.trb.org/View/2671342</link>
      <description><![CDATA[As a critical component of the vehicle-road-cloud system, high-definition (HD) maps not only provide essential auxiliary information to intelligent connected vehicles but also serve as a unified spatiotemporal reference between vehicles and intelligent roadside infrastructure. However, existing HD maps primarily focus on static road information, with limited representation of dynamic data. Given the rapidly changing road environments, the diversity and heterogeneity of road information, and the significant uncertainties, static data alone cannot fully depict a comprehensive and accurate driving environment. To address these challenges, this study proposes a dynamic cognitive map specifically designed for vehicle-road-cloud systems. The study begins by exploring the definition and framework of dynamic cognitive maps, followed by the development of a logical model inspired by the spatial cognition mechanisms of brain. Lastly, this paper introduces and analyzes the key technologies of dynamic cognitive maps. The proposed dynamic cognitive map aims to advance the practical implementation and application of intelligent connected vehicles.]]></description>
      <pubDate>Thu, 22 Oct 2026 15:49:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2671342</guid>
    </item>
    <item>
      <title>Resource-efficient lane geometry monitoring for work zone environments</title>
      <link>https://trid.trb.org/View/2784995</link>
      <description><![CDATA[Lane monitoring in construction zones is challenged by temporary markings, irregular geometry, occlusions, and varying illumination. Existing deep learning-based detection systems achieve strong benchmark performance but require GPU acceleration, domain-specific retraining, and substantial hardware resources unavailable in temporary work zone deployments. This paper presents a lightweight, failure-aware lane geometry monitoring framework designed for CPU-only edge deployment in construction environments. The system integrates a dual-path preprocessing pipeline combining adaptive HSV segmentation and LAB/CLAHE contrast enhancement, probabilistic Hough line extraction, polynomial curve fitting, and temporal smoothing within a calibration-derived region of interest. Rather than reporting pixel-level detection accuracy, the framework produces self-consistency geometric monitoring signals, lane width, angular deviation, curvature, and parallelism alongside a structured failure diagnostic module that classifies boundary loss and width violations in real time. Partial ground truth validation against 529 manually annotated frames across three evaluation scenarios demonstrates strong detection performance for continuous lane markings (F1 score of 0.660–0.932, mean boundary deviation of 0.084–0.128 m), with stability precision of 0.996 to 1.0 across standard and construction roadway scenarios confirming that the temporal stability metric reliably identifies frames with genuine lane boundary detections. Experiments on 15,300 frames demonstrate sustained throughput of 20.8–31.2 FPS below 7% CPU utilization. These results establish the system as a practical, interpretable monitoring component for resource-constrained work zone deployments where diagnostic transparency is prioritized over benchmark accuracy.]]></description>
      <pubDate>Thu, 22 Oct 2026 09:16:37 GMT</pubDate>
      <guid>https://trid.trb.org/View/2784995</guid>
    </item>
    <item>
      <title>Real-Time traffic flow prediction with drones and adaptive signal control using YOLO v8</title>
      <link>https://trid.trb.org/View/2784989</link>
      <description><![CDATA[The congestion experienced in the world cities is a menace that is pushing cities to incur long travel time, fuel usage, and pollution. Conventional traffic management systems do not have the flexibility necessary to react to changing conditions of traffic in real-time, which worsens the congestion of the busiest periods and unexpected delays. The present paper offers a real-time traffic flow prediction framework that is to be used to overcome these issues by combining drones’ technology with adaptive signal control. This system tracks traffic in real-time based on aerial footage of drones and uses the state of the art object detector, YOLOv8, and supplementary ground-level data is obtained via the Google Maps API. A combination of these sources of data creates a multi-level picture of the traffic situation. A regression model is used to forecast the best traffic light times based on real-time data, which allows dynamic control of the signals, depending on the density of the traffic flowing. This system operates on a Raspberry Pi 5 with exact location readings of a GPS module mounted to the drone and constantly manipulates signal timing to reduce traffic jams and increase traffic speed. It combines advanced AI, drone surveillance, and predictive modelling, which can provide a solution to the urgent problem of more efficient management of urban traffic.]]></description>
      <pubDate>Thu, 22 Oct 2026 09:16:37 GMT</pubDate>
      <guid>https://trid.trb.org/View/2784989</guid>
    </item>
    <item>
      <title>A simulation-based comparative evaluation of CNN–, LSTM-, and reinforcement learning–based traffic signal control using vision-derived data</title>
      <link>https://trid.trb.org/View/2784895</link>
      <description><![CDATA[Urban signalized intersections are critical bottlenecks in metropolitan road networks, where inefficient control strategies contribute to excessive delay, congestion, and environmental impacts. Although Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) models, and Reinforcement Learning (RL) approaches have been widely studied for traffic analysis and signal control, prior research typically evaluates these paradigms in isolation using heterogeneous data sources and metrics. This fragmentation limits systematic comparison and obscures practical trade-offs. This study presents a controlled comparative evaluation of CNN–, LSTM-, and RL-based controllers for real-time traffic signal control using online vision-derived data under consistent experimental conditions. All models were evaluated at a real four-leg urban intersection (17 Shahrivar–Taleghani, Tabriz) across 12 traffic scenarios representing varying demand levels and stochastic arrival patterns, totaling 3,600 simulation episodes and more than 2.5 million control decisions. Performance was assessed using average vehicle delay, queue length, throughput, robustness metrics, and statistical significance testing. Results indicate that the RL-based controller consistently outperforms the CNN and LSTM models, reducing average delay by approximately 21–33% relative to the baselines while simultaneously increasing throughput and maintaining the lowest performance variance. The CNN-based controller demonstrated high computational efficiency but lacked anticipatory capability, whereas the LSTM-based controller improved stability yet remained constrained by its predict-then-control architecture. The RL framework achieved real-time feasibility, with 100% of decisions executed within 20 ms. The findings demonstrate that objective-aligned, decision-centric learning provides structural advantages over perception or prediction-driven paradigms. This study offers one of the first unified vision-based benchmarks across these modelling frameworks and provides evidence-based guidance for scalable adaptive traffic signal control.]]></description>
      <pubDate>Wed, 21 Oct 2026 16:56:24 GMT</pubDate>
      <guid>https://trid.trb.org/View/2784895</guid>
    </item>
    <item>
      <title>Mesoscopic pedestrian dynamics enhancement robust optimization for signage collaboration in metro stations under uncertainties</title>
      <link>https://trid.trb.org/View/2784984</link>
      <description><![CDATA[Dynamic guidance signage in metro stations demonstrates significant potential for enhancing evacuation efficiency, primarily by proactively adapting to passenger flow distributions and the evolution of risk, thereby optimizing the overall evacuation route network. To address the uncertainty of fire risk, this paper proposes a dynamic guidance signage coordinated control method incorporating robust optimization. First, a cell transmission model is constructed to dynamically model the passenger evacuation process in metro stations, capturing the temporal evolution of passenger flows under fire conditions. Second, a budget uncertainty set is introduced to characterize fluctuations in fire risk, and the dynamic guidance signage optimization problem is formulated as a robust decision-making problem that seeks an optimal and stable coordinated guidance strategy under the worst-case realizations of uncertain parameters. Subsequently, a solution algorithm is developed by integrating a local search mechanism with a global optimization framework. Compared with conventional metaheuristic algorithms, the proposed approach exhibits significant advantages in both solution quality and convergence efficiency. Finally, extensive numerical experiments are conducted to evaluate the effectiveness of the proposed method. The results indicate that, compared with static guidance strategies, the coordinated dynamic guidance signage strategy could significantly improve evacuation performance. In addition, the impacts of key factors, including robust parameters, weight configurations, solution algorithms, crowd density, fire scenarios, and signage adjustment frequency, on the dynamic guidance system performance are systematically analyzed.]]></description>
      <pubDate>Mon, 19 Oct 2026 12:05:09 GMT</pubDate>
      <guid>https://trid.trb.org/View/2784984</guid>
    </item>
    <item>
      <title>Kriging-Based Metamodeling for Accurate and Explainable Real-Time Taxi-Time Prediction in Airport Surface Networks</title>
      <link>https://trid.trb.org/View/2789807</link>
      <description><![CDATA[This paper proposes a Kriging-based metamodel for real-time taxiing time prediction on complex airport surface networks. By combining the strengths of analytical and machine learning methods, the model offers superior adaptability and interpretability. It produces not only accurate point predictions but also confidence intervals to quantify predictive uncertainty, with each prediction traceable to specific training samples. The model relies on simple and readily available inputs, including flight schedules and observed runway-queue information, which facilitates adaptation to other airports after local calibration. Trained on historical operational records and evaluated through high-fidelity simulations of Beijing Capital International Airport and benchmarked against current operational methods and artificial intelligence-based alternatives, the results demonstrate significant improvements over existing taxi-time estimation techniques. These advantages highlight the model’s potential as a robust solution for future automated air traffic management systems.]]></description>
      <pubDate>Thu, 15 Oct 2026 11:00:50 GMT</pubDate>
      <guid>https://trid.trb.org/View/2789807</guid>
    </item>
    <item>
      <title>Real-time path optimization in green logistics using the honey bee algorithm</title>
      <link>https://trid.trb.org/View/2776333</link>
      <description><![CDATA[This study develops a real-time multi-objective path optimization framework for green logistics using the Honey Bee Algorithm (HBA) to address the limitations of conventional routing approaches under dynamic traffic and environmental conditions. The proposed framework simultaneously optimizes fuel consumption, carbon emissions, and delivery time, thereby integrating operational efficiency with environmental sustainability. A simulation-based experimental design is employed to compare HBA with three established metaheuristic algorithms—Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Ant Colony Optimization (ACO)—under controlled logistics scenarios. The results demonstrate that HBA consistently outperforms the benchmark algorithms, reducing fuel consumption by approximately 20% and carbon emissions by approximately 25%, while achieving on-time delivery performance of up to 95%. These results indicate that the adaptive exploration–exploitation mechanism of HBA enables more effective route selection under dynamic and uncertain transportation conditions. The findings further demonstrate that incorporating environmental objectives directly into routing decisions can simultaneously improve operational efficiency and sustainability performance without imposing impractical computational demands. The proposed framework therefore provides a scalable decision-support approach for logistics firms, particularly in urban and last-mile delivery environments where traffic conditions and delivery requirements change dynamically. Overall, the study contributes empirical evidence on the effectiveness of bio-inspired optimization for sustainability-oriented logistics and demonstrates the potential of real-time multi-objective routing to support simultaneous improvements in transportation efficiency and environmental performance.]]></description>
      <pubDate>Tue, 13 Oct 2026 16:53:06 GMT</pubDate>
      <guid>https://trid.trb.org/View/2776333</guid>
    </item>
  </channel>
</rss>