IET Intelligent Transport Systems最新文献

The three-dimensional macroscopic fundamental diagram (3D-MFD) provides a novel approach to characterize the complex interactions between cars and buses in multimodal urban networks, offering particular value for designing efficient bimodal perimeter control strategies. In this study, a perimeter control strategy for cars is implemented by regulating the transfer flow rate at subregion boundaries, while bus numbers are dynamically adjusted through optimized dispatch frequencies. A multimodal traffic system state equation integrating both car and bus dynamics is constructed. Building on operational state factors for both modes, a passenger mode choice model based on the Logit model is established. With the dual objectives of maximizing the overall passenger arrival rate and minimizing total network energy consumption, an integrated multimodal traffic control framework (I-MPC) is developed using model predictive control (MPC). The comparative analysis against the no boundary control (NBC) method, the MPC-based boundary control method for private cars (C-MPC), and the bus scheduling optimization method (B-MPC) demonstrates that the proposed I-MPC method achieves outstanding performance across multiple key metrics, including passenger arrival efficiency, network energy consumption, and average bus occupancy rate, thereby enabling the optimized allocation and efficient utilization of traffic resources. Moreover, the method maintains reasonable bus occupancy levels while significantly enhancing passenger comfort and reducing overall system energy consumption.

Reliable and time-bounded perception systems are necessary for autonomous vehicles' (AVs') safe navigation, especially at intersections. In this work, a post-training quantized you only look once (YOLOv8n) model for real-time obstacle and traffic light recognition is implemented on the NVIDIA Jetson Orin Nano. The system, which is integrated with the robot operating system 2 (ROS 2) framework, analyzes stereo input from a ZED 2i camera using soft real-time scheduling theory, taking worst-case execution time (WCET), jitter, and slack into account. Despite the workload surpassing the traditional schedulability constraints under earliest deadline first (EDF) and rate monotonic scheduling (RMS), empirical evaluation across 423 daytime urban frames reveals that 98.11% of inferences fulfil a 150 ms soft deadline. The results show minimal thermal drift, low jitter, consistent slack margins, and bounded deadline violations (<30 ms). Further analysis incorporates fixed-priority scheduling, CPU core affinity, and a deadline penalty model to assess safety implications in AV decision loops. While extreme conditions such as night driving or adverse weather were not included, future work will extend to these scenarios. Overall, the findings validate the feasibility of deploying a probabilistically schedulable, timing-aware perception pipeline for integration into intelligent transport systems (ITS) and edge AI platforms.

The swift evolution from vehicular ad hoc networks (VANETs) to the Internet of Vehicles (IoV) landscape has posed substantial routing optimization challenges regarding high mobility, dynamic topologies and intermittent connectivity. Conventional routing protocols such as AODV, DSR and GPSR are often unable to cater to the requirements of the IoV environment as they can result in latency, control overhead and overall scalability. To help tackle these limitations, this work proposes COANET (crayfish optimization algorithm-based route optimization for IoV networks), which is an innovative bio-inspired framework based on the crayfish optimization algorithm (COA). COANET's core utilized the crayfish behaviours of foraging, competition and summer resort to allow the dynamic balancing of exploration and exploitation during routing decisions. We implement these behaviours as explicit algorithmic operators and provide reproducible specifications to support replication. The framework is supported by energy-aware clustering, hybrid exploration-exploitation and multi-metric optimization to optimize latency, energy efficiency and packet delivery. To validate COANET, simulation performance results show that COANET, as compared to traditional protocols, improves the packet delivery ratio by 15–20% while reducing end-to-end delay by 30% and energy efficiency by 41.5%. Additionally, COANET reduced control overhead by 52.7% in both urban and highway scenarios, thus affirming its robustness and ability to scale for next-generation IoV Systems.

One of the primary challenges in ensuring road safety is effectively alerting drivers to adverse weather conditions, such as fog, which can severely impair visibility and increase the risk of accidents. Timely and accurate fog detection is crucial for providing drivers with the necessary warnings to adapt their driving behaviour and enhance safety. This paper presents a system designed to detect foggy scenarios and classify visibility levels, thereby enabling timely alerts for drivers to minimise the risks associated with reduced visibility. To achieve this, we have developed two new image datasets of road fog scenarios – Foggy-Ceit 2023 and an extension to the Foggy CityScapes – DBF dataset – featuring both real and synthetic fog. Additionally, we compare various algorithms developed using classical vision techniques and deep learning methods (vision transformers [ViT] and EfficientNet). Finally, eXplainable artificial intelligence techniques are utilised to provide visual explanations and evaluate the performance of these models.

The majority of existing research on collision severity focuses on post-collision severity, which is not conducive to collision prevention. This paper proposes a novel method for predicting the severity of potential collisions, aiming to establish a prediction model to predict the potential consequences of collisions before they occur, providing a basis for quantifying driving risk. In developing this model, two key challenges are addressed: how to effectively characterise the severity of potential collisions and how to manage the class imbalance caused by the scarcity of severe collisions. To tackle the first challenge, we introduce a systematic approach to find the most representative features of potential collision severity. For the second challenge, we propose a distribution-preserving resampling method to address the class imbalance. This approach includes two techniques: Remove Redundant Under Sampling (RRUS) and Core Seed-based Synthetic Minority Oversampling Technique (CS-SMOTE), which transform the imbalanced dataset into a balanced one while preserving the distribution characteristics of the original dataset. Finally, using the National Highway Traffic Safety Administration (NHTSA) dataset and the XGBoost algorithm, a potential collision severity prediction model is developed. The results demonstrate that the model achieves a prediction accuracy of over 97.7%, outperforming comparison models developed using other classification algorithms.

Assessing available sight distances (ASDs) affected by disability glare on highways is essential for establishing a relationship among ASDs, sun ray variations, roadside occlusions, and the driver's field-of-view. This study proposes a novel disability-glare-coupled ASD (DG-ASD) assessment method for two-lane highways. The method involves simulating road glare using sun ray simulations and ray occlusion identification, evaluating ASDs through a gaze-based field-of-view model combined with a primary line-of-sight function, and quantifying the reduction in ASDs caused by disability glare. Three road datasets are analysed to validate the proposed method. The proposed ray occlusion algorithm reduced computation time by approximately 89.9%, and the efficiency of the proposed field-of-view model improved by 97.40%. On average, DG-ASDs were approximately 42 m shorter than ASDs without the influence of disability glare. The findings of this research contribute to enhancing intelligent navigation systems and roadside infrastructure by enabling timely alerts for insufficient ASDs caused by disability glare.This research assessing ASDs affected by disability glare on highways, and contributes to enhancing intelligent navigation systems and roadside infrastructure by enabling timely alerts for insufficient ASDs caused by disability glare.

Accurate accident prediction is crucial for proactive safety management on urban expressways. However, its practical efficacy is hindered by several complex challenges, including the heterogeneity of causal data, the need to model the full temporal evolution of risk, and the synergistic, non-linear interactions between variables. To address these challenges, this study proposes BGAR, a dual-channel deep learning framework. The framework features a dual-channel architecture to disentangle static and dynamic data streams, a bidirectional GRU to model the complete risk lifecycle, and a multi-head attention mechanism to weigh critical factor combinations. Validated on a real-world expressway dataset, BGAR demonstrates superior predictive accuracy, outperforming the strongest of 12 established baseline models by 3% in terms of $�R^2$. More importantly, it provides a diagnostic tool that translates forecasts into actionable control strategies. By pinpointing risk drivers, the framework enables a fundamental shift from reactive response to precise, proactive safety management, thus bridging the gap between prediction and prevention. The predictive target is the short-term accident count for the monitored corridor, enabling operators to quantify imminent risk levels in addition to identifying their drivers.

Evaluating the accessibility of amenities is fundamental to achieving equitable urban planning of cities. The cumulative opportunity measure (CO) and the two-step floating catchment area method (2SFCA) are widely used in previous studies. Although there is ongoing debate and discussion about the choice of method for measuring accessibility, the comparison between these two methods has not been thoroughly examined and differences in the spatial distribution of accessibility and the resulting equity from them have tended to be ignored. Here, we contrasted the similarities and differences in spatial accessibility in 12 different scenarios by using CO and 2SFCA, respectively. The scenarios considered the two models in two transportation modes, public transport (PT) and private car (PC), and six key urban services, company, education, healthcare, shopping, restaurant, and scenery, are thoroughly explored. Equity, between different housing price areas, was also evaluated by using the Gini coefficient and Palma ratio. The findings show that the spatial distributions of accessibility from CO are more related to the whole city structure, while the results from 2SFCA can better reflect the local characteristics and spatial heterogeneity. Regarding equity, PT accessibility is less equitable than PC under CO, but more equitable under 2SFCA. We also found that the accessibility and equity of PT are more susceptible to the chosen method compared to PC. This study can help planners understand accessibility and equity from different views and make adjustments of resources allocation in future planning.

Deep reinforcement learning (DRL) based autonomous driving vehicles (ADVs) has attracted numerous researchers in recent years. Many DRL-based urban traffic scenarios ADVs have been studied. However, there still remains a notable gap in the literature regarding the incorporation of dynamic passenger preferences. For instance, the passenger dynamic preferences between safety, comfort and efficiency change as traffic changes. Existing researches often overlook the dynamic nature of passenger preferences, which can significantly impact the overall passenger experience. Therefore, to improve driving personality and efficiency, in this paper, we deal with the challenge of incorporating dynamic passenger preferences into ADVs using DRL. We propose an innovative DRL method that first leverages prior knowledge to reduce the preference space which can speed up the training process. Then we apply homotopy optimization to make DRL optimization problem gradually transition from non-preference to dynamic preference. We validate our approach utilizing a simulated merge environment. Experimental results show that our approach has faster convergence and better performance when dealing with dynamic preference.

The joint optimisation of parking gates and taxiing time is critical in improving airport operation efficiency. However, there is a lack of effective solutions to this problem, especially during peak hours. This paper constructs a joint optimisation model for parking gate and taxiing route assignment based on column generation (CG). An artificial bee colony–adaptive genetic algorithm fusion is designed to solve the joint model considering CG characteristics and can operate in parallel. Then this paper uses the actual data from Beijing Capital International Airport (PEK) and Kunming Changshui International Airport (KMG) to verify the proposed method. It is proved that this study can effectively improve parking gate and taxiway utilisation compared with the actual allocation results and baseline algorithms. Meanwhile, in peak hours, this method can still give stable results at an acceptable time.