Transportation Research Part C-Emerging Technologies最新文献

A distributed method for concurrent traffic signal and routing control of traffic networks is proposed. The method is based on the multi-commodity store-and-forward model, in which the destinations are the commodities. The system benefits from the communication between vehicles and infrastructure, providing optimal signal timings to intersections and routes to vehicles on a link-by-link basis. Using the augmented Lagrangian to model the constraints into the objective, the baseline centralized problem is decomposed into a set of objective-coupled subproblems, one for each intersection, enabling the solution to be computed by a distributed-gradient projection algorithm. The intersection agents only need to communicate and coordinate with neighboring intersections to ensure convergence to the optimal solution while tolerating suboptimal iterations that offer more flexibility, unlike other distributed approaches. Through microsimulation, we demonstrate the effectiveness of the proposed algorithm in traffic networks with time-varying demand. Computational analysis shows that the distributed problem is suitable for real-time applications. A robustness analysis show that the distributed formulation enables a graceful degradation of the system in case of failure.

Sailing speed optimization is a cost-effective strategy to improve ship energy efficiency and a viable way to fulfill emission reduction requirements. This study develops a novel ship sailing speed optimization method that considers dynamic meteorological conditions. We first develop an artificial neural network model for vessel fuel consumption rate (FCR) prediction based on a fusion dataset of ship noon reports and public meteorological data. Then, based on the predicted FCRs, the method repeatedly formulates a multistage graph based on the most recent forecasts, and optimal speeds for the remaining voyage are obtained until the vessel reaches the destination port. The computational efficiency of the optimization process is enhanced by progressively removing nodes without connections to successor nodes, starting from the penultimate stage. We examine the proposed method on two 11-day voyages of a dry bulk carrier. Results show that the proposed method demonstrates significant reductions in fuel consumption by 5.35% compared with a constant sailing speed scheme and by 7.34% compared with a static speed optimization model. In addition, the proposed model achieves similar fuel savings to those achieved by speed optimization based on actual meteorological conditions, enabling shipping companies to optimize ship sailing speeds in the absence of actual meteorological conditions. The proposed method can be applied to various types of vessels due to its flexibility and adaptability, making it a valuable tool for the shipping industry to reduce greenhouse gas (GHG) emissions, thereby supporting the International Maritime Organization (IMO)’s goal of reaching net-zero GHG emissions by around 2050.

With the increased deployment of autonomous vehicles (AVs) in mixed traffic flow, ensuring safe and efficient interactions between AVs and human road users is important. In urban environments, intersections have various conflicts that can greatly affect driving safety and traffic efficiency. This study uses road test data to examine the possible safety and efficiency impacts of intersection conflict resolution involving AVs. The contribution comprises two main aspects. Firstly. we prepare and open a high-quality lateral conflict resolution dataset derived from the Argoverse-2 data, specifically targeting urban intersections. A rigorous data processing pipeline is applied to extract pertinent scenarios, rectify anomalies, enhance data quality, and annotate conflict regimes. This effort yields 5000+ AV-involved and 16000 AV-free cases, covering rich conflict regimes and balanced traffic states. Secondly, we employ surrogate safety measures to assess the safety impact of AVs on human-driven vehicles (HVs) and pedestrians. In addition, a novel concept of Minimum Recurrent Clearance Time (MRCT) is proposed to quantify the traffic efficiency impacts of AVs during conflict resolution. The results show that, for AV–HV and HV–HV conflict resolution processes, the differences in selected safety and efficiency measures for human drivers are statistically insignificant. In contrast, pedestrians demonstrate diverse behaviour adjustments. Some pedestrians behave more conservatively when interacting with AVs than with HVs. Notably, the efficiency of AV-involved conflict resolution is significantly lower than in AV-free instances due to the conservative driving style of AVs. This efficiency gap is particularly large when AVs pass through the conflict point after human drivers in unprotected left turns. These observations offer a perspective on how AVs potentially affect the safety and efficiency of mixed traffic. The processed dataset is openly available via https://github.com/RomainLITUD/conflict_resolution_dataset.

To improve the model accuracy and control efficiency for the movements of a virtual formation, this paper investigates distributed optimal control for the virtual formation control system in railways. Adopting the relative distance braking mode, a coupled optimal control problem with nonlinear train dynamics and constraints regarding collision avoidance and jerk is formulated for the virtual formation. To handle the non-convex constrained problem efficiently, a distributed augmented Lagrangian based alternating direction inexact newton (ALADIN) method under the model predictive control (MPC) framework is developed. For the execution of the distributed computational process, the copied variables are introduced to reformulate the original coupled problem in an objective separable form. By exploiting the problem separability, the ALADIN method decomposes the reformulation into a coordinated quadratic programming problem of small-scale and several local nonlinear programming problems that can be calculated in parallel, thereby facilitating real-time control and relieving communication burden. Numerical experiments on a metro line are carried out to verify the effectiveness of the proposed model and method. Experimental results demonstrate that high-performance tracking control for virtually coupled train units can be achieved in real time.

Rush-period traffic conditions in two idealized settings are forecast into the future, when most drivers will presumably rely on adaptive cruise control (ACC) while operating their cars. Field experiments emulating the full range of congested conditions confirm that, for a given traffic speed, the spacings for ACC-vehicles tend to be larger than those in present-day congestion, where vehicles are fully human-controlled. These larger spacings mean smaller densities, which mean, in turn, that queues will be less compacted than at present. The queues will therefore expand over greater distances in the future, as more ACC-controlled vehicles enter the scene. These wider-spread, uncompacted queues spell trouble for cities, where queue storage during a rush is often a problem already.

Simulations calibrated to the field-measured data were used to explore this unintended consequence of ACC for various foreseeable futures. Assumptions favorable to ACC were adopted throughout, to produce what are likely lower-bound estimates of future queue-storage problems. These lower bounds served as simple means to address forecast uncertainties. This is because our best-case outcomes for all futures examined are still far worse than the glowing predictions from elsewhere of how ACC may someday eliminate congestion. The first idealized setting was inspired by Downtown Los Angeles, where moderately high congestion already persists during each rush, but where physically long street links help with queue storage. We predict that, owing to ACC alone, rush-period vehicle hours traveled (VHT) on this first network will grow from present-day levels by as much as 12%. In the second setting, inspired by Midtown Manhattan where congestion is already severe and link lengths are short, VHT is predicted to grow by as much as 87%. Higher bottleneck capacities often promised of ACC are shown to be of little value when spillover queues constrain bottleneck flows from reaching those capacities. Adjusting onboard ACC controllers to produce smaller jam spacings was tested through simulation. The tests show how looming problems might be averted by this intervention, and futures thus improved.

In urban traffic management, the primary challenge of dynamically and efficiently monitoring traffic conditions is compounded by the insufficient utilization of thousands of surveillance cameras along the intelligent transportation system. This paper introduces the multi-level Traffic-responsive Tilt Camera surveillance system (TTC-X), a novel framework designed for dynamic and efficient monitoring and management of traffic in urban networks. By leveraging widely deployed pan–tilt-cameras (PTCs), TTC-X overcomes the limitations of a fixed field of view in traditional surveillance systems by providing mobilized and 360-degree coverage. The innovation of TTC-X lies in the integration of advanced machine learning modules, including a detector–predictor–controller structure, with a novel Predictive Correlated Online Learning (PiCOL) methodology and the Spatial–Temporal Graph Predictor (STGP) for real-time traffic estimation and PTC control. The TTC-X is tested and evaluated under three experimental scenarios (e.g., maximum traffic flow capture, dynamic route planning, traffic state estimation) based on a simulation environment calibrated using real-world traffic data in Brooklyn, New York. The experimental results showed that TTC-X captured over 60% total number of vehicles at the network level, dynamically adjusted its route recommendation in reaction to unexpected full-lane closure events, and reconstructed link-level traffic states with best MAE less than 1.25 vehicle/hour. Demonstrating scalability, cost-efficiency, and adaptability, TTC-X emerges as a powerful solution for urban traffic management in both cyber–physical and real-world environments.

Car following (CF) models are fundamental to describing traffic dynamics. However, the CF behavior of human drivers is highly stochastic and nonlinear. As a result, identifying the “best” CF model has been challenging and controversial despite decades of research. Introduction of automated vehicles has further complicated this matter as their CF controllers remain proprietary, though their behavior appears different than human drivers. This paper develops a stochastic learning approach to integrate multiple CF models, rather than relying on a single model. The framework is based on approximate Bayesian computation that probabilistically concatenates a pool of CF models based on their relative likelihood of describing observed behavior. The approach, while data-driven, retains physical tractability and interpretability. Evaluation results using two datasets show that the proposed approach can better reproduce vehicle trajectories for both human-driven and automated vehicles than any single CF model considered.

Urban air mobility is an innovative mode of transportation in which electric vertical takeoff and landing (eVTOL) vehicles operate between nodes called vertiports. We outline a self-organized vertiport arrival system based on deep reinforcement learning. The airspace around the vertiport is assumed to be circular, and the vehicles can freely operate inside. Each aircraft is considered an individual agent and follows a shared policy, resulting in decentralized actions that are based on local information. We investigate the development of the reinforcement learning policy during training and illustrate how the algorithm moves from suboptimal local holding patterns to a safe and efficient final policy. The latter is validated in simulation-based scenarios, including robustness analyses against sensor noise and a changing distribution of inbound traffic. Lastly, we deploy the final policy on small-scale unmanned aerial vehicles to showcase its real-world usability.

In fire evacuation, social groups of pedestrians often maintain proximity, proceeding at a similar pace towards a common destination. However, the effect of social groups on pedestrian evacuation behavior is underexplored due to the lack of quantification of the social relationships and the subsequent inadequate assessment of their influence on pedestrian dynamics during evacuation. To address these issues, an immersive virtual reality (VR)-based multi-participant evacuation experiment was conducted in a virtual metro station. Social groups of different relationship strengths measured by trust were asked to evacuate from a simulated metro station fire emergency scene. Results showed that grouped pedestrians with stronger social relationships had lower stress response to emergency situations, and tended to stay closer to each other during evacuation. In addition, stronger social relationships also led to more coordinated evacuation decisions between grouped pedestrians. In terms of evacuation performance, stronger social relationship sightly delayed pedestrians’ initial response but reduced their overall evacuation time. By quantitatively measuring the strength of social relationships and comprehensively revealing its influence on pedestrians who evacuate in social groups, this study is expected to enhance the understanding of social group dynamics in pedestrian evacuation, and offer significant insights for emergency management in indoor environments, such as transportation facilities, where high footfall and complex crowd patterns demand efficient evacuations to avert massive injuries.

Research on Connected and Automated Vehicles (CAV) has primarily focused on highway and urban environments, neglecting the significance and dangers of two-lane two-way rural roads. However, CAV driving strategies have the potential to improve significantly this network safety, particularly in critical maneuvers such as overtaking. This paper proposes an overall safety autonomous driving architecture particularly adapted to overtaking maneuver in a two-lane two-way rural road context. The proposed architecture considers vehicle connectivity to share their ego speeds and positions, enabling a rule-based decision-making process coupled with a Fuzzy Inference Systems (FIS) to manage the maneuver’s tasks and to ensure the feasibility of the maneuver. A safety-oriented abort task facilitates a return to the starting lane in case of potential collisions improving maneuver reactivity. Additionally, an original driving personalization is proposed through one driving style parameter modifying the trajectory shape and the maneuver initiation. Two low level controllers handle the vehicle control signals for braking, throttle, and steering wheel angle completing the architecture and allowing full autonomous driving. The algorithm is evaluated using a high fidelity simulation environment in different driving situations. The obtained results demonstrate its reliability and consistency in producing safe overtaking maneuvers regardless the generated situation. A Monte Carlo test highlights the correlation between driving style and comfort in most cases. However, the algorithm limited to two vehicles in the surrounding environment needs improvement to cope with more diverse driving situations.