Transportation Research Part B-Methodological最新文献

{"title":"A contextual framework for learning routing experiences in last-mile delivery","authors":"Huai Jun (Norina) Sun,&nbsp;Okan Arslan","doi":"10.1016/j.trb.2025.103172","DOIUrl":"10.1016/j.trb.2025.103172","url":null,"abstract":"<div><div>This paper presents a contextual framework for solving the experience-driven traveling salesman problem in last-mile delivery. The objective of the framework is to generate routes similar to historic high-quality ones as classified by operational experts by considering the unstructured and complex features of the last-mile delivery operations. The framework involves learning a transition weight matrix and using it in a TSP solver to generate high quality routes. In order to learn this matrix, we use descriptive analytics to extract and select important features of the high-quality routes from the data. We present a <em>rule-based method</em> using such extracted features. We then introduce a factorization of the transition weight matrix by features, which reduces the dimensions of the information to be learned. In the predictive analytics stage, we develop (1) <em>Score Guided Coordinate Search</em> as a derivative-free optimization algorithm, and (2) <em>label-guided methods</em> inspired by supervised learning algorithms for learning the routing preferences from the data. Any hidden preferences that are not obtained in the descriptive analytics are captured at this stage. Our approach allows us to blend the advantages of different facets of data science in a single collaborative framework, which is effective in generating high-quality solutions for a last-mile delivery problem. We test the efficiency of the methods using a case study based on Amazon Last-Mile Routing Challenge organized in 2021. A preliminary version of our rule-based method received the third place and a $25,000 award in the challenge. In this paper, we improve the learning performance of our previous methods through predictive analytics, while ensuring that the methods are effective, interpretable and flexible. Our best performing algorithm improves the performance of our rule-based method on an out-of-sample testing dataset by more than 23.1%.</div></div>","PeriodicalId":54418,"journal":{"name":"Transportation Research Part B-Methodological","volume":"194 ","pages":"Article 103172"},"PeriodicalIF":5.8,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interactive biobjective optimization algorithms and an application to UAV routing in continuous space","authors":"Hannan Tureci-Isik ,&nbsp;Murat Köksalan ,&nbsp;Diclehan Tezcaner-Öztürk","doi":"10.1016/j.trb.2025.103162","DOIUrl":"10.1016/j.trb.2025.103162","url":null,"abstract":"<div><div>We develop interactive optimization algorithms for biobjective problems with continuous nondominated frontiers to search for the most preferred solution of a decision maker who is assumed to have an underlying linear or quasiconvex preference function. We progressively acquire preference information from the decision maker through pairwise comparisons of efficient solutions. We keep reducing the search space based on the obtained preference information and the properties of the form of the preference function. Our algorithms provide a performance guarantee on the final solution's distance from the most preferred solution in the objective function space. We demonstrate the algorithms on complex Unmanned Air Vehicle routing problems in continuous space with nonconvex and continuous nondominated frontiers. We consider the objectives of minimizing the total distance traveled and minimizing the total radar detection threat. We simulate the preference function of the decision maker using several underlying preference functions. The interactive algorithms for all preference functions converge to solutions within the desired accuracies after a few pairwise comparisons.</div></div>","PeriodicalId":54418,"journal":{"name":"Transportation Research Part B-Methodological","volume":"193 ","pages":"Article 103162"},"PeriodicalIF":5.8,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143350867","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":"Adaptive signal control at partially connected intersections: A stochastic optimization model for uncertain vehicle arrival rates","authors":"Shaocheng JIA ,&nbsp;S.C. WONG ,&nbsp;Wai WONG","doi":"10.1016/j.trb.2025.103161","DOIUrl":"10.1016/j.trb.2025.103161","url":null,"abstract":"<div><div>Optimizing traffic signal control is crucial for improving efficiency in congested urban environments. Current adaptive signal control systems predominantly rely on on-road detectors, which entail significant capital and maintenance costs, thereby hindering widespread implementation. In this paper, a novel connected vehicle (CV)-based adaptive signal control (CVASC) framework is proposed that optimizes signal plans on a cycle-by-cycle basis without the need for on-road detectors, leveraging partial CV data. The framework comprises a consequential system delay (CSD) model, deterministic penetration rate control (DPRC), and stochastic penetration rate control (SPRC). The CSD model analytically estimates vehicle arrival rates and, consequently, the total junction delay, utilizing CV penetration rates as essential inputs. Employing the CSD model without considering CV penetration rate uncertainty results in fixed vehicle arrival rates and leads to DPRC. On the other hand, incorporating CV penetration rate uncertainty accounts for uncertain vehicle arrival rates, establishing SPRC, which poses a high-dimensional, non-convex, and stochastic optimization problem. An analytical stochastic delay model using generalized polynomial chaos expansion is proposed to efficiently and accurately estimate the mean, variance, and their gradients for the CSD model within SPRC. To solve DPRC and SPRC, a gradient-guided golden section search algorithm is introduced. Comprehensive numerical experiments and VISSIM simulations demonstrate the effectiveness of the CVASC framework, emphasizing the importance of accounting for CV penetration rate uncertainty and uncertain vehicle arrival rates in achieving optimal solutions for adaptive signal optimizations.</div></div>","PeriodicalId":54418,"journal":{"name":"Transportation Research Part B-Methodological","volume":"193 ","pages":"Article 103161"},"PeriodicalIF":5.8,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143325364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-time vehicle relocation, personnel dispatch and trip pricing for carsharing systems under supply and demand uncertainties","authors":"Mengjie Li ,&nbsp;Haoning Xi ,&nbsp;Chi Xie ,&nbsp;Zuo-Jun Max Shen ,&nbsp;Yifan Hu","doi":"10.1016/j.trb.2025.103154","DOIUrl":"10.1016/j.trb.2025.103154","url":null,"abstract":"<div><div>In one-way carsharing systems, striking a balance between vehicle supply and user demand across stations poses considerable operational challenges. While existing research on vehicle relocation, personnel dispatch, and trip pricing have shown effectiveness, they often struggle with the complexities of fluctuating and unpredictable demand and supply patterns in uncertain environments. This paper introduces a real-time relocation-dispatch-pricing (RDP) problem, within an evolving time-state-extended transportation network, to optimize vehicle relocation, personnel dispatch, and trip pricing in carsharing systems considering both demand and supply uncertainties. Furthermore, recognizing the critical role of future insights in real-time decision making and strategic adaptability, we propose a novel two-stage anticipatory-decision rolling horizon (ADRH) optimization framework where the first stage solves a real-time RDP problem to make actionable decisions with future supply and demand distributions, while also incorporating anticipatory guidance from the second stage. The proposed RDP problem under the ADRH framework is then formulated as a stochastic nonlinear programming (SNP) model. However, the state-of-the-art commercial solvers are inadequate for solving the proposed SNP model due to its solution complexity. Thus, we customize a hybrid parallel Lagrangian decomposition (HPLD) algorithm, which decomposes the RDP problem into manageable subproblems. Extensive numerical experiments using a real-world dataset demonstrate the computational efficiency of the HPLD algorithm and its ability to converge to a near-globally optimal solution. Sensitivity analyses are conducted focusing on parameters such as horizon length, fleet size, number of dispatchers, and demand elasticity. Numerical results show that the profits under the stochastic scenario are 18<span><math><mtext>%</mtext></math></span> higher than those under the deterministic scenario, indicating the significance of incorporating uncertain and future information into the operational decisions of carsharing systems.</div></div>","PeriodicalId":54418,"journal":{"name":"Transportation Research Part B-Methodological","volume":"193 ","pages":"Article 103154"},"PeriodicalIF":5.8,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143325369","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":"Conditional forecasting of bus travel time and passenger occupancy with Bayesian Markov regime-switching vector autoregression","authors":"Xiaoxu Chen ,&nbsp;Zhanhong Cheng ,&nbsp;Alexandra M. Schmidt ,&nbsp;Lijun Sun","doi":"10.1016/j.trb.2024.103147","DOIUrl":"10.1016/j.trb.2024.103147","url":null,"abstract":"<div><div>Accurate forecasting of bus travel time and passenger occupancy with uncertainty is essential for both travelers and transit agencies/operators. However, existing approaches to forecasting bus travel time and passenger occupancy mainly rely on deterministic models, providing only point estimates. In this paper, we develop a Bayesian Markov regime-switching vector autoregressive model to jointly forecast both bus travel time and passenger occupancy with uncertainty. The proposed approach naturally captures the intricate interactions among adjacent buses and adapts to the multimodality and skewness of real-world bus travel time and passenger occupancy observations. We develop an efficient Markov chain Monte Carlo (MCMC) sampling algorithm to approximate the resultant joint posterior distribution of the parameter vector. With this framework, the estimation of downstream bus travel time and passenger occupancy is transformed into a multivariate time series forecasting problem conditional on partially observed outcomes. Experimental validation using real-world data demonstrates the superiority of our proposed model in terms of both predictive means and uncertainty quantification compared to the Bayesian Gaussian mixture model.</div></div>","PeriodicalId":54418,"journal":{"name":"Transportation Research Part B-Methodological","volume":"192 ","pages":"Article 103147"},"PeriodicalIF":5.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable State-Space Model of Urban Dynamics for Human-Machine Collaborative Transportation Planning","authors":"Jiangbo Yu ,&nbsp;Michael F. Hyland","doi":"10.1016/j.trb.2024.103134","DOIUrl":"10.1016/j.trb.2024.103134","url":null,"abstract":"<div><div>Strategic Long-Range Transportation Planning (SLRTP) is pivotal in shaping prosperous, sustainable, and resilient urban futures. Existing SLRTP decision support tools predominantly serve forecasting and evaluative functions, leaving a gap in directly recommending optimal planning decisions. To bridge this gap, we propose an Interpretable State-Space Model (ISSM) that considers the dynamic interactions between transportation infrastructure and the broader urban system. The ISSM directly facilitates the development of optimal controllers and reinforcement learning (RL) agents for optimizing infrastructure investments and urban policies while still allowing human-user comprehension. We carefully examine the mathematical properties of our ISSM; specifically, we present the conditions under which our proposed ISSM is Markovian, and a unique and stable solution exists. Then, we apply an ISSM instance to a case study of the San Diego region of California, where a partially observable ISSM represents the urban environment. We also propose and train a Deep RL agent using the ISSM instance representing San Diego. The results show that the proposed ISSM approach, along with the well-trained RL agent, captures the impacts of coordinating the timing of infrastructure investments, environmental impact fees for new land development, and congestion pricing fees. The results also show that the proposed approach facilitates the development of prescriptive capabilities in SLRTP to foster economic growth and limit induced vehicle travel. We view the proposed ISSM approach as a substantial contribution that supports the use of artificial intelligence in urban planning, a domain where planning agencies need rigorous, transparent, and explainable models to justify their actions.</div></div>","PeriodicalId":54418,"journal":{"name":"Transportation Research Part B-Methodological","volume":"192 ","pages":"Article 103134"},"PeriodicalIF":5.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142867439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Revisiting McFadden’s correction factor for sampling of alternatives in multinomial logit and mixed multinomial logit models","authors":"Thijs Dekker ,&nbsp;Prateek Bansal ,&nbsp;Jinghai Huo","doi":"10.1016/j.trb.2024.103129","DOIUrl":"10.1016/j.trb.2024.103129","url":null,"abstract":"<div><div>When estimating multinomial logit (MNL) models where choices are made from a large set of available alternatives computational benefits can be achieved by estimating a quasi-likelihood function based on a sampled subset of alternatives in combination with ‘<em>McFadden’s correction factor</em>’. In this paper, we theoretically prove that McFadden’s correction factor minimises the expected information loss in the parameters of interest and thereby has convenient finite (and large sample) properties. That is, in the context of Bayesian estimation the use of sampling of alternatives in combination with McFadden’s correction factor provides the best approximation of the posterior distribution for the parameters of interest irrespective of sample size. As sample sizes become sufficiently large consistent point estimates for MNL can be obtained as per McFadden’s original proof. McFadden’s correction factor can therefore effectively be applied in the context of Bayesian MNL models. We extend these results to the context of mixed multinomial logit models (MMNL) by using the property of data augmentation in Bayesian estimation. McFadden’s correction factor minimises the expected information loss with respect to the augmented individual-level parameters, and in turn also for the population parameters characterising the shape and location of the mixing density in MMNL. Again, the results apply to finite and large samples and most importantly circumvent the need for additional correction factors previously identified for estimating MMNL models using maximum simulated likelihood. Monte Carlo simulations validate this result for sampling of alternatives in Bayesian MMNL models.</div></div>","PeriodicalId":54418,"journal":{"name":"Transportation Research Part B-Methodological","volume":"192 ","pages":"Article 103129"},"PeriodicalIF":5.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142788858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unveiling network capacity potential with imminent supply information part I: Theoretical derivation","authors":"Dianchao Lin ,&nbsp;Li Li","doi":"10.1016/j.trb.2024.103150","DOIUrl":"10.1016/j.trb.2024.103150","url":null,"abstract":"<div><div>An urban network’s supply capability is notably impacted by the operational efficiency of its bottlenecks, namely the intersections. An essential and powerful metric for describing a network’s overall supply performance is the capacity region (CR), which represents all potential combinations of capacities for different intersection movements. This study explores the impact of imminent saturation flow rate (I-SFR) information on the CR of traffic networks. The work is separated into Part I and Part II to prevent a lengthy paper. Specifically, in Part I, we systematically formulate the conflicting relationship between different movements using greatest conflicting group and green ratio constraints, formally define the dominating relationship between different CRs, and theoretically demonstrate 1) how knowing the accurate I-SFRs of additional conflicting movements can expand the CR, resulting in a larger CR that dominates the original one, and 2) how improving the prediction accuracy of observed movements’ I-SFRs can enlarge the CR. Part II will develop a “ruler” – the BackPressure control with partial I-SFR information – to measure the changes in CR and validate the theories of Part I through simulation experiments.</div></div>","PeriodicalId":54418,"journal":{"name":"Transportation Research Part B-Methodological","volume":"192 ","pages":"Article 103150"},"PeriodicalIF":5.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446094","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":"Bike network planning in limited urban space","authors":"Nina Wiedemann ,&nbsp;Christian Nöbel ,&nbsp;Lukas Ballo ,&nbsp;Henry Martin ,&nbsp;Martin Raubal","doi":"10.1016/j.trb.2024.103135","DOIUrl":"10.1016/j.trb.2024.103135","url":null,"abstract":"<div><div>The lack of cycling infrastructure in urban environments hinders the adoption of cycling as a viable mode for commuting, despite the evident benefits of (e-)bikes as sustainable, efficient, and health-promoting transportation modes. Bike network planning is a tedious process, relying on heuristic computational methods that frequently overlook the broader implications of introducing new cycling infrastructure, in particular the necessity to repurpose car lanes. In this work, we call for optimizing the trade-off between bike and car networks, effectively pushing for Pareto optimality. This shift in perspective gives rise to a novel linear programming formulation towards optimal bike network allocation. Our experiments, conducted using both real-world and synthetic data, testify the effectiveness and superiority of this optimization approach compared to heuristic methods. In particular, the framework provides stakeholders with a range of lane reallocation scenarios, illustrating potential bike network enhancements and their implications for car infrastructure. Crucially, our approach is adaptable to various bikeability and car accessibility evaluation criteria, making our tool a highly flexible and scalable resource for urban planning. This paper presents an advanced decision-support framework that can significantly aid urban planners in making informed decisions on cycling infrastructure development.</div></div>","PeriodicalId":54418,"journal":{"name":"Transportation Research Part B-Methodological","volume":"192 ","pages":"Article 103135"},"PeriodicalIF":5.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Shore-power capacity allocation in a container shipping network under ships’ strategic behaviors","authors":"Zhijia Tan ,&nbsp;Dian Sheng ,&nbsp;Yafeng Yin","doi":"10.1016/j.trb.2024.103151","DOIUrl":"10.1016/j.trb.2024.103151","url":null,"abstract":"<div><div>Shore power (SP) is an effective way to cut carbon emissions at ports by replacing fuel oil for docked ships. The adoption of SP by ships hinges on the onboard transformer setup cost and the cost saving from SP utilization in comparison with fuel oil. The allocation of SP capacity at ports influences the availability of SP-equipped berths and, along with conventional berths, incurs potential service delays. Misallocation can actually increase port emissions. This paper addresses the SP capacity allocation problem in a general container shipping network with multiple ports and a ship fleet. The service congestion or capacity-dependent waiting time at berths is considered, which results in strategic choices or choice equilibrium of ships on SP adoption. The emission quantity at each port is affected by the choice equilibrium of ships. For the benchmark case with a single port, we analytically identify a threshold SP capacity above which emissions decrease, below which a counterintuitive increase occurs. For the general shipping network, assuming government covers transformer setup costs, we develop an exact method to determine the critical level for each port to ensure emission reductions. A case study based on the Yangtze River is conducted to illustrate the analytical results.</div></div>","PeriodicalId":54418,"journal":{"name":"Transportation Research Part B-Methodological","volume":"192 ","pages":"Article 103151"},"PeriodicalIF":5.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142918066","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}