Search Results (751)

With the deep integration of the modern automotive industry and artificial intelligence technologies, connected and automated vehicles (CAVs) have emerged as a key breakthrough for improving traffic safety and operational efficiency. This study proposes a distributed multi-vehicle cooperative trajectory planning and control framework for ramp merging and diverging scenarios, integrating Deep Neural Networks (DNNs) with Model Predictive Control (MPC). The methodology consists of three key components: First, a distributed cooperative architecture based on dynamic topology is constructed to effectively reduce communication loads; second, a feature point-based Cubic Bézier Curve trajectory generation method is proposed, enabling flexible path planning with reduced reliance on high-precision maps; finally, a DNN-accelerated MPC solving strategy (NN-MPC) is designed. This strategy employs an offline-trained deep neural network to approximate the online optimization process, supplemented by a terminal Safety Check mechanism and a dynamic surrounding vehicle selection algorithm. Experimental results demonstrate that the proposed method successfully reproduces the planning capability of offline high-precision MPC in ramp merging and diverging scenarios while reducing computation time to the millisecond level. It effectively overcomes the myopic decision-making problem of traditional real-time algorithms, achieving smoother conflict resolution and higher traffic efficiency. Notably, quantitative validation confirms that this cooperative framework achieves an approximate 30% reduction in average travel delay compared to the non-cooperative baseline. This study confirms the engineering advantages of the hybrid architecture under dynamic high-density traffic flows, significantly enhancing the system’s real-time response capability while balancing the safety and riding comfort of cooperative driving. Full article

Coordinated control of ramp metering, variable speed limits, and intersection signals is critical for mitigating congestion and enhancing efficiency at urban expressway–arterial interfaces. Existing strategies often operate in isolation, leading to fragmented responses and limited adaptability under heterogeneous traffic demands. This study develops a multi-agent reinforcement learning framework based on MADDPG to achieve cooperative decision-making across heterogeneous controllers. An asynchronous control cycle mechanism is designed to accommodate different temporal requirements of ramp meters, speed limits, and signal controllers, ensuring practical feasibility in real-time operations. A conflict-aware reward design further embeds density regulation, speed harmonization, and spillback prevention to stabilize flow dynamics. Simulation experiments on a calibrated urban network demonstrate that the proposed framework delays congestion onset, reduces shockwave propagation, and improves throughput compared with classical benchmarks. In particular, at the mainline merge, average travel time is reduced to 13.56 s (62.4% of VSL-only); at the ramp, occupancy is lowered to 6.4% (40.6% of ALINEA); and at the signalized approach, average delay decreases to 85.71 s (62.7% of actuated control). These results highlight the scalability and deployment potential of the proposed cooperative control approach for system-level traffic management in mixed traffic environments. Full article

Since the emergence of big data analytics, forecasting future population distributions in specific regions has become a popular prominent research topic. Accurate predictions offer benefits for urban planners, traffic management authorities, and commercial stakeholders. However, most studies have concentrated on population dynamics within isolated locations, often overlooking broader spatial fluctuations across larger geographic areas. This narrow scope limits the practical utility of such predictions. Therefore, generative adversarial networks (GANs) have been employed to estimate population counts across multiple locations within expansive regions. Despite their potential, many GAN-based models encounter significant challenges when tasked with predicting numerous locations simultaneously, resulting in prolonged training times or failure to achieve convergence. To address these limitations, we developed a novel random number generation method to improve the training efficiency and convergence stability of GANs. We also set a new identification criterion to ensure that the large-scale population distributions generated by GAN closely reflect real-world conditions. The developed model in this study was validated using actual telecommunications-based pedestrian flow data from Taiwan, demonstrating its effectiveness and practical feasibility. Full article

Urban traffic noise poses escalating environmental challenges in rapidly urbanizing regions with high-density buildings, yet systematic investigations into its spatiotemporal characteristics remain relatively scarce. This study addresses this research gap via the synchronized on-site monitoring of traffic noise and traffic flow on a representative arterial road in Guangzhou, China. The analysis reveals that nighttime equivalent continuous A-weighted sound levels (L_Aeq) are 3.0–4.0 dB(A) higher than those during the congested daytime peak, a phenomenon primarily driven by higher vehicle speeds under nighttime free-flow traffic conditions. The spatial analysis uncovers complex three-dimensional noise propagation dynamics specific to urban street canyons. Vertical profiling demonstrates a counterintuitive pattern where noise levels do not attenuate with building height, and upper floors experience marginally higher noise exposure than the ground floor, which is attributed to the canyon effect, where multiple sound wave reflections offset the natural distance attenuation. A validated three-dimensional computational model was further employed to evaluate the efficacy of noise mitigation strategies, showing that an integrated intervention combining porous asphalt pavement and acoustic barriers achieves a maximum noise attenuation of 19.9 dB(A) at ground-level receptors. This significant reduction stems from a synergistic effect: porous asphalt reduces noise at the source on a global scale, while acoustic barriers provide localized shielding for the lower floors of adjacent buildings. This research concludes that effective traffic noise control in high-density urban areas requires three-dimensional, multi-faceted strategies addressing noise source characteristics, transmission pathways, and receptor vulnerabilities. Full article

Accurate multi-modal traffic demand forecasting is key to optimizing intelligent transportation systems (ITSs). To overcome the shortcomings of existing methods in capturing dynamic high-order correlations between heterogeneous spatial units and decoupling intra- and inter-mode dependencies at multiple time scales, this paper proposes a Dynamic Multi-Relation Learning with Multi-Scale Hypergraph Transformer method (MST-Hype Trans). The model integrates three novel modules. Firstly, the Multi-Scale Temporal Hypergraph Convolutional Network (MSTHCN) achieves collaborative decoupling and captures periodic and cross-modal temporal interactions of transportation demand at multiple granularities, such as time, day, and week, by constructing a multi-scale temporal hypergraph. Secondly, the Dynamic Multi-Relationship Spatial Hypergraph Network (DMRSHN) innovatively integrates geographic proximity, passenger flow similarity, and transportation connectivity to construct structural hyperedges and combines KNN and K-means algorithms to generate dynamic hyperedges, thereby accurately modeling the high-order spatial correlations of dynamic evolution between heterogeneous nodes. Finally, the Conditional Meta Attention Gated Fusion Network (CMAGFN), as a lightweight meta network, introduces a gate control mechanism based on multi-head cross-attention. It can dynamically generate node features based on real-time traffic context and adaptively calibrate the fusion weights of multi-source information, achieving optimal prediction decisions for scene perception. Experiments on three real-world datasets (NYC-Taxi, -Bike, and -Subway) demonstrate that MST-Hyper Trans achieves an average reduction of 7.6% in RMSE and 9.2% in MAE across all modes compared to the strongest baseline, while maintaining interpretability of spatiotemporal interactions. This study not only provides good model interpretability but also offers a reliable solution for multi-modal traffic collaborative management. Full article

Autonomous vehicles (AVs) are expected to significantly influence road safety, traffic efficiency, and urban mobility. However, their real-world impacts depend not only on vehicle-level automation but also on interactions within the broader traffic ecosystem, including human-driven vehicles, vulnerable road users, infrastructure, and governance frameworks. This review provides a system-level synthesis of recent research on the integration of autonomous and connected autonomous vehicles in mixed traffic environments. Following PRISMA 2020 guidelines, 51 peer-reviewed studies published between 2016 and 2025 were systematically reviewed and thematically analyzed. The review addresses technological foundations, safety impacts, traffic flow and network performance, mixed traffic dynamics, infrastructure and urban systems, and policy and governance challenges. The findings indicate that AV impacts are highly non-linear and sensitive to market penetration rates, control strategies, and human behavioral adaptation. While high levels of automation and connectivity can improve safety, capacity, and traffic stability, early-stage deployment may temporarily increase delays and traffic conflicts. Policy measures—such as pricing, shared mobility integration, and regulatory oversight—are therefore critical to ensuring that AV deployment delivers sustainable and equitable mobility outcomes. Full article

To address the rapidly growing demand for charging stations (CSs) and the associated challenges posed by the expansion of electric vehicles (EVs), this study proposes a collaborative planning method integrates user demand considerations with operational constraints at the grid level. Based on graph theoretical principles, static topology models of the road network and distribution grid were constructed. A dynamic origin–destination (OD) prediction framework was then formulated by jointly considering traffic flow variations, battery energy consumption, user charging behavior, and ambient temperature, in which an enhanced gravity model is coupled with the Floyd algorithm. Charging load characteristics were quantified through Monte Carlo simulation, and K-means++ clustering was further applied to identify spatial charging demand hotspots. On this basis, a multi-objective optimization model was established to simultaneously balance the annualized cost of charging stations, user costs, and voltage deviation in the distribution network. To solve the resulting high dimensional problem, a collaborative optimization mechanism was designed by integrating a weighted Voronoi diagram with a multi-objective particle swarm optimization (MOPSO) algorithm, enabling dynamic service area partitioning and global capacity optimization. Case analysis demonstrates that the proposed method reduces user time costs by 15.8%, optimizes queue delay by 42.2%, and improves voltage stability, maintaining fluctuations within 5%. It also balances the interests of charging station operators, users, and distribution networks, with only a slight increase in construction costs. These results offer valuable theoretical and practical insights for charging infrastructure planning. Full article

Traffic flow prediction is a pivotal task in intelligent transportation systems. The primary challenge lies in accurately modeling the dynamically evolving and directional spatio-temporal dependencies inherent in road networks. Existing graph neural network-based methods suffer from three main limitations: (1) symmetric adjacency matrices fail to capture the causal propagation of traffic flow from upstream to downstream; (2) the serial combination of graph and temporal convolutions lacks an explicit modeling of joint spatio-temporal state transition probabilities; (3) the inherent low-pass filtering property of temporal convolutional networks tends to smooth high-frequency abrupt signals, thereby weakening responsiveness to sudden events. To address these issues, this paper proposes a causal-enhanced spatio-temporal Markov graph convolutional network (CSHGCN). At the spatial modeling level, we construct an asymmetric causal adjacency matrix by decoupling source and target node embeddings to learn directional traffic flow influences. At the spatio-temporal joint modeling level, we design a spatio-temporal Markov transition module (STMTM) based on spatio-temporal Markov chain theory, which explicitly learns conditional transition patterns through temporal dependency encoders, spatial dependency encoders, and a joint transition network. At the temporal modeling level, we introduce differential feature enhancement and high-frequency residual compensation mechanisms to preserve key abrupt change information through frequency-domain complementarity. Experiments on four datasets—PEMS03, PEMS04, PEMS07, and PEMS08—demonstrate that CSHGCN outperforms existing baselines in terms of MAE, RMSE, and MAPE, with ablation studies validating the effectiveness of each module. Full article

Background: Ports play a strategic role in the efficiency and sustainability of European transport corridors; however, empirical evidence on their performance remains limited, particularly for Eastern European countries. This study aims to assess the technical efficiency and productivity dynamics of Romanian ports along the Danube corridor in a context of structural change and evolving cargo flows. Methods: Technical efficiency is estimated using an output-oriented Data Envelopment Analysis (DEA) model under variable returns to scale, followed by bias correction and determinant analysis employing the Simar–Wilson bootstrap procedure. Productivity change is examined separately using the Malmquist Productivity Index based on original DEA distance functions. Results: The analysis reveals substantial heterogeneity in efficiency levels across ports, with bias-corrected estimates indicating that efficiency differentials are structural rather than statistical. Cargo specialization emerges as the main determinant of efficiency, while location effects are found to be asymmetric. Efficiency levels are largely stable over time, and productivity change is modest, being driven exclusively by efficiency change, with no evidence of technological progress. Conclusions: These findings suggest that the performance of ports along the Romanian Danube corridor is shaped primarily by structural and organizational factors rather than temporal dynamics, underlining the importance of targeted policy interventions focusing on traffic consolidation, port specialization, and coordinated spatial and hinterland planning to enhance inland port performance within European transport corridors. Full article

Connected and Autonomous Vehicles (CAVs) are exposed to increasingly sophisticated cyber threats hidden within high-dimensional, heterogeneous network traffic. A critical bottleneck in existing Intrusion Detection Systems (IDS) is the feature heterogeneity gap: discrete protocol signatures (e.g., flags, services) and continuous traffic statistics (e.g., flow duration, packet rates) reside in disjoint latent spaces. Traditional deep learning approaches typically rely on naive feature concatenation, which fails to capture the intricate, non-linear semantic dependencies between these modalities, leading to suboptimal performance on long-tail, minority attack classes. This paper proposes HCA-IDS, a novel framework centered on Semantics-Aware Cross-Modal Alignment. Unlike heavy-weight models, HCA-IDS adopts a streamlined Multi-Layer Perceptron (MLP) backbone optimized for edge deployment. We introduce a dedicated Multi-Head Cross-Attention mechanism that explicitly utilizes static “Pattern” features to dynamically query and re-weight relevant dynamic “State” behaviors. This architecture forces the model to learn a unified semantic manifold where protocol anomalies are automatically aligned with their corresponding statistical footprints. Empirical assessments on the NSL-KDD and CICIDS2018 datasets, validated through rigorous 5-Fold Cross-Validation, substantiate the robustness of this approach. The model achieves a Macro-F1 score of over 94% on 7 consolidated attack categories, exhibiting exceptional sensitivity to minority attacks (e.g., Web Attacks and Infiltration). Crucially, HCA-IDS is ultra-lightweight, with a model size of approximately 1.00 MB and an inference latency of 0.0037 ms per sample. These results confirm that explicit semantic alignment combined with a lightweight architecture is key to robust, real-time intrusion detection in resource-constrained CAVs. Full article

Understanding the propagation interactions among intersections in city road networks and uncovering their traceability patterns is vital for proactive traffic management and control. However, measuring the propagation strength between intersections is difficult due to the dynamic nature of traffic flow and the interference at the network level caused by interactions among many nearby intersections. Additionally, mining traceability patterns requires a comprehensive representation of complex propagation influences among intersections and the ability to detect subtle changes in network structure. This study introduces a detailed framework for extracting traceability patterns in urban road networks. It identifies high-impact intersections using the mean excess function, constructs an interaction graph with these critical nodes, applies graph structural entropy to describe the global topological features of the interaction graph, and uses k-means clustering to classify different traceability patterns. The proposed method was validated using real-world traffic data, showing superior performance in estimating propagation strength compared to benchmark models. Kolmogorov–Smirnov tests confirmed the statistical reliability of high-impact and high-impact intersection identification results. Furthermore, the study identified four core interaction structures—chain, collider, fork, and circle—and four representative traceability patterns formed by these structures. Full article

Wireless communication and the Internet of Things (IoT) are integrated for the formulation of an emerging Intelligent Transportation System (ITS) for the interaction of vehicles and to enhance road safety. The emerging network manages the traffic flow, real-time data analytics, and resource control for the development of urban transportation systems and smart cities. Extensive research has been conducted on the development of efficient routing response time for the IoT-ITS environment; however, the rapid changes in the network topologies still lead to unmanageable congestion and communication holes. Moreover, it is also often threatened due to high urban mobility and incurs additional transmission with excessive overhead. Such concepts are not able to maintain secure interactions among vehicles and expose confidential data to malicious devices while interacting on unpredictable channels. This research proposes a trust-aware edge-assisted model to secure the vehicular network and offers a more reliable system with optimal routing performance. The global trust model is maintained based on network conditions using localized computing and attaining data privacy and coherence. Furthermore, a blockchain ledger is included along with trust to ensure tamper-proof and transparent computing across the boundaries of the IoT-ITS environment. The proposed model is compared with Graph-Based Trust-Enabled Routing (GBTR) and Bacteria for Aging Optimization Algorithm (BFOA), and the results revealed significant performance for network throughput by 50% and 62.5%, end-to-end delay by 33.3% and 37.5%, routing overhead by 34% and 38.7%, and false positive rate by 67.9% and 68.5% over the dynamic network infrastructure. Full article

The accurate prediction of extreme dynamic amplification factor (DAF) values is significantly important to ensure a long-term safety assessment of bridges under stochastic vehicular loading. However, predicting extreme DAFs is challenging due to traffic randomness, road roughness variability, and nonlinear vehicle–bridge interaction (VBI) effects. This study presents an integrated framework for extreme DAF prediction for simply supported bridges by combining stochastic traffic–bridge interaction simulations with Bayesian updating and a Peaks-Over-Threshold–Generalized Pareto Distribution (POT–GPD) model. A coupled VBI model is developed, incorporating cellular automaton-based traffic flow, multi-axle nonlinear vehicle dynamics, finite-element bridge modeling, and stochastic road roughness profiles. A new DAF definition based on dynamic displacement difference is proposed to better represent dynamic effects. DAF samples obtained from VBI simulations under different road roughness levels are analyzed using the POT method, with GPD parameters estimated through maximum likelihood and Bayesian inference. Extreme DAFs corresponding to different return periods are then determined. The results indicate that extreme DAF values increase with worsening road roughness and longer return periods and that the Bayesian POT–GPD approach effectively captures tail behavior while providing reliable uncertainty quantification for extreme DAF prediction. Full article

For battery-powered Smart Road components deployed in locations without access to the electrical grid, limited energy availability represents a major challenge to long-term autonomous operation. While photovoltaic panels are the most commonly used energy-harvesting solution, their effectiveness depends strongly on environmental and climatic conditions and may be insufficient in shaded areas or in highly dynamic road environments. Road infrastructure, however, inherently provides additional and largely underutilized energy sources, among which thermoelectric energy generated by temperature gradients within the road structure is particularly promising. This review addresses the problem of identifying viable alternatives or complements to photovoltaic energy harvesting by focusing on thermoelectric transducers as a potential power source for Smart Road applications. The objective of the article is to provide a comprehensive overview of the physical principles underlying thermoelectric transducers, the different architectures of thermoelectric modules, and their practical applicability in road transportation systems. Particular attention is devoted to implementation approaches that do not interfere with traffic flow or compromise road safety, as well as to existing applications of thermoelectric energy harvesting in transportation infrastructure. In addition, the review discusses the potential and limitations of concentrated thermoelectric transducers for increasing power density. By synthesizing current research results, this work evaluates the feasibility, advantages, and challenges of thermoelectric energy harvesting to extend the operational lifetime of autonomous Smart Road components and identifies directions for future research. Full article

Airport aprons are complex, multi-node operational hubs frequently affected by queue congestion resulting from control handovers, taxi conflicts, and external factors. To enable proactive congestion management, we propose a new and accurate method for apron queue length prediction. The core of our approach is a multi-queue network model in which queues are systematically divided by control position and taxi direction. This framework, which applies the Fluid Flow Approximation and is calibrated with historical data, effectively captures the dynamics of multi-node traffic flow. In a validation case study at Beijing Daxing International Airport (ZBAD), the model achieved high accuracy, with the mean absolute error of queue length prediction averaging 0.5 aircraft. The results demonstrate the model’s ability to characterize queue dynamics on a minute-level scale across a full day. Full article