In the context of global decarbonisation initiatives, the logistics sector faces dual challenges: its substantial energy consumption and carbon footprint conflict with societal goals for a low-carbon economy, while escalating pressures from urban traffic congestion also inflate distribution costs. The environmental externalities and economic losses induced by the combination of inefficient routing and congestion have jointly motivated the emerging research field of low-carbon vehicle routing optimisation. To reconcile these issues, this study develops a bi-level programming framework for low-carbon-oriented vehicle routing optimisation that explicitly accounts for road congestion. The upper-level model aims to minimise the total cost (including vehicle fixed cost, transportation cost, carbon emission cost and time-window penalty) by internalising a carbon tax constraint. The lower-level model employs a user equilibrium (UE) model, focusing on minimising travel time from the perspective of road users. A hybrid solution methodology (GA-Tent & Frank-Wolfe) is proposed, integrating an enhanced genetic algorithm with Tent chaos mapping for global optimisation and a modified Frank-Wolfe algorithm for traffic assignment. Finally, a case study using the Sioux Falls network demonstrates that traffic congestion increases carbon emissions, but a moderate carbon tax increase can effectively reduce vehicle carbon emissions. These insights suggest policymakers should implement progressive carbon pricing mechanisms coupled with dynamic congestion pricing, while logistics operators should prioritise route optimisation systems with real-time traffic adaptation capabilities.
Frequent traffic crashes on urban roads seriously threaten public safety and traffic operations. Accurate risk prediction is vital for improving management efficiency and developing intervention measures. This paper proposes a traffic crash risk prediction model integrating multi-source heterogeneous data. It constructs a dynamic spatio-temporal graph network (DTGN) based on edge-aware graph convolutional networks (EGCN) and introduces a dynamic threshold risk stratification mechanism and local crash density (LCD) indicators to alleviate the issue of “zero inflation” in low-frequency areas. The model combines graph convolutional and spatio-temporal convolutional networks to extract multi-dimensional spatio-temporal features and enhances the ability to identify high-risk areas through a weighted loss function. The city is partitioned into hexagonal grid units, and a dynamic adjacency matrix is constructed to capture spatial associations and evolutionary features. Experimental results indicate that DTGN performs effectively in processing multi-source data and extracting key risk features, achieving an accuracy rate of 87% in high-risk area predictions, thereby providing more practical early warning support and decision-making basis for urban traffic safety management.
Frequent freeway accidents cause significant casualties and economic losses, necessitating robust risk assessment methods. This study proposes a quantitative method for assessing freeway driving risk using continuous observational data from toll transactions. Based on toll data from the Yongguan Freeway in Guangdong Province, China (June–August 2022), 18 risk characteristic indicators for cargo vehicles and 13 for passenger vehicles were developed. Factor analysis reduced these indicators into five common factors, followed by K-means++ clustering to categorise vehicles into risk groups. The entropy weight method calculated risk scores, determining risk levels. The model identified 17.75% of cargo vehicles as high-risk and 14.03% as moderately high-risk, and 7.47% of passenger vehicles as high-risk and 1.08% as moderately high-risk. Validation using rescue events per 10,000 vehicles (RM) from a Guangdong Province accident database, due to limited crash data availability, confirmed consistency with model-assigned risk levels, supporting targeted safety interventions.
With the rapid development of intelligent operation and management of urban rail transit, accurate passenger flow prediction is crucial for management and operation. However, the complex, nonlinear and non-smooth characteristics make detecting passenger flow evolution features challenging. In this regard, a novel decomposition integration model, IC-TLCA, is proposed. The model first decomposes the raw passenger flow data into multiple sublayers with different frequencies using an improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) algorithm to better capture the intrinsic structure of the data. Then, the temporal convolutional network (TCN), long-short-term memory network (LSTM) and channel attention module (CAM) are combined to predict each sublayer separately. Finally, by combining the prediction results of each sublayer, the final passenger flow prediction is obtained. After comparing with all baseline models and conducting ablation experiments, the IC-TLCA model has been validated to be innovative in theory and superior in practical applications, thereby providing an effective solution for passenger flow prediction.
Traffic flow prediction is an important component of intelligent transportation systems. Most existing studies adopt spatio-temporal methods for real-time short-term prediction. However, when dealing with complex and dynamically changing historical data in long-term prediction tasks, several challenges arise, such as high complexity, high computational cost and unstable spatial dependencies. In response to this deficiency, this paper proposes a trend-season dual-branch fusion network with harmonic weighting for long-sequence traffic flow prediction. This model decomposes the original sequence into trend and seasonal components. Specifically, the trend branch applies multi-scale sampling, and the trend components at different scales are fused in a top-down manner to enhance information representation. Finally, a linear layer is used to predict the trend results. The seasonal branch encodes the seasonal components through wavelet transform, and a harmonic weighting mechanism is designed to adaptively fuse the prediction results of both branches. Experiments conducted on multiple public transportation datasets demonstrate that the proposed model significantly outperforms existing mainstream methods in long-term predictions at time steps of 96, 192, 288 and 336, thereby verifying the effectiveness and robustness of time-series modelling approach in long-sequence prediction scenarios.
The global proliferation of electric bicycles (EBs) marks a significant advancement in sustainable urban transportation. However, two critical barriers impede EB’s full societal integration: insufficient analysis of user needs and fire safety risks exacerbated by inadequate risk awareness. To address the above challenges, this study proposes a three-phase approach integrating user needs identification, quantitative prioritisation and risk-aware guidance to promote safer EB design practices. We establish an integrated analytical framework combining quality function deployment (QFD) with the fuzzy best-worst method (F-BWM) to achieve the first two phases-identification and quantitative prioritisation of user needs. For the third phase, we design and implement an innovative video-based guidance framework as an effective risk communication strategy, specifically targeting the enhancement of fire safety considerations during EB selection processes. Findings indicate: (1) six primary EB user needs are identified: battery and charging, handling performance, safety and security, comfort and convenience, technology and connectivity, and appearance design. (2) “Battery and charging” and “safety and security” emerge as the highest-priority EB user needs. (3) The video intervention yielded a measurable 27.73% increase in the perceived importance of fire-related features. This study provides theoretical foundations for user-centred EB design approaches.
The transport sector is facing a system-wide shortage of labour and a high turnover rate among truck drivers. The objective of this study is to determine the effects of financial and non-financial rewards on fatigue and, consequently, on the satisfaction of truck drivers. For this purpose, a survey was conducted on a sample of 218 truck drivers within the EU. The hypotheses were tested using structural modelling. The results of the structural equation model showed that higher rewards are associated with increased fatigue among truck drivers; however, there is a positive correlation between driver fatigue and job satisfaction. The truck drivers are not considering employment in a different industry and are satisfied with their choice of profession. The study builds on previous research and contributes to the understanding of factors that influence the work of truck drivers. The results contribute to improvements in the area of financial and non-financial rewards in transport companies. They are also valuable for policy-makers in establishing new legislative frameworks in the transport sector, both in terms of safety and employment of truck drivers.
Autonomous driving requires precise vehicle localisation, especially in moving, unstructured environments. Existing methods focus on spatial matching or temporal sequence modelling for sensor noise, occlusions and partial data. This causes errors. Spatial-only methods struggle with environmental uncertainty, while temporal-only models lack geometric coherence. This study proposes the iterative closest point and long short-term memory-based joint localisation algorithm (ICP-LSTM-JLA) to solve these limitations. This hybrid approach combines geometric point cloud registration and learning-based motion sequence modelling. LSTM-driven predictions that employ inertial and motion data modify the system’s initial posture estimation. Aligning real-time sensor data with pre-mapped environments does this. ICP-LSTM-JLA can enhance localisation accuracy and resilience in diverse driving conditions by integrating spatial alignment with temporal dynamics. The experiments showed that compared to state-of-the-art models, the absolute trajectory error (ATE) has decreased by 17.8%, the relative positioning error (RPE) by 14.3%, the map registration error by 19.1% and the orientation error by 12.6%. This study found that the hybrid architecture improves short-term stability and long-term trajectory accuracy. Thus, it is a reliable real-world autonomous navigation system.
Self-driving vehicle platoons offer promising improvements in traffic efficiency and safety. However, their deployment is hindered by limited communication bandwidth and computational constraints in distributed control systems. This paper presents a bandwidth‑aware event‑triggered adaptive distributed model predictive control (DMPC) method. Firstly, to mitigate resource waste from frequent communications under bandwidth-constrained conditions in conventional DMPC, a bandwidth-aware event-triggered mechanism is designed based on a sigmoid threshold function of vehicle state errors. This mechanism adjusts the triggering threshold according to bandwidth availability, thereby suppressing unnecessary transmissions while maintaining a balance between communication efficiency and control performance. Secondly, a dual-input fuzzy adaptive module is introduced to reduce the computational burden in vehicle platoon control. This module takes maximum position and velocity errors as inputs to tune the prediction horizon dynamically. Finally, numerical simulation results show that under high bandwidth usage, the proposed method reduces communication resource consumption to 57.3%, while decreasing the communication frequency by up to 15.7% compared with the existing method. Meanwhile, it decreases the controller’s computational overhead by approximately 19.5% relative to fixed-horizon DMPC. The proposed approach enhances both communication and computational efficiency, making it applicable for resource‑constrained platoon control scenarios.
Road safety performance indicators (RSPI) provide essential insight into traffic safety beyond crash statistics, enabling a better understanding of risk factors and policy impacts. In this sense, it is important to determine how RSPIs are related to the outcomes of traffic crashes. This point was the aim of this research, which used data from the ten-year experience of monitoring RSPI in Serbia. Monitoring of road safety performance indicators began in 2013 at the level of 27 police administration units. The relationship between RSPI and the outcomes of traffic crashes was investigated by applying fixed-effects regressions and Mundlak correlated random-effects models for panel data. Results showed that the most significant relationships were observed in the RSPI of protective systems in vehicles (seatbelts, child restraint systems and helmets) and speeding in urban areas. On the other side, speed-related indicators in rural areas and indicators related to distraction had weaker associations with the outcomes of traffic crashes. The set of constructs obtained from observed RSPI explained around 37% of the variability in the total weighted number of traffic crash casualties, highlighting the need to include indicators from all other groups. The findings highlight the methodological and policy value of sustained RSPI monitoring and suggest improvements in indicator design, especially for vulnerable road users, distraction and emerging mobility modes. Finally, the study’s results confirm the importance of monitoring and incorporating indicators from all groups to describe the road safety situation in a local entity accurately.
This study proposes a novel intersection-centric information framework designed to provide a new perspective and practical approach for enabling autonomous vehicles (AVs) to navigate intersections safely and efficiently. While high-definition (HD) maps provide rich spatial information for autonomous driving, their excessive data volume often leads to increased computational burden and delays, particularly in intersection environments where timely positioning, perception, and decision-making are critical. To address this issue, we introduce the Road-Lane-Device-Scenario (RLDS) model, which separates and extracts key static and dynamic intersection elements, focusing on essential semantic features such as lane topology, traffic signal logic, and right-of-way rules. This targeted framework introduces an innovative approach to reduce data redundancy, thereby providing significant potential for enhancing the efficiency and intelligence of information processing and decision-making in autonomous driving systems. By effectively addressing the critical bottlenecks associated with intersection scenarios, the proposed framework demonstrates strong potential for practical application, enabling safer, more reliable, and more efficient autonomous vehicle operations in complex urban environments.
The existence of invalid parking areas significantly contributes to the disorderly parking of shared bicycles. A thorough investigation into the effectiveness of various management mechanisms in addressing this issue is crucial for promoting the sustainable development of the shared bicycle market. This study establishes an evolutionary game model among three stakeholders: the government, enterprises and users. The model integrates the rate of invalid parking areas and governmental supervision methodologies, which have been largely overlooked in existing literature. The strategy stability of each stakeholder is analysed using the Lyapunov discriminant method. Furthermore, the impact of various parameters on the evolutionary process is examined through numerical simulations. The findings indicate the following. (1) Differing initial levels of willingness among stakeholders significantly affect both the speed and trajectory of system evolution. (2) The primary objective of effectively managing shared bicycle parking is to enhance the efficiency of enterprise-constructed parking areas. (3) Increasing government fines while improving enterprise reward and punishment mechanisms proves to be an effective strategy for fostering a healthier shared bicycle parking governance system. These results provide actionable recommendations for regulating uncontrolled shared bicycle parking and optimising urban transportation resource utilisation within a more realistic modelling framework.
This paper analyses the digitalisation of the transport sector in Bosnia and Herzegovina through the theoretical frameworks of institutional theory, the resource-based view (RBV) and the concept of digital maturity. The study, conducted on a sample of 85 transport companies, aimed to examine the role of institutional pressures and internal capacities in the implementation of digital technologies, with particular emphasis on smart tachographs as a key regulatory and technological driver of digital transformation. Smart tachographs, together with telematics and navigation systems, are considered indicators of the digital maturity level of transport companies. The results show that legislation remains the main driver of digitalisation, supporting institutional theory, while companies with higher levels of digital maturity are more likely to recognise strategic benefits such as efficiency improvements, data-driven decision-making and advanced analytics. The findings also suggest that the intensive use of tachograph and telematics data contributes to the development of organisational competencies that represent valuable and hard-to-imitate resources, consistent with RBV. The paper contributes by linking institutional pressures and digital maturity and by introducing the concept of the “digital stack”, while the practical implications highlight the need to strengthen internal digital capacities beyond regulatory compliance.
The existing traffic flow allocation methods lack sufficient flexibility and adaptability by analysing the impact of parameter changes on traffic flow distribution through examples, resulting in a decrease in traffic flow allocation performance on congested road sections. A traffic flow allocation method for the main skeleton road network of congested road sections is developed on the basis of the genetic tabu algorithm. First, a traffic flow allocation model is established, and data are collected using microwave vehicle detectors and high-definition checkpoint video detectors. Subsequently, the congested sections of the main skeleton road network are analysed, and the discrete-time and continuous-time forms of the section state equation are introduced. Finally, drawing on the results of the state analysis, a flow-control equilibrium joint optimisation objective function is formulated. Finally, it is proposed to use the genetic tabu algorithm to solve the model, in order to obtain the optimal traffic flow allocation scheme and improve the network traffic rate of the main skeleton. Experimental results have shown that this method can effectively determine the impedance time function of congested road sections and complete the traffic flow allocation of the main skeleton road network of congested road sections. It effectively enhances the distribution of traffic volumes across individual sections and contributes to achieving a more balanced flow throughout the entire main skeleton road network.
Monitoring vehicle movements at roundabouts and determining their operational throughput traditionally relies on tracking individual turning movements, a process that is technically demanding, labour-intensive and often impractical for complex multi-leg roundabouts. This study proposes a simplified approach to data collection and the determination of roundabout flow parameters. Two data collection techniques were examined: simplified manual counting of vehicles at entry legs and automated licence plate recognition. For roundabout flow parameters, determining the key methodological contribution is applying the roundabout investigation model (MIKR). Model MIKR enables capacity and turning-movement estimation using only entry and exit counts, thereby substantially reducing the scope of required field observations compared with conventional trajectory-based methods. The results show that licence plate recognition can determine turning flows with an accuracy of approximately 90%. The MIKR model reliably estimates roundabout capacity without requiring vehicle trajectory tracking. These findings confirm the practical value of the MIKR approach and highlight its potential for more efficient and cost-effective traffic-flow analysis at roundabouts.
Global warming demands urgent action to reduce greenhouse gas emissions, with road transport being a major contributor. Electrification of passenger cars is widely promoted as a key mitigation strategy; however, its real-world impact remains debated. This study develops a calculation framework to estimate annual fleet-level greenhouse gas emissions based on actual consumption data, vehicle type distribution, age and mileage. Using this method, short- and mid-term drawbacks of electrification are quantified alongside long-term benefits through scenario analysis aligned with the European Union 2035 target. Results indicate that electrification begins to deliver net emission reductions after 2032, achieving a 5.3% decrease by 2035 compared to an internal combustion engine fleet. These findings highlight the temporal dynamics of electrification and provide evidence-based insights for policymakers and industry stakeholders.
In the operation of railway transportation enterprises, having prior knowledge of future loading volumes and trends at freight stations is crucial for optimal deployment of empty cars and the development of daily operational plans. Long-term freight volumes at railway stations often exhibit cyclical patterns influenced by seasonal fluctuations, holidays and other factors. Additionally, changes in freight volume are significantly affected by the proportion of freight from various industries. To address these dynamics, this study proposes a hybrid prediction model for long-term loading volumes at railway freight stations. This model predicts by stage segmentation through peak-valley segmentation (PVS), variational mode decomposition (VMD) and an attention mechanism integrated into a temporal convolutional network (TCN). Using historical freight volumes from the Shuohuang railway freight station as a case study, we employed mean absolute percentage error (MAPE), mean absolute error (MAE) and root mean square error (RMSE) as evaluation metrics to assess the combined predictive performance of the PVS, VMD and TCN methods. The experimental results show that the PVS-VMD-A-TCN model significantly improves the accuracy of long-term freight volume predictions. Compared to traditional methods such as ARIMA, GRU and TCN, it exhibits superior predictive performance, offering a new approach for accurately forecasting long-term loading volumes.
With the improvement of deep learning technology, traditional obstacle avoidance approaches for blind people can no longer meet practical needs. In response to the problems of poor adaptability to multiple scenarios and low obstacle avoidance rates in current obstacle avoidance methods for blind people, this study proposes an intelligent obstacle avoidance method for blind people based on an improved You Only Look Once (YOLO) algorithm and binocular vision. This method first improves the YOLOv8 algorithm by introducing an angle loss function, SPD convolution and a more efficient local convolution structure, and proposes an I-YOLOv8-BBOD model suitable for blind people’s travel. Then, based on this model, a blind travel intelligent obstacle avoidance platform is built. The confusion matrix analysis showed that the research model performed the best and had significant advantages in reducing false positives and false negatives. Its precision, recall and F1 score were all above 0.90, indicating the best overall performance. The ablation experiment showed that after the improvement of each module, the mAP and the average accuracy at the 50% IoU threshold increased by 13.19% and 16.00%, significantly improving the detection accuracy. In the example application, the successful obstacle avoidance rate of the proposed obstacle avoidance platform exceeded 90%, and the false alarm rate was below 1.3%. The traditional platform could reach up to 5.4%, which was better than the previous platform. This indicates that the research method can accurately detect obstacles and road conditions, ensuring the safety of visually impaired people’s travel.
The long-term coexistence of connected and automated vehicles (CAVs) and human-driven vehicles (HDVs) in mixed traffic flows will continue to significantly impact merging behaviours and operational efficiency in freeway on-ramp merging areas. To improve merging efficiency at freeway on-ramps, this paper proposes a cooperative merging model for mixed traffic. First, the merging points for ramp vehicles are determined based on vehicle interaction characteristics in the merging area. Then, for the dynamic decision-making problem of merging sequences, considering the differences in cooperative merging between CAVs and HDVs, the optimal merging sequence for both single-vehicle and multi-vehicle platoon merging is determined by minimising the global deviation between the actual travel time and the expected minimum travel time. Finally, according to the predetermined merging sequence, a bidirectional speed guidance strategy based on virtual vehicle mapping is designed for both mainline and ramp vehicles to achieve cooperative optimisation of the merging sequence and vehicle trajectories, enabling the smooth merging of ramp vehicles into the mainline. Simulations verify that the proposed method performs better than FIFO and effectively improves merging efficiency under different CAV penetration rates. Particularly in low-to-medium penetration scenarios, it achieves a 25% delay optimisation rate and 22% reduction in travel time, with the optimisation effect improving to varying degrees as penetration rates increase. This establishes a foundation for traffic analysis and cooperative control in freeway on-ramp merging areas under mixed traffic environments.
This work investigates intent recognition and trajectory prediction for multiple types of traffic participants at an unsignalized intersection within connected intelligence environments based on bidirectional spatiotemporal attention network (Bi-STANet). An unsignalized intersection is used as the studied object, where the participants include Connected and Automated Vehicles (CAVs), Human Vehicles (HVs), bicyclists, and pedestrians. A novel method is proposed based on Bi-STANet. First, a multimodal spatiotemporal feature extraction model is constructed based on (2+1)-dimensional CNN ((2+1)D CNN), where grid encoding method is used to unify the spatial structure and 2D convolution is used to extract spatial features for capturing the disordered characteristics of participants. Temporal dynamics are modelled via 1D convolution along the time axis, enabling spatiotemporal decoupling. Second, a bidirectional dynamic interaction model is developed by integrating LSTM-based temporal feature extraction with (2+1)D CNN layers, where heterogeneous modality fusion is implemented through a Bidirectional Contextual Block (BiCoBlock). Finally, a model integrating dynamic interaction, intent recognition, and trajectory prediction is developed. The proposed method is validated through the inD dataset innovatively. The results show that the average accuracy of intent recognition can reach to 95.4%. Within a 3-second horizon, Average Displacement Error (ADE) and Final Displacement Error (FDE) can be reduced to 0.51 m and 0.64 m, respectively, compared with the best baseline model. In Ablation studies, intent recognition F1-score can be enhanced by 7.2%, and ADE and FDE of trajectory prediction can be enhanced by 41.4% and 39.0%, respectively.
