Transportation Research Part E-Logistics and Transportation Review最新文献

{"title":"Who should invest in EV charging infrastructure? Policy design under ZEV mandates","authors":"Ting Chen ,&nbsp;Kannan Govindan ,&nbsp;Wenting Yang ,&nbsp;Qiuwei Wang ,&nbsp;Lu Liu","doi":"10.1016/j.tre.2025.104642","DOIUrl":"10.1016/j.tre.2025.104642","url":null,"abstract":"<div><div>Governments worldwide have implemented multiple incentive measures to promote electric vehicle (EV) adoption, including consumer subsidies, infrastructure investment subsidies, and Zero Emission Vehicle (ZEV) mandates. Motivated by these policy instruments, various stakeholders (including automakers and EV component suppliers) are actively investing in charging infrastructure. Which subsidy policy is most cost-effective, and which entity’s infrastructure investment yields optimal outcomes? This study constructs a Stackelberg game model comprising government, component supplier, and competing fuel/electric vehicle manufacturers to explore optimal policy structures under three investment modes (i.e., supplier-led infrastructure investment, EV manufacturer-led investment, and traditional automaker-led investment). We systematically evaluate the performance in minimizing government expenditure while achieving adoption targets for each investment mode. More importantly, we extend our analysis to include ZEV mandates and their impact on subsidy effectiveness and government expenditure. Our results provide several interesting and counterintuitive insights. First, we show that supplier-led infrastructure investment (i.e., Mode S) consistently achieves the lowest policy expenditure and highest social welfare. Second, when automakers invest (Modes E and F), consumer subsidies alone are never optimal, contradicting widespread policy practice. Mode S consistently achieves the lowest expenditure and highest social welfare, yet Modes E and F generate superior economic benefits for firms—revealing a fundamental trade-off between public cost-efficiency and private profitability. Third, although ZEV mandates are intended to substitute for costly subsidies and reduce fiscal burden, our analysis reveals they may paradoxically increase government expenditure and discourage EV production when requirements become overly stringent.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"208 ","pages":"Article 104642"},"PeriodicalIF":8.8,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep reinforcement learning for the vehicle routing problem with route balancing","authors":"Jianhua Xiao ,&nbsp;Detian Kong ,&nbsp;Zhiguang Cao ,&nbsp;Jingyi Zhao","doi":"10.1016/j.tre.2025.104632","DOIUrl":"10.1016/j.tre.2025.104632","url":null,"abstract":"<div><div>The Vehicle Routing Problem with Route Balancing (VRPRB) is a multi-objective combinatorial optimization (MOCO) problem that aims to balance workload distribution while minimizing overall travel costs. Unlike traditional Vehicle Routing Problems (VRP), VRPRB introduces fleet size constraints to improve resource utilization and reduce operational costs. Existing deep reinforcement learning (DRL) approaches for VRP rarely address multi-objective optimization and often assume an unlimited fleet size, limiting their practical applicability. To address this issue, we propose an Equity Attention Model (E-AM), a problem-tailored DRL framework designed to generate Pareto-optimal solutions for VRPRB. Our E-AM formulates the problem as a sequential decision-making process, where each decision involves pairing a vehicle with a customer. E-AM is built on an attention-based architecture, incorporating a node encoder, a vehicle context encoder, and a decoder, with a hyper-network technique to efficiently handle multi-objective optimization. Experimental results demonstrate that our approach finds better solutions than current state-of-the-art methods on VRPRB benchmark instances while maintaining higher computational efficiency. By fully leveraging the strengths of deep reinforcement learning, our approach provides a scalable and adaptive alternative to traditional heuristic and exact algorithms, achieving high-quality solutions for complex real-world routing problems. To enhance scalability and training efficiency, we introduce a two-stage reinforcement learning strategy that enables E-AM to solve VRPRB instances with up to 1000 customers. To promote transparency and reproducibility, we have open-sourced our implementation<span><span>¹</span></span>.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"208 ","pages":"Article 104632"},"PeriodicalIF":8.8,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum to “Cost allocation in a robust two-stage resource allocation game: fairness and robustness”. [Trans. Res. Part E: Logist. Trans. Rev. 207 (2026) 104633]","authors":"Menghang Wang,&nbsp;Lan Lu,&nbsp;Lindong Liu,&nbsp;Jie Wu","doi":"10.1016/j.tre.2026.104680","DOIUrl":"10.1016/j.tre.2026.104680","url":null,"abstract":"","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"208 ","pages":"Article 104680"},"PeriodicalIF":8.8,"publicationDate":"2026-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145956561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An integrated framework of vessel demand shifting and port capacity utilization for congestion mitigation","authors":"Haowen Lei ,&nbsp;Shuai Jia","doi":"10.1016/j.tre.2025.104660","DOIUrl":"10.1016/j.tre.2025.104660","url":null,"abstract":"<div><div>Port congestion remains a critical hurdle for global maritime logistics, particularly as opportunities for infrastructure expansion become increasingly limited. In this study, we introduce a unified optimization framework that coordinates vessel service demand with port capacity, empowering the mitigation of port congestion. The integrated framework comprises three key components: A demand shifting model that optimizes vessel arrival distributions over time; a descriptive queueing model that characterizes vessel arrival and service processes, enabling a holistic evaluation of congestion levels; and a resource management model that effectively allocates available port resources to vessels by leveraging a data-driven throughput envelope calibrated from port operational data. To address the computational challenges posed by the integration these models, we develop a bi-level iterative solution algorithm that iteratively enhances the coordination between demand-side and supply-side decisions, achieving a satisfactory performance with respect to tractability and scalability. Empirical validation is performed using a large-scale, real-world operational dataset from a major container port in Shanghai. Our algorithm proves highly scalable, solving large-scale instances 20–30 times faster than Gurobi and achieving near-optimal solutions (e.g., optimality gaps as low as 0.91 %). The framework delivers economic value with a substantial reduction of total system costs (ranging from 14.47 %-16.67 %) over a non-integrated baseline. The results highlight the practical value and generalizability of the unified approach for enhancing the efficiency and resilience of port systems.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"208 ","pages":"Article 104660"},"PeriodicalIF":8.8,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Service network design for electric vehicles with combined battery swapping and recharging","authors":"Xudong Diao ,&nbsp;Meng Qiu","doi":"10.1016/j.tre.2026.104668","DOIUrl":"10.1016/j.tre.2026.104668","url":null,"abstract":"<div><div>Incorporating both battery swapping and recharging strategies within electric vehicle (EV) service networks provides a flexible means of mitigating range limitations. While jointly optimizing these strategies poses significant modeling and computational challenges, it also yields valuable insights into their relative operational performance. We develop an optimization framework that jointly determines service network design, EV routing decisions, and the scheduling of recharging and battery swapping operations, while respecting capacity constraints on both activities. This study establishes a unified mixed-integer programming framework for EV service network design that integrates the two replenishment strategies under system-wide capacity limitations. To handle large-scale instances efficiently, we employ a column generation scheme, in which the pricing subproblem is solved using a bidirectional labeling algorithm supported by tailored dominance rules and problem-specific resource extension functions. In addition, a dedicated heuristic is designed to construct high-quality integer solutions. Computational experiments based on real-world case studies show that when both strategies are available, battery swapping tends to outperform recharging due to its shorter service time, highlighting the scalability and practical relevance of the proposed approach.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"208 ","pages":"Article 104668"},"PeriodicalIF":8.8,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Climate shock impacts on supply chains: the case of the truckload spot market","authors":"Sara Hsu ,&nbsp;Andrew Balthrop ,&nbsp;Dan Pellathy ,&nbsp;Travis Kulpa ,&nbsp;Gonzalo Andrew Ferrada ,&nbsp;Joshua Fu","doi":"10.1016/j.tre.2025.104609","DOIUrl":"10.1016/j.tre.2025.104609","url":null,"abstract":"<div><div>Climate shocks increasingly disrupt supply chains, yet research has focused primarily on mitigation strategies (i.e., carbon reduction), leaving adaptation strategies comparatively understudied. We begin to fill this gap by studying how transportation managers within a supply chain respond to climate-related shocks, defined as a month in which a state’s exposure to extreme temperature or precipitation events rises significantly, measured by the custom University of Tennessee Climate Index (UTCI), which combines anomalies in high/low temperature and heavy precipitation with population exposure. Drawing on structured interviews with transportation managers, we uncover beliefs that shippers tend to be less demand-responsive in the short-term to climate-related shocks, often prioritizing the desire to move freight at any reasonable cost. Motor carriers, in contrast, are more sensitive to price. To test these qualitative assessments, we regress monthly state-level truckload spot market data from the contiguous 48 states on the UTCI in reduced-form two-way fixed effects specifications, finding that a one-standard-deviation increase in climate shocks increases freight prices by 1.9%, with minimal effects on freight volume, indicating that market adjustments occur primarily through price rather than quantity. We further estimate IV specifications based on three-stage least squares (3SLS) models to disentangle the net causal effects from the reduced form specification. Consistent with our interviews, we find motor carriers are more sensitive than shippers to climate shocks. The results have important implications, offering shippers, carriers, and brokers with concrete price-change benchmarks they can use to budget transportation spend, design contract–spot portfolios, and plan capacity during climate shocks.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"208 ","pages":"Article 104609"},"PeriodicalIF":8.8,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing on-site green hydrogen consumption using heavy-duty hydrogen fuel cell electric vehicles","authors":"Mohammad Reza Ghorbanali Zadegan ,&nbsp;Zhaomiao Guo","doi":"10.1016/j.tre.2025.104627","DOIUrl":"10.1016/j.tre.2025.104627","url":null,"abstract":"<div><div>Transitioning to zero-emission heavy-duty freight vehicles, such as fuel cell electric vehicles (FCEVs), could contribute to mitigating the environmental footprint in the freight sector. However, sustainable and economical production, transportation, and storage of hydrogen fuels remain challenging. The goal of this study is to leverage the flexibility of logistics delivery to maximize the utilization of green hydrogen while balancing the freight operational costs. To achieve this goal, we develop a mixed integer programming (MIP) model that optimizes the planning, routing/scheduling, refueling, and on-site “green” hydrogen production to support the operations of FCEVs. The model strategically determines the locations and sizes of hydrogen refueling stations (HRSs) and the corresponding vehicle routing/refueling plans to minimize total costs, while utilizing solar-powered on-site hydrogen generation in freight operations. Our model was initially tested using the Solomon benchmark and later implemented in a real-world case study of freight distribution systems in Florida to evaluate its robustness and efficiency. Computational performance between exact methods and a customized Adaptive Large Neighborhood Search (ALNS) metaheuristic algorithm are also compared. Extensive sensitivity analyses were conducted on operational and environmental parameters to generate numerical insights. We found that strategic trade-offs in routing the FCEV fleet and placing HRSs, coupled with optimized solar hydrogen production, substantially reduce operational costs and enhance sustainability.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"208 ","pages":"Article 104627"},"PeriodicalIF":8.8,"publicationDate":"2026-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing driver’s discount order acceptance strategies: A policy-improved deep deterministic policy gradient framework","authors":"Hanwen Dai ,&nbsp;Chang Gao ,&nbsp;Fang He ,&nbsp;Congyuan Ji ,&nbsp;Yanni Yang","doi":"10.1016/j.tre.2025.104628","DOIUrl":"10.1016/j.tre.2025.104628","url":null,"abstract":"<div><div>The rapid expansion of platform integration has emerged as an effective solution to mitigate market fragmentation by consolidating multiple ride-hailing platforms into a single application. To address heterogeneous passenger preferences, third-party integrators provide Discount Express service delivered by express drivers at lower trip fares. For the individual platform, encouraging broader participation of drivers in Discount Express services has the potential to expand the accessible demand pool and improve matching efficiency, but often at the cost of reduced profit margins. This study aims to dynamically manage drivers’ acceptance of Discount Express from the perspective of an individual platform, incorporating the spatiotemporal demand-supply patterns. The lack of historical data under the new business model necessitates online learning. However, early-stage exploration through trial and error can be costly in practice, highlighting the need for reliable early-stage performance in real-world deployment. To address these challenges, this study formulates the decision regarding the proportion of drivers accepting discount orders as a continuous control task. In response to the high stochasticity, the opaque matching mechanisms employed by third-party integrator, and the limited availability of historical data, we propose an innovative policy-improved deep deterministic policy gradient (pi-DDPG) framework. The proposed framework incorporates a refiner module to boost policy performance during the early training phase, leverages a convolutional long short-term memory network to effectively capture complex spatiotemporal patterns, and adopts a prioritized experience replay mechanism to enhance learning efficiency. A customized simulator based on a real-world dataset is developed to validate the effectiveness of the proposed pi-DDPG. Numerical experiments demonstrate that pi-DDPG achieves superior learning efficiency and significantly reduces early-stage training losses, enhancing its applicability to practical ride-hailing scenarios.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"208 ","pages":"Article 104628"},"PeriodicalIF":8.8,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Discriminatory order assignment and payment-setting of on-demand food-delivery platforms: A multi-action and multi-agent reinforcement learning framework","authors":"Zijian Zhao ,&nbsp;Sen Li","doi":"10.1016/j.tre.2025.104653","DOIUrl":"10.1016/j.tre.2025.104653","url":null,"abstract":"<div><div>This paper studies the discriminatory order assignment and payment-setting strategies for on-demand food-delivery platforms. We consider an on-demand food-delivery platform that coordinates customers, couriers, and restaurants to maximize the profit. It determines how to bundle orders, assign orders to couriers, and set payments to couriers in real-time. These decisions are made in a personalized manner, depending on the historical data collected from each of the couriers, such as the order acceptance and rejection rates under distinct scenarios of order assignment and payment values. A Markov Decision Process is formulated for the courier, capturing the decisions of the platform (including differentiated order assignment/bundling strategies and the discriminatory payment-settings decisions) while considering its dependence on the personalized work-related data of each individual courier. To derive the optimal policies, we propose a novel multi-action and multi-agent deep reinforcement learning framework, where a double Deep Q-Network is employed to develop discrete order assignment strategies, and double Proximal Policy Optimization is utilized to determine continuous payment decisions. Within this learning framework, we introduce a novel neural network architecture that leverages the Query-Key attention mechanism to transform multiplicative time complexities into additive computation complexity for order assignment, and we adopt a variable-length Bi-LSTM module that compresses variable-length order sequence into a fixed-dimensional feature space to enhance scalability. The proposed neural network and algorithmic framework was validated in a case study using real-world food-delivery data from Hong Kong. By comparing the proposed method with a vanilla MLP-based neural network architecture, we find that the proposed neural network architecture significantly enhances platform performance: it increases the number of orders served by 5.25%, reduces platform expenses by 10%, and improves the overall reward of the platform by over 50%. Additionally, our results reveal that couriers with higher order rejection rates receive more orders during peak hours but earn lower wages. This counterintuitive finding is attributed to a strategic approach by the platform to differentiate order allocation: instead of simply allocating fewer orders to couriers with higher rejection rates, the platform preferentially assigns longer-distance trips to couriers with a higher likelihood of order acceptance. These findings expose the implicit biases in the discriminatory algorithms used by the profit-maximizing platform and highlight potential areas for governmental regulatory intervention. The code of this paper is provided at <span><span>https://github.com/RS2002/Discriminatory-Food-Delivery</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"208 ","pages":"Article 104653"},"PeriodicalIF":8.8,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inventory-constrained online learning for revenue management with delayed feedback","authors":"Sheng Ji","doi":"10.1016/j.tre.2025.104649","DOIUrl":"10.1016/j.tre.2025.104649","url":null,"abstract":"<div><div>Delayed feedback is a prevalent challenge in modern logistics and transportation systems, especially on digital retail platforms. This paper investigates an online learning and pricing problem characterized by aggregated and anonymous delays. In this setting, neither demand nor revenue is immediately observable following a pricing decision; instead, these metrics become available to the retailer only after some stochastic delay. The retailer also faces an initial inventory constraint, creating a complex exploration-exploitation trade-off among learning demand, generating revenue, and managing inventory. To address this challenge, we propose a novel batch-based learning algorithm, referred to as Bandits with Dual Mirror Descent (BUD for short), which integrates mirror descent with bandit control. The algorithm employs a carefully designed batch structure to isolate the impact of delayed feedback, while combining Upper Confidence Bound (UCB) for pricing with dual updates for inventory management. Our theoretical analysis shows that the regret (defined as the revenue gap between the optimal policy and the learning algorithm) of BUD grows sublinearly with the selling horizon and matches the known lower bounds in both bandit with delays and online pricing problems. We conducted numerical experiments to demonstrate that the regret of BUD converges to 0 in various scenarios.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"208 ","pages":"Article 104649"},"PeriodicalIF":8.8,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145940516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}