<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>Experimental Exploration of An Ammonia Cracking Power Generation System for Electric Aircraft Propulsion</title>
      <link>https://trid.trb.org/View/2679315</link>
      <description><![CDATA[The aviation sector faces growing pressure to reduce carbon emissions, and electric propulsion systems (EPS) based on proton exchange membrane fuel cells (PEMFCs) provide a promising path toward sustainable, zero-carbon aviation. However, challenges related to hydrogen storage and transport have hindered the practical implementation of such systems. Ammonia (NH₃), with high energy density, convenient storage and transport, and carbon neutrality, has emerged as an attractive hydrogen carrier. This study proposes and experimentally validates a compact NH₃ cracking power generation system tailored for EPS through laboratory-scale exploration, engineering-scale validation, and system-level evaluation. The system delivers a maximum power output of 30 kW and comprises a custom-designed multifunctional NH₃ cracking reactor with integrated heat recovery, a temperature swing adsorption (TSA) purification unit, and PEMFC stacks. To meet practical application needs, this study screens and optimizes a commercially available 1% Ru–Ni/Al₂O₃ catalyst, achieving over 99% NH₃ conversion under realistic conditions. The TSA unit reduces NH₃ concentration to below the detection limit, ensuring stable PEMFC performance with a single-stack maximum power output of 5.3 kW. Simulation results further show that the multi-stage thermal management increases the propulsion usable net electrical efficiency to 20.52%, and further raises the overall energy efficiency to 28.33% when the low-grade recovered heat is assumed fully usable. The optimized system achieves a gravimetric energy density of 692.7 W·h·kg−1 and a hydrogen storage capacity of 6.7 wt% when equipped with five NH₃ tanks, each containing 22.7 kg of NH₃. This work demonstrates an NH₃-powered PEMFC EPS for aviation, offering both experimental validation and theoretical guidance for NH₃-fueled propulsion technologies. The study provides system-level insights into design, integration, and performance optimization, supporting the future development of electrified aviation and related zero–carbon distributed energy systems.]]></description>
      <pubDate>Wed, 25 Mar 2026 11:44:56 GMT</pubDate>
      <guid>https://trid.trb.org/View/2679315</guid>
    </item>
    <item>
      <title>ABCDWaveNet: Advancing Robust Road Ponding Detection in Fog Through Dynamic Frequency-Spatial Synergy</title>
      <link>https://trid.trb.org/View/2679326</link>
      <description><![CDATA[Road ponding presents a substantial threat to vehicular safety, particularly in foggy conditions where reliable detection continues to be a major challenge for advanced driver assistance systems (ADASs). To address this issue, we propose an aggregation-broadcast-coupling dynamic wavelet network (ABCDWaveNet), a novel deep learning framework specifically designed to achieve robust ponding detection in fog-affected environments. The central architecture of ABCDWaveNet improves detection performance by utilizing dynamic convolution for adaptive feature extraction under reduced visibility, together with a wavelet-based module that improves feature representation across both spatial and frequency domains, thereby effectively alleviating fog-related interference. In addition, ABCDWaveNet incorporates multi-scale structural and contextual information and employs an adaptive attention coupling gate to dynamically integrate global and local features, leading to improved detection accuracy. For realistic evaluations under compounded adverse weather conditions, we introduce the Foggy Low-Light Puddle dataset. Comprehensive experiments confirmed that ABCDWaveNet attained state-of-the-art results, with notable intersection over union gains of 3.51%, 1.75%, and 1.03% on the Foggy-Puddle, Puddle-1000, and Foggy Low-Light Puddle datasets, respectively. Furthermore, with an inference speed (FPS) of 25.48 on the NVIDIA Jetson AGX Orin, the proposed framework demonstrates strong suitability for development in ADAS applications. These results highlight the effectiveness of ABCDWaveNet, presenting valuable advancements for proactive road safety under challenging weather conditions.]]></description>
      <pubDate>Wed, 25 Mar 2026 11:44:56 GMT</pubDate>
      <guid>https://trid.trb.org/View/2679326</guid>
    </item>
    <item>
      <title>Three-Dimensional Geometric Digital Twin of Cable-Stayed Bridges: UAV- and TLS-Based Point Cloud Registration, Fusion Modeling, and Damage Inspection</title>
      <link>https://trid.trb.org/View/2667031</link>
      <description><![CDATA[Advanced inspection techniques are essential for the efficient detection of damage, particularly in long-span bridges situated over challenging terrains, such as rivers. This study introduces an innovative methodology for reconstructing three-dimensional geometric digital twin (DT) models and conducting associated damage inspections on large cable-stayed bridges. The proposed approach utilizes a multi-source registration technique, integrating point cloud data acquired from two types of unmanned aerial vehicles and terrestrial laser scanners. The proposed framework is implemented on an extra-large cable-stayed prestressed concrete bridge located in Jiamusi, China. Three distinct registration methods are employed to achieve fusion modeling of the point cloud data following noise reduction. Experimental results indicate that the automatic registration algorithm significantly improves the absolute accuracy, relative accuracy, and integrity of the DT model by 28.2%, 10.8%, and 18.8%, respectively. Furthermore, the enhanced DT model facilitates the detection of various forms of bridge damage, including surface concrete spalling and deformations in the deck and girders, thereby providing a promising solution for effective bridge maintenance planning.]]></description>
      <pubDate>Fri, 20 Feb 2026 14:15:15 GMT</pubDate>
      <guid>https://trid.trb.org/View/2667031</guid>
    </item>
    <item>
      <title>IoT-Enabled Real-Time Energy Consumption Anomaly Detection and Diagnosis for Automotive Paint Drying System</title>
      <link>https://trid.trb.org/View/2648342</link>
      <description><![CDATA[The energy-intensive automotive industry requires sophisticated energy management systems to improve energy efficiency. In automotive workshops, paint drying systems are a significant energy consumer, necessitating real-time monitoring and control to minimize energy waste and potentially prevent system malfunctions. Thus, this study proposed a novel real-time energy consumption anomaly detection and diagnosis methodology (eAnoD) for automotive paint drying systems to enhance their energy efficiency and operational safety. Specifically, an architecture combining a temporal convolutional network and graph attention network (TCN-GAT) was devised to extract spatiotemporal features from multidomain data, including energy consumption, equipment parameters, production states, and environmental conditions. A hybrid neural network combining a backpropagation neural network (BPNN) and variational autoencoder (VAE) was constructed to enable the prompt identification of energy consumption deviations. Furthermore, an anomaly grading method integrating combination weighting and cloud modeling techniques was developed to evaluate anomaly severity, facilitating targeted maintenance and proactive risk prevention. A real-world case study was conducted in a new-energy vehicle factory to validate the effectiveness and practicality of the proposed methodology and demonstrate its potential for energy saving and risk mitigation in automotive manufacturing. This study is expected to serve as a reference for practical implementation and generate new ideas for academic exploration.]]></description>
      <pubDate>Mon, 26 Jan 2026 08:41:46 GMT</pubDate>
      <guid>https://trid.trb.org/View/2648342</guid>
    </item>
    <item>
      <title>Exhaust Heat Recovery for Cryogenic Hydrogen-Powered Aircraft: From Conceptual Design to Experimental Validation</title>
      <link>https://trid.trb.org/View/2647843</link>
      <description><![CDATA[Cryogenic hydrogen aircrafts are a critical pathway toward carbon neutrality for the aviation industry; however, the low volumetric energy density of hydrogen hinders their development. Exhaust heat recovery for cryogenic hydrogen heating is considered a promising approach towards higher energy efficiency; however, it lacks experimental validation. Herein, we validate the feasibility of recovering engine exhaust to heat liquid hydrogen through systematic experimentation and provide the first quantitative evaluation of the impact of heat recovery on engine thrust performance. Using thermodynamic analysis of a hydrogen-fueled aircraft engine, it is demonstrated that exhaust heat recovery can heat cryogenic hydrogen from 30 to 250 K while maintaining thrust losses below 0.74%, thereby theoretically validating the concept. Subsequently, a heat exchange test rig was constructed to verify the exhaust heat recovery and experimentally investigate the impact of the technology on engine thrust performance. The experiments were conducted under the idle, takeoff, and cruise conditions of the engine, achieving heat-transfer capacities of 9.89, 25.5, and 29.5 kW, respectively. Exhaust heat recovery can heat hydrogen to temperatures beyond 189 K, exceeding the minimum temperature requirement for a combustor (150 K). Additionally, the flow resistance of the heat exchanger causes exhaust flow deceleration, resulted in a significant 16.7% thrust reduction. Hence, this study experimentally confirms the feasibility of exhaust heat recovery for cryogenic hydrogen aircraft, identifies existing challenges, and provides a clear direction for future development.]]></description>
      <pubDate>Mon, 26 Jan 2026 08:41:46 GMT</pubDate>
      <guid>https://trid.trb.org/View/2647843</guid>
    </item>
    <item>
      <title>Monitoring and Detection Technologies and AI-Powered Development Toward Transparent Roads</title>
      <link>https://trid.trb.org/View/2647537</link>
      <description><![CDATA[Intelligentization presently emerges as the primary direction for future developments of road infrastructure, providing specific scenarios that integrate conventional transport infrastructure research with cutting-edge technologies, such as artificial intelligence (AI), the Internet of Things (IoT), big data, and new forms of business, including automated driving and intelligent connected vehicles. The key technologies for the construction and operation of smart roads include digital sensor networks, intelligent management systems, and interconnected service frameworks, among which sensor networks provide a data foundation. This study focuses on monitoring and detection technologies for road service performance, which constitute an integral part of the digital sensor networks of smart roads. Reviews were conducted, and observations were made, from three perspectives: embedded sensing of road service performance, automated detection of road surface defects, and intelligent identification of hidden road defects. Advancements and existing challenges faced by monitoring and detection technologies for road service performance were examined, and applications of AI in monitoring road service performance and detecting road service problems were elucidated. Finally, a roadmap for future research on sensing and detection for AI-powered road service performance was proposed. Breakthroughs are expected in four areas: establishing a “space–air–ground” multi-source three-dimensional monitoring and detection system, developing monitoring and detection technologies based on multi-source data fusion algorithms, building a digital twin base integrating the physical structures of roads, and creating a road control and service system that integrates end–edge–cloud collaboration. This comprehensive approach aims to advance the key technologies and theoretical foundations that are essential for the construction and operation of smart roads.]]></description>
      <pubDate>Mon, 26 Jan 2026 08:41:46 GMT</pubDate>
      <guid>https://trid.trb.org/View/2647537</guid>
    </item>
    <item>
      <title>Embodied Interactive Intelligence Towards Autonomous Driving</title>
      <link>https://trid.trb.org/View/2636591</link>
      <description><![CDATA[Autonomous driving depends on successful interactions among humans, vehicles, and roads. However, people often lack an understanding of autonomous vehicle (AV) behaviours and decisions. Moreover, AVs have difficulty aligning with human intentions in their interactions. To overcome the obstacles associated with the absence of interactive intelligence, especially in complex and uncertain environments, we introduce the concept of embodied interactive intelligence towards autonomous driving (EIIAD), which establishes representation and learning methods aligned with the physical world, enhancing human–machine integration. Building on this concept, we propose an end-to-end unified constrained vehicle environment interaction (UniCVE) model, which involves the construction of an end-to-end perception–cognition–behaviour closed-loop feedback paradigm and continuous learning through accumulated split driving scenarios. This model realizes interaction cognition through networks designed for pedestrians and vehicles, and it unifies the cognition as a value network of AVs to generate socially compatible behaviours. The UniCVE model is implemented on Dongfeng autonomous buses, which have successfully travelled 22 thousand kilometres and completed 45 thousand navigation tasks in Xiong’an New Area, China, demonstrating its general applicability in various driving scenarios. In addition, we highlight the high-level interactive intelligence of the UniCVE model in selected simulated complex interaction scenarios, demonstrating that it makes AVs more intelligent, more reliable, and more attuned to human relationships. Furthermore, the UniCVE model’s capacity for self-learning and self-growth allows it to infinitely approximate true intelligence, even with limited experience.]]></description>
      <pubDate>Mon, 29 Dec 2025 09:32:47 GMT</pubDate>
      <guid>https://trid.trb.org/View/2636591</guid>
    </item>
    <item>
      <title>Pilot-Ignition Reactivity-Stratification Combustion for Ammonia Fueled Engines</title>
      <link>https://trid.trb.org/View/2626003</link>
      <description><![CDATA[Ammonia combustion does not produce carbon dioxide, and has been recognized as one of the promising approaches to achieving carbon neutrality in transportation sector. Due to the slow flame propagation speed and high ignition energy requirements, reactive fuel pilot ignition is essential for ammonia combustion in compression ignition engines. The reduction of pilot fuel drives CO₂ mitigation by curtailing carbon input, but this has a demand of advanced combustion modulation techniques to sustain engine efficiency. Designed pilot fuel stratification enables an activated in-cylinder environment, overcoming the difficulty in ammonia ignition and combustion, and allowing for a minimal pilot fuel amount to trigger premixed ammonia combustion. The minimum pilot fuel permits 99.1% ammonia energy substitution, accounting for only 1.3% of the CO₂ emissions from diesel combustion at the same load condition. Optimized intake organization coupled with improved reactivity stratification also achieves over 46% brake thermal efficiency, and reduces unburned ammonia by over 80% compared to baseline operation.]]></description>
      <pubDate>Fri, 21 Nov 2025 17:10:10 GMT</pubDate>
      <guid>https://trid.trb.org/View/2626003</guid>
    </item>
    <item>
      <title>Machine Learning-Guided Gradient Dual-Proton Conducting Catalytic Layers for High Temperature Proton Exchange Membrane Fuel Cells in Aviation</title>
      <link>https://trid.trb.org/View/2625993</link>
      <description><![CDATA[State-of-the-art proton exchange membrane fuel cell (PEMFC) for aviation application requires large radiator to avoid overheating. High temperature PEMFCs (HT-PEMFCs) using phosphoric acid (PA) as a proton conductor enable operating over 160 °C and anhydrous conditions, solving the heat rejection problems. Nevertheless, the dynamic PA redistribution in catalytic layers severely compromises their electrochemical performance. This study, using machine learning, clarifies that the PA volume concentration within the catalytic layers is the dominant performance factor, contributing 25.5% of fuel cell performance. Furthermore, multiphysics simulations for the catalytic layers reveal a detrimental PA gradient formation from membrane to the gas diffusion layer, causing progress deactivation of Pt catalyst by 50% in membrane-distal electrode regions. That has also been confirmed by electrochemical performance of gradient electrode layers with a 111.5% loss of Pt utilization in PA-deficient zones. To address this critical challenge, we propose an innovative dual proton conductor system combining ethylenediamine tetramethylene with PA (EDTMPA). The strong hydrogen bonding interactions between the phosphonic groups of EDTMPA and PA molecules create continuous proton conduction pathways and limit PA migration. This modification achieves a record peak power density of 2.16 W·cm−2 at 160 °C, significantly advancing HT-PEMFCs for aviation application.]]></description>
      <pubDate>Fri, 21 Nov 2025 17:10:10 GMT</pubDate>
      <guid>https://trid.trb.org/View/2625993</guid>
    </item>
    <item>
      <title>Intelligent Forming of Large-Span Arch Bridges: Methodology and Engineering Applications</title>
      <link>https://trid.trb.org/View/2622313</link>
      <description><![CDATA[Arch bridges are well-suited to mountainous regions because their force characteristics align with local site conditions. However, construction in such areas faces challenges including large temperature differentials, complex canyon wind fields, and rugged terrain. Arch-forming also entails extensive work at height, high construction risk, and difficulties in achieving precise alignment after forming. To overcome these issues, this study presents an intelligent arch-forming method for large-span arch bridges. First, an optimization model for the entire arch-forming process is established to compute cable forces that meet objectives during construction. Second, a digital preassembly-based manufacturing control scheme is developed, allowing high-precision virtual assembly of arch rib segments in a digital environment. Finally, an automatic installation attitude adjustment strategy is proposed, based on restoring the structure to its designed shape, enabling high-precision, automated adjustment of the three-dimensional installation attitude of arch rib segments. The proposed method has been successfully applied to the Deyu Expressway Wujiang Bridge (with a main span of 504 m) located in Guizhou Province, China, demonstrating its reliability and practicality. This approach offers guidance for low-labor, resource-efficient, rapid, and automated construction of large-span arch bridges.]]></description>
      <pubDate>Fri, 21 Nov 2025 08:44:21 GMT</pubDate>
      <guid>https://trid.trb.org/View/2622313</guid>
    </item>
    <item>
      <title>Algorithm for Transportation Pathways and Patterns Through Pipeline Network: A Case Study in California for the Power Generation Sector</title>
      <link>https://trid.trb.org/View/2626090</link>
      <description><![CDATA[Decarbonization and energy transition in modern energy systems require integrated tools that can analyze complex supply pathways, optimize infrastructure choices, and evaluate policy impacts. This study presents the algorithm for transportation pathways and patterns through pipeline network (ATP3), an open-source framework combining high‐resolution supply‐chain traceability, cost- and emissions‐aware network optimization, and scenario simulation. ATP3 reconstructs real-world flows by matching supply and demand nodes across an entire pipeline network, integrating the entropy weight method (EWM)-based allocation and a minimum-cost flow formulation with scenario‐driven computational simplification. In a California power generation case study, ATP3 accurately identified 154 processing-to-plant supply routes and 134 upstream field linkages. In addition, when using the EWM-based 40% baseline allocation, the model determined that 90.53% of natural gas used for electricity was imported—primarily from Arizona (48.66%), Oregon (27.43%), and Nevada (14.44%)—with Arizona supplying the largest single external volume (1034.51 MMscf·d⁻¹, here MMscf is million standard cubic feet, and 1 MMscf ≈ 28 317 m³). In‐state production accounted for only 201.37 MMscf·d⁻¹ (9.47%). Meanwhile, EWM allocation reduced transportation costs by 2.76% compared to uniform allocation by favoring geographically proximate sources. These results demonstrate the ability of ATP3 to bridge granular infrastructure mapping with system‐level planning, offering a robust and versatile platform for life‐cycle assessment, infrastructure planning, and policy evaluation across power, transportation, and industrial sectors. The continuously updated resource is available via the GitHub repository.]]></description>
      <pubDate>Fri, 21 Nov 2025 08:44:21 GMT</pubDate>
      <guid>https://trid.trb.org/View/2626090</guid>
    </item>
    <item>
      <title>A Comparative Analysis of Conventional Thermal and Electrochemical Reforming Pathways for Hydrogen Production Towards Sustainable Aviation Fuels (SAF)</title>
      <link>https://trid.trb.org/View/2622438</link>
      <description><![CDATA[H₂ is increasingly recognized as a cornerstone of global decarbonization strategies, including in hard-to-abate sectors, such as aviation. Its large-scale applicability remains limited owing to the limited diversity and maturity of low-carbon production pathways. Approximately 96% of global H2 production originates from non-renewable sources, primarily through steam methane reforming (SMR),₂ which remains the most commercially established route. Another critical barrier to the substitution of conventional aviation fuels lies in hydrogen storage, as the current volumetric energy density and cryogenic storage requirements render onboard integration impractical for most aircraft configurations. To address these challenges, this study developed a techno-economic and environmental benchmarking framework that compares conventional thermal reforming technologies (SMR, autothermal, and POX) with emerging electrochemical routes (water electrolysis and alcohol electro-oxidation), highlighting their potential roles in the transition toward sustainable aviation fuels (SAF). By normalizing efficiency, energy intensity, CO₂ emissions, and cost (USD kg⁻¹H₂ and USD·GJ⁻¹), this study quantifies the trade-offs that define current and emerging pathways. SMR remains the industrial baseline (70%–85% thermal efficiency, 1–2 USD·kg⁻¹ H₂, 9–12 kg CO₂·kg⁻¹ H₂), whereas ethanol-based electrochemical reforming operates 0.3–0.9 V below conventional electrolysis, achieving up to 40% lower electrical energy demand (∼2.4 kW·h·(Nm³)⁻¹H₂) with near-zero direct emissions. A sensitivity analysis demonstrates that a 60% reduction in catalyst cost or electricity prices below 0.03 USD·(kW·h)⁻¹ could make electrochemical reforming cost-competitive with SMR. This study consolidates fragmented knowledge into a comprehensive roadmap that links catalyst performance and technology readiness for aviation decarbonization by integrating engineering metrics with policy and infrastructure perspectives to identify realistic transition pathways toward sustainable hydrogen and hybrid aviation fuels.]]></description>
      <pubDate>Fri, 21 Nov 2025 08:44:21 GMT</pubDate>
      <guid>https://trid.trb.org/View/2622438</guid>
    </item>
    <item>
      <title>Dynamic Response of Full-Section Asphalt Concrete Waterproof Layer on Ballastless Tracks Employing Fractional-Order Modeling</title>
      <link>https://trid.trb.org/View/2614652</link>
      <description><![CDATA[The full-section asphalt concrete waterproof layer (FACWL) has garnered significant attention for its outstanding ability to reduce frost heave and thaw-related weakening in railway track beds, particularly in seasonally frozen regions. To explore the dynamic properties of the FACWL, a fractional-order constitutive model was utilized to characterize the viscoelastic behavior of asphalt concrete. Additionally, a vehicle–track coupled finite element (FE) model and the numerical approach incorporating the fractional-order constitutive model were developed and validated via experimental and field testing. Simulation results indicate that applying the FACWL reduces the vertical dynamic response of each structural layer, vertical peak accelerations across the subgrade surface layer exhibited reductions exceeding 30% in both positive and negative directions. Moreover, the tensile strain at the bottom of the FACWL remained relatively low, less than 100 με. Compared with conventional waterproof sealing layers, the viscoelastic nature of the FACWL facilitates energy dissipation, effectively decreasing the overall vibrational amplitude and vertical deformation within the track structure by more than 20%. Consequently, the FACWL plays a crucial role in ensuring the long-term stability of the subgrade and minimizing vibrations in the track system.]]></description>
      <pubDate>Thu, 30 Oct 2025 13:27:19 GMT</pubDate>
      <guid>https://trid.trb.org/View/2614652</guid>
    </item>
    <item>
      <title>LearningEMS: A Unified Framework and Open-Source Benchmark for Learning-Based Energy Management of Electric Vehicles</title>
      <link>https://trid.trb.org/View/2611893</link>
      <description><![CDATA[An effective energy management strategy (EMS) is essential to optimize the energy efficiency of electric vehicles (EVs). With the advent of advanced machine learning techniques, the focus on developing sophisticated EMS for EVs is increasing. Here, the authors introduce LearningEMS: a unified framework and open-source benchmark designed to facilitate rapid development and assessment of EMS. LearningEMS is distinguished by its ability to support a variety of EV configurations, including hybrid EVs, fuel cell EVs, and plug-in EVs, offering a general platform for the development of EMS. The framework enables detailed comparisons of several EMS algorithms, encompassing imitation learning, deep reinforcement learning (RL), offline RL, model predictive control, and dynamic programming. The authors rigorously evaluated these algorithms across multiple perspectives: energy efficiency, consistency, adaptability, and practicability. Furthermore, the authors discuss state, reward, and action settings for RL in EV energy management, introduce a policy extraction and reconstruction method for learning-based EMS deployment, and conduct hardware-in-the-loop experiments. In summary, the authors offer a unified and comprehensive framework that comes with three distinct EV platforms, over 10  000 km of EMS policy data set, ten state-of-the-art algorithms, and over 160 benchmark tasks, along with three learning libraries. Its flexible design allows easy expansion for additional tasks and applications. The open-source algorithms, models, data sets, and deployment processes foster additional research and innovation in EV and broader engineering domains.]]></description>
      <pubDate>Thu, 23 Oct 2025 09:22:20 GMT</pubDate>
      <guid>https://trid.trb.org/View/2611893</guid>
    </item>
    <item>
      <title>Leveraging Battery Electric-Bus Charging Networks for Resilient Shared EV Charging via Deep Reinforcement Learning</title>
      <link>https://trid.trb.org/View/2611608</link>
      <description><![CDATA[The rapid electrification of urban transportation has increased dependence on public electric-vehicle (EV) charging infrastructure, making it more vulnerable to frequent and severe disruptions. To address this issue, this study proposes utilizing underused battery electric-bus (BEB) charging networks by dynamically reallocating surplus depot chargers for public EV charging. The authors introduce an adaptive shared-charging coordination framework to increase the resilience of public charging services. This coordination problem is formulated as a Markov decision process (MDP) that jointly optimizes BEB charging schedules and shared charger allocation under uncertainty. To enable real-time decision-making without requiring precise forecasts of future system states, an on-policy deep reinforcement-learning (DRL) approach based on the asynchronous advantage actor-critic (A3C) algorithm is developed. A case study using real-world data from Beijing during a major urban flood demonstrates the effectiveness of the proposed adaptive shared-charging coordination framework. The results reveal that the authors' approach significantly mitigates degradation in public charging service performance, accelerates recovery to normal operating levels, enhances user accessibility, and supports grid stability. Under an extreme scenario with only 25% of public chargers operational, the proposed strategy limits revenue losses to just 3.49%, compared with losses of 53.34% under conventional operations. Additionally, the A3C-based approach demonstrates notable training efficiency and achieves a favorable balance between short-term responsiveness and long-term system performance when benchmarked against a perfect-information optimization model, proximal policy optimization (PPO), and a greedy heuristic. These findings highlight the substantial potential of BEB charging networks as critical resilience resources for urban public EV charging infrastructure during extreme disruption events.]]></description>
      <pubDate>Thu, 23 Oct 2025 09:22:20 GMT</pubDate>
      <guid>https://trid.trb.org/View/2611608</guid>
    </item>
  </channel>
</rss>