Transportation Research Part C-Emerging Technologies最新文献

{"title":"Learning human-like decisions for flight approach: Environment and an imitation learning method","authors":"Haifeng Liu,&nbsp;Dongyue Guo,&nbsp;Shizhong Zhou,&nbsp;Zheng Zhang,&nbsp;Hongyu Yang,&nbsp;Yi Lin","doi":"10.1016/j.trc.2025.105142","DOIUrl":"10.1016/j.trc.2025.105142","url":null,"abstract":"<div><div><span><span>¹</span></span> Flight approach in terminal airspace is a challenging task with high aircraft density and maneuvering in air traffic control decisions. Existing reinforcement learning methods were only studied based on simulation environments, and also suffered from sparse reward and state-space explosion problems. In this work, an imitation learning-based autonomous framework, AppGAIL, is proposed to achieve the flight approach decision based on human expert demonstrations, which has the ability to eliminate the requirement of designing handcrafted rewards. To cope with the state-space explosion problem, a cylindrical grid airspace model is designed to convert the earth space to discrete airspace, obtaining the transformation of the real-time traffic situation by near distance–identical cells. The generative adversarial mechanism is applied to achieve imitation learning by distinguishing the source of the input observations (state and action sequences with a sliding window), i.e., from the generator or expert demonstrations. Since all human expert demonstrations are safe operations, limiting the model to learn knowledge of flight conflicts and confusing the generator to plan conflict trajectories, a conflict-aware discriminator is proposed to detect possible conflicts by a multi-task framework with learnable weights, which further supports the adversarial training. The real-world traffic dataset is applied to validate the proposed method, in which several custom metrics are proposed to support the real-world air traffic control. The experimental results demonstrate that the AppGAIL outperforms other baseline methods, achieving only 0.67% potential conflict rate and 3.732 kilometers dynamic time wrapping distance. Most importantly, all proposed technical modules contribute the desired performance improvement. Additionally, multi-aircraft planning and real-time factors can also be resolved to improve the applicability of the proposed method.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105142"},"PeriodicalIF":7.6,"publicationDate":"2025-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143899412","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":"Comparing skip-stop and all-stop transit network designs","authors":"Li Zhen,&nbsp;Weihua Gu,&nbsp;Xiaokuan Zhao","doi":"10.1016/j.trc.2025.105149","DOIUrl":"10.1016/j.trc.2025.105149","url":null,"abstract":"<div><div>Skip-stop service is a public transportation scheme designed to improve operational speed and travel efficiency by skipping certain stops along a route. This paper focuses on the optimal design of a specific type of skip-stop service, known as AB-type service. While previous research primarily addressed corridor-level designs for this service, we present a continuous model to optimize an AB-type skip-stop service network in a square city layout. Our objective is to minimize the combined costs of the agency and patrons’ travel time by making optimal decisions about network design—including line and stop spacings—and the operational plan, consisting of the number of skip-stop routes and service headways.</div><div>We conduct extensive numerical case studies to compare the performance of the skip-stop service with two variants of all-stop services: one incorporating non-transfer stops and one without. We examine two prevalent transit modes: rail and bus. The results indicate that the optimal skip-stop network outperforms all-stop networks in most scenarios for rail systems. In contrast, for bus systems, the all-stop service without non-transfer stops performs best. Interestingly, skip-stop service results in a lower commercial speed compared to all-stop services, and it also significantly reduces agency costs for rail systems. Moreover, we observe that the advantages of skip-stop service at the network level decrease as travel demand increases. These findings are contrary to those from corridor-level studies, highlighting the importance of understanding network-level dynamics when planning skip-stop services in a broader range.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"176 ","pages":"Article 105149"},"PeriodicalIF":7.6,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143895010","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":"A dynamic continuous flow intersection collaborative control framework based on virtual channelization in an intelligent connected environment","authors":"Kangyu Zhang ,&nbsp;Lishan Sun ,&nbsp;Dewen Kong ,&nbsp;Yan Xu ,&nbsp;Ziyuan Gu ,&nbsp;Zilong Zhao ,&nbsp;Miao Wang","doi":"10.1016/j.trc.2025.105123","DOIUrl":"10.1016/j.trc.2025.105123","url":null,"abstract":"<div><div>This study proposes a dynamic continuous flow intersection cooperative (DCFIC) control framework, integrating traditional continuous flow intersections with connected and automated vehicle technology. The challenge of adapting to traffic demand at conventional continuous flow intersections is addressed by incorporating virtual channelization, enabling real-time dynamic matching of road space resources to high traffic demand within brief time frames. A dynamic speed control method is introduced for exit vehicles to mitigate conflicts between these vehicles and left-turning vehicles. This method allows left-turning vehicles to change lanes without halting, actualizing continuous traffic flow. In addition, we have integrated all the methods into a unified control framework (DCFIC) for systematic control of intersection. The framework encompasses five primary modules: space layout optimization module, safety distance calculation module, left shift lane change condition I determination module, left shift lane change condition II determination module and exit vehicle platoon combination generation module. The DCFIC system activates different control modules in real-time based on the zone through which vehicles are navigating. Simulation results demonstrate that, under diverse traffic demand scenarios, DCFIC outperforms both traditional signal controls and continuous flow intersections. It exhibits pronounced adaptability, markedly reducing delays.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"175 ","pages":"Article 105123"},"PeriodicalIF":7.6,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143881969","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":"Mobility resilience and recovery dynamics: Parsimonious framework beyond V-shapes","authors":"Fang Tang ,&nbsp;Xiangyong Luo ,&nbsp;Xuesong (Simon) Zhou","doi":"10.1016/j.trc.2025.105122","DOIUrl":"10.1016/j.trc.2025.105122","url":null,"abstract":"<div><div>System resilience is increasingly crucial in responding to disruptions from human activities, climate change, earthquakes, pandemics, etc. Existing literature commonly employs V-shaped or variants, such as U-shaped or trapezoid-shaped models, to describe system performance trends, but capturing the non-linear dynamics, identifying steady-state points, and analyzing impacts by interventions have been challenging, especially across multiple resolutions. While the challenges of extending the model to capture multiple waves are acknowledged, this study focuses exclusively on single-wave scenarios. To gain a deeper understanding of system resilience, this paper proposes an Ordinary Differential Equation (ODE): the Double Quadratic Queue (DQQ) model, which is adapted from the fluid-based Polynomial Arrival Queue (PAQ) model proposed by Newell (1982). The DQQ Model offers a parsimonious framework for understanding and estimating the dynamic evolution of disruption and recovery processes. The queue-theoretical ODE is adapted to multiple resolutions from national to route level in complex systems and is capable of identifying steady-state points and quantifying system resilience metrics. To validate the applicability, this paper employs transit mobility data at national, state, and county resolutions from Google COVID-19 Community Mobility Reports and two-way ridership data for RapidRide routes in King County, Seattle. The results reveal that the DQQ model demonstrates a notable improvement over the traditional models, particularly in identifying and approximating stabilization status at the end of the recovery process. Also, this paper conducts regression analysis to examine the correlation between resilience metrics. In addition, to examine the impact of the interventions on the system’s recovery capability, statistical analysis is conducted to analyze the impact of the new opening of the H Line to other lines.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"175 ","pages":"Article 105122"},"PeriodicalIF":7.6,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143877264","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 experimental study on Max-Pressure traffic controller based on travel time delays","authors":"Razi Zoabi,&nbsp;Jack Haddad","doi":"10.1016/j.trc.2025.105070","DOIUrl":"10.1016/j.trc.2025.105070","url":null,"abstract":"<div><div>First, this paper develops and examines a new <em>travel time-based</em> traffic signal controller. By applying a decentralized approach that relies solely on local information, the controller optimizes phase duration to maximize throughput. Three issues from previous queue-based max-pressure controllers are addressed: (i) infinite link capacity, (ii) non-fixed phase sequences, and (iii) the neglect of spatial distribution of the queues. The newly developed cyclic time-based max-pressure control is compared with existing cyclic queue-based and time-based max-pressure schemes. The results show that the introduced time-based approach offers improved fairness and more effective decision-making.</div><div>Second, new time-varying schemes are developed for the time-based max-pressure controller: bounded cycle lengths, which impose stability-preserving minimum and maximum limits, and unbounded cycle lengths, which dynamically adjust based on real-time traffic flow for enhanced flexibility. A comparative analysis with fixed cycle length schemes highlights the advantages of appropriate cycle length allocation for improved performance.</div><div>Finally, the developed controller was evaluated through simulation tests and an experimental case study in an urban traffic network, specifically at a complex T-intersection. The intersection, which was originally controlled by loop detectors, was isolated from adjacent intersections for the experiment, with the loop detectors disconnected. Traffic control was instead managed using Bluetooth data, providing real-time travel time information and enabling the intersection to adapt to current traffic conditions while complying with traffic regulations and constraints. The results demonstrated that, despite the constraints, the adaptive controller performed more effectively than the actuated controller, providing a cost-effective solution for traffic control.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"175 ","pages":"Article 105070"},"PeriodicalIF":7.6,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143863541","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":"Group-benefit control strategy for connected automated vehicles in mixed traffic at intersections","authors":"Ruochuan Fan ,&nbsp;Jian Lu ,&nbsp;David Z.W. Wang ,&nbsp;Meng Li ,&nbsp;Qingchao Liu","doi":"10.1016/j.trc.2025.105121","DOIUrl":"10.1016/j.trc.2025.105121","url":null,"abstract":"<div><div>The unpredictable driving behavior of Human-driven Vehicles (HVs) exhibits significant complexity when mixed with Connected Autonomous Vehicles (CAVs) and the periodic variations of the intersection signal phase impact the efficiency and stability of traffic flows. In response to these challenges, this study proposed a group-benefit driving behavior control strategy based on a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm to provide comprehensive and overall efficient driving guidance for CAVs in multi-agent scenarios and reduce the impact of heterogeneous traffic flow on the signalized intersections. The dynamically encoded state enables the model to effectively adapt to dynamically changing environments, and each agent independently makes combined action decisions to achieve group benefits. Regularization methods and the attention mechanism are integrated to prevent overfitting and enhance stability, with the attention mechanism having a more significant impact. The results indicate that the model effectively reduces delays and fuel consumption even at low CAV Market Penetration Rates (MPRs), with the optimization effects significantly improving as MPR increases. Compared to the HV traffic flow, the optimized CAV traffic flow reduces average vehicle delay by 10.11% and CO₂ emissions by 20.93%. The comparison with test models, which separately adjust traffic flow and signal phases, and interpolation experiments, which modify the MPR, demonstrates the model’s strong generalization ability and adaptability. Furthermore, compared with the Multi-Agent Deep Q-Network (MADQN) model, the proposed model demonstrates greater robustness with significantly better optimization results.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"175 ","pages":"Article 105121"},"PeriodicalIF":7.6,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860135","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":"Modular electric units for first-and-last-mile reservation services considering uncertainty","authors":"Bo Sun ,&nbsp;Yu Zhou ,&nbsp;Qiang Meng","doi":"10.1016/j.trc.2025.105127","DOIUrl":"10.1016/j.trc.2025.105127","url":null,"abstract":"<div><div>This study explores the day-ahead management of a fleet of modular electric units (MEUs) providing reservation-based first-and-last-mile services (FLMRS). Given limited fleet resources, the operator seeks to strategically select requests to accept and deploy optimal MEU configurations, aiming to maximize service revenue. This process involves pre-determining MEU configurations and travel itineraries, including routing and charging plans, and providing passengers with timely feedback. Furthermore, the operational environment is variable, affected by uncertain congestion levels, with request information emerging over time. Consequently, the FLMRS problem is modeled as a stochastic, time-dependent, and dynamic routing problem, formulated by a semi-Markov decision process (SMDP). To address this, we develop a multi-agent deep hierarchical reinforcement learning (MADHRL) approach to solve the distributed SMDP model through a reshaped reward function. A tailored MEU assembly rule is introduced to manage complex interactions among agents and reduce the action space for heterogeneous MEUs with varying battery levels. A mean-field fleet state representation helps to mitigate the curse of dimensionality. Additionally, an adjustable rolling-horizon strategy is applied to balance the trade-off between potential request cancellation and profitable request collection, taking into account the distribution of passengers’ patience times. Extensive numerical experiments, based on real-world data from Singapore, validate the efficacy of our methodology. Results offer insights into effective capacity management, including optimal MEU combinations for request acceptance and response timing control, indicating a 3.22% increase in service profit by an MEU fleet compared to traditional vehicles without assembled operations.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"175 ","pages":"Article 105127"},"PeriodicalIF":7.6,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860136","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":"On-demand ridesharing based on dynamic scheduling in urban air mobility","authors":"Shanghan Li ,&nbsp;Tengfei Zhang ,&nbsp;Yiyong Xiao ,&nbsp;Daqing Li","doi":"10.1016/j.trc.2025.105111","DOIUrl":"10.1016/j.trc.2025.105111","url":null,"abstract":"<div><div>Urban Air Mobility (UAM) utilizes electric vertical take-off and landing (eVTOL) aircraft to provide fast, reliable air transport services in cities and surrounding areas. As a flexible mode of transportation service, UAM ridesharing can provide convenient and adaptive multi-modal on-demand travel. In this scenario, multi-modal mobility-on-demand service providers can offer traditional door-to-door ridesharing with an integrated solution, through connecting users to eVTOL vertiports. We establish the integrated dynamic scheduling model for UAM ridesharing, and develop a cloud-edge collaborative multi-modal mobility-on-demand service architecture. This architecture integrates ordinary, multi-hop ridesharing and air-ground integrated mobility, offering flexible travel combinations tailored to user needs. We propose a multi-modal transportation dynamic scheduling algorithm based on this architecture to solve the problem. The solution process is divided into four stages: travel service plan planning, available resource search, dynamic cooperative multiple task assignment, and vehicle rebalancing. In the first two stages, an improved pulse algorithm is used to search for feasible service plans and filter available transport resources. In the dynamic cooperative multiple task assignment stages, we use a hybrid adaptive large neighborhood search algorithm to select travel plans, allocate transport resources, and plan vehicle routes. The graph structure of the task network is used in the algorithm to decouple the original problem, thereby effectively controlling the problem size. Finally, in the vehicle rebalancing stage, idle vehicles are repositioned based on demand distribution to improve supply–demand matching efficiency. Experiments based on New York City travel data indicate that compared to traditional ridesharing, our system can significantly improve the service rate and reduce user travel time. In the best-case scenario, the service rate increased by approximately 25%, while the average detour time decreased by around 52%. This demonstrates the possibility of enhancing convenience and attractiveness of UAM, which can also provide support and reference for the design and operation of future multi-modal transportation systems.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"175 ","pages":"Article 105111"},"PeriodicalIF":7.6,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860134","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":"On solving the suburban commuting problem in megacities: Integrating ridesharing with urban rail transit","authors":"Haonan Guo ,&nbsp;Yun Wang ,&nbsp;Xuedong Yan ,&nbsp;Yu Zhou","doi":"10.1016/j.trc.2025.105120","DOIUrl":"10.1016/j.trc.2025.105120","url":null,"abstract":"<div><div>The increasing spatial separation between workplaces and residences, coupled with the continued rise in motor vehicle ownership, has significantly strained urban traffic during rush hours. Suburban commuters, in particular, experience prolonged travel times. To enhance suburban commuting efficiency and alleviate congestion, this paper introduces a novel approach to address the Suburban Commuting Problem (SCP) in megacities. The proposed solution integrates ridesharing with urban rail transit (URT) systems. By promoting ridesharing in suburban areas, commuters can broaden their options for URT stations, no longer restricted to the nearest but often overcrowded end stations. This approach enhances the accessibility of URT and helps alleviate queuing congestion at end stations. Consequently, this approach shortens travel times for suburban commuters. We formulate the SCP as an arc-flow mixed-integer linear programming model, as well as a set-partitioning formulation. We introduce a tailored branch-and-price (BP) algorithm based on the set-partitioning approach to accurately solve the SCP. To expedite the solution process for the pricing sub-problem, we devise a tailored label-setting algorithm incorporating a bi-directional search strategy. Finally, we evaluate our model and algorithm’s performance through extensive computational experiments and provide valuable managerial insights. The case results based on part of road network in Beijing indicate that the proposed optimized solution for the integrated commuting mode can reduce vehicle commuting distance by 34.65%, thereby mitigating traffic congestion and reducing pollutant emissions.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"175 ","pages":"Article 105120"},"PeriodicalIF":7.6,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143844471","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":"Exploiting the flexibility of modular buses in an urban transit system","authors":"Carlo Filippi,&nbsp;Gianfranco Guastaroba,&nbsp;Lorenzo Peirano,&nbsp;M. Grazia Speranza","doi":"10.1016/j.trc.2025.105119","DOIUrl":"10.1016/j.trc.2025.105119","url":null,"abstract":"<div><div>Urban transit systems usually operate according to fixed-route and fixed-schedule schemes by employing fixed-capacity vehicles, despite the mobility demand is unevenly spread out in both space and time. Modular buses are an emerging technology in which modules of relatively small capacity can be dynamically docked together to form greater capacity buses and can, therefore, make the transit system capable of adapting the capacity to the actual mobility demand. A module can be shifted from one line to another at pre-defined intersections and can be relocated when empty, if beneficial. We call these two operations sharing and rebalancing, respectively. Given a transit network comprising multiple bus lines and a mobility demand, we present an integer linear program to determine an optimal assignment of modules to lines, so that the mobility demand is met with a minimum total number of modules. Computational experiments show that, by exploiting the flexibility of modular buses, the total capacity deployed can be reduced by 49% with respect to a conventional transit system, whereas the average occupancy ratio increases from 41.22% to 72.85%.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"175 ","pages":"Article 105119"},"PeriodicalIF":7.6,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143837822","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}