IET Intelligent Transport Systems最新文献

Existing studies on trajectory optimization for cooperative automated driving systems (C-ADS) equipped vehicles at signalized intersections operate under a simplified assumption of cooperative behaviour: all vehicles accept and follow to the prescribed plans. To investigate trajectory optimization for C-ADS-equipped vehicles with different cooperation classes, a deep deterministic policy gradient (DDPG) algorithm was developed within a reinforcement learning (RL) framework, alongside baseline implementations of trajectory smoothing (TS)-based C-ADS systems and human-driven vehicle scenarios. Experimental results indicate that the proposed methodology achieves significant reductions in average travel time (53.59%) and stop times, compared to benchmark approaches. Furthermore, novel insights into the performance improvements at signalized intersections were derived from analysing different cooperation classes of C-ADS-equipped vehicles via the RL model, providing critical guidance for refining control strategies in cooperative automated driving systems. This study validates that RL models utilizing the DDPG algorithm serve as effective tools for enhancing the performance of cooperative automated driving systems.

Unmanned aerial vehicles (UAVs) are becoming integral to time-sensitive logistics and intelligent mobility systems due to their flexibility, low deployment cost, and real-time connectivity. However, their open and dynamic communication environment—typically organized as flying ad hoc networks (FANETs)—makes them highly vulnerable to a wide spectrum of cyber threats. To address this, we propose a novel multihop intrusion node detection scheme (MINDS) powered by an AI-driven ensemble learning model, X-CID, optimized for lightweight drone networks. The proposed system integrates a decentralized multi-hop architecture with intra- and inter-cluster communication validation, enabling real-time anomaly detection across the physical, communication, and architectural layers of UAV systems. To improve detection performance under resource constraints, feature selection is applied using the Pearson correlation coefficient (PCC), and model hyperparameters are fine-tuned using randomized search cross-validation. Trained and evaluated on three benchmark datasets (WSN-DS, NSL-KDD, CICIDS2017) covering 24 distinct attack types, X-CID outperforms traditional models in F1-score (up to 99.84%), accuracy (up to 99.70%), and achieves low false alarm rates with competitive latency. The proposed approach ensures robust, scalable, and energy-efficient security for autonomous drone communication, making it suitable for critical missions in logistics, disaster response, and aerial surveillance.

In recent years, multi-agent reinforcement learning (MARL) has been increasingly applied in training cooperative decision models for connected autonomous vehicles (CAVs). Despite the success they have demonstrated, they are bound to inherit issues that deep learning models suffer, such as vulnerability to adversarial attacks which is the focus of this study. Consequently, this paper aims to assess and enhance the robustness of MARL-trained cooperative policies used by CAVs, in terms of their resilience to adversarial behavior encountered during deployment. First, a specific existing cooperative policy was identified to be the victim policy, deployed in an on-ramp merging road scenario. Second, two adversarial policies, namely collision adversary ($��a�d�v_c�$) and speed adversary ($��a�d�v_s�$), were developed and trained to disrupt the performance of the victim policy. The adversarial policies significantly impacted the victim policy, increasing the collision rate to 62% and decreasing the average speed from 25 m/s to 21.73 m/s. Finally, several adversarial training approaches were developed, producing more robust cooperative policies against adversarial scenarios, by significantly bolstering road safety in adversarial conditions. The collision rate was cut by half against $��a�d�v_c�$, whereas, 0% collision scored in the face of $��a�d�v_s�$.

It is a critical problem to improve battery energy management for electric vehicle platooning systems. Moreover, different from internal combustion engine vehicles, regenerating braking is widely used to recover part of the energy in the electric vehicle when it is braking. This paper presents the optimization method of battery energy management for electric vehicle platooning with regenerating braking. By investigating the force analysis of platooning and the battery model, a new optimization strategy is presented to minimize the cost of the battery for both charging and maintaining. The cost of the battery is not only related to the state of charge (SoC) but also concerned with the state of health (SoH) due to the battery aging phenomenon. Thus, a new cost function concerned with SoC and SoH consumption is presented. Further, the optimization problem is addressed by the dynamic programming method combined with the successive convex approximation method. Finally, it is discussed how to choose the trade-off weights to adapt to different actual situations, and simulation results are provided to verify the effectiveness and advantages of the proposed methods.

Vehicular edge computing (VEC) has emerged as a promising paradigm to reduce the latency of vehicular tasks by leveraging edge computing resources. However, the high mobility of vehicles and the limited computational capacity of edge servers (ESs) present significant challenges to achieving efficient VEC. To address these challenges, this paper proposes a fine-grained computation task cooperative offloading and migration strategy. Specifically, applications are decomposed into multiple interdependent subtasks, which are collaboratively executed across multiple ESs. As vehicles move, computation tasks are dynamically migrated among ESs to ensure service continuity. The joint optimisation of task offloading and migration is formulated as a multi-stage mixed integer non-linear programming problem. To tackle this problem, we first employ Lyapunov optimisation to transform the multi-stage problem into a deterministic optimisation problem at each time slot, aiming to maximise long -term system revenue. Furthermore, considering the dynamic environment characterised by vehicle mobility, time-varying channels, subtask dependencies and inter-vehicle channel interference, we integrate a graph convolutional network (GCN) into the counterfactual multi-agent policy gradients (COMA) framework. By integrating Lyapunov optimisation with COMA-GCN, we propose Ly-COMA, a novel algorithm that effectively minimises the average task execution delay. Extensive experimental results demonstrate that the proposed algorithm outperforms existing methods in terms of average delay reduction and migration cost efficiency.

This paper presents a comprehensive, data-driven framework for personalised driving risk assessment, designed to enhance driver safety within intelligent transportation systems. By leveraging crowdsensed telemetric and road environment data, the framework captures diverse driving behaviours and contextual factors to provide real-time, individualised risk insights. The two-phase framework combines Gaussian Mixture Model (GMM) clustering, Deep Embedded Clustering (DEC), and Fully Connected Network (FCN) for accurate risk classification and prediction, while Deep Q-Learning (DQN) delivers adaptive feedback that encourages safer driving practices. Extensive evaluation shows that our approach outperforms traditional models in both accuracy and adaptability with an accuracy score of 95% and an average F1-score of 0.94, demonstrating its value in capturing complex driver behaviour patterns and contributing a scalable solution for transportation safety.

To improve transportation efficiency, an adaptive speed control method is proposed for ship formation control when a ship formation enters a port with tidal elevation variations. The nonlinear model predictive control (NMPC) method and leader‒follower structure are utilised for the formation keeping and trajectory tracking tasks. The proposed method establishes a ship manoeuvring model and a dynamic speed constraint model for adaptive speed control. A safe distance model is constructed to maintain a safe distance between ship formation members. The proposed safe distance model utilises a Serret‒Frenet (S‒F) coordinate system to describe the positions of ship formation members. Simulation experiments are applied to the North Channel of the Yangtze River. The experimental results indicate that the maximum actual draught accounts for 101.4% of the maximum safe draught without speed constraints. The draft ratio decreases to 99.2% after the adaptive speed control method is applied. This method can be utilised to effectively control ship formation navigation considering variations in tidal elevation.

The continuous expansion of the high-speed rail (HSR) network not only shortens tourists' travel time but also significantly impacts the network attention of destinations. This study uses door-to-door HSR travel times from the Baidu Map API to compute weighted average travel time (WATT) for transportation accessibility (TA) and Baidu Index search data for tourism network attention (TNA) and applies coupling coordination degree (CCD) and relative development degree (RDD) models to evaluate TA-TNA coordination across 28 scenic areas and their host cities in the urban agglomerations in the middle reaches of the Yangtze River (UAMRYR) for 2016–2023. The results indicate that WATT fell by 14.9%, whereas TNA rose overall but remained uneven. The CCD-RDD analysis reveals that most scenic areas exhibit a TA lag category, whereas cities perform better than scenic areas in the coordinated development. To translate these findings into practice, three priorities emerge. (1) Last-mile transport and visitor services in fringe nodes should be improved; (2) Digital marketing and pricing should guide scenic area operations; (3) National and regional transport-tourism governance tools need to be strengthened. These insights provide a quantitative basis for aligning rail expansion, destination marketing, and infrastructure finance to achieve balanced regional tourism growth.

The transition to electric buses (e-buses) is essential for reducing greenhouse gas emissions in urban transit systems. However, successful e-bus deployment requires careful planning to ensure service reliability while minimising costs. A key challenge in this transition is determining the replacement factor, the ratio of e-buses needed to replace the current diesel-engine bus fleet for a certain route. This factor is essential for transit agencies as it directly influences fleet size, capital investment, and operational efficiency. Accurately estimating replacement factors allows agencies, to prioritise routes where electrification achieves the highest economic and environmental benefits while preventing unnecessary fleet expansion and idle capacity by selecting routes with low replacement factors. This study develops a framework for estimating e-bus replacement factors based on route characteristics, vehicle attributes, and external conditions. Multiple machine learning models are evaluated, with XGBoost achieving the highest accuracy (R² = 0.93). Model interpretability using SHapley Additive exPlanations (SHAP) analysis identifies the average bus speed and ambient temperature as the main variables affecting the replacement factor. The proposed framework enables transit agencies to optimise fleet deployment by prioritising routes with lower replacement factors, maximising e-bus utilisation, and achieving cost efficiencies while aligning with environmental objectives.

Electric vehicles (EVs) provide significant advantages for sustainable transportation, such as reduced energy consumption, the ability to integrate with renewable energy sources, and emission reductions. Nevertheless, range anxiety, high battery costs, and long charging times limit the adoption of EVs. Accurately estimating driving range is one of the solutions to overcome these limitations. This study proposes a method that combines an extra tree regressor (ETR) model and an artificial rabbit optimization (ARO) algorithm to predict the driving distance using a comprehensive dataset for EVs. In our experiments, we compared ARO with well-known hyperparameter optimization methods such as grid search (GS) and random search (RS), and tested the models across multiple train and test splits. Besides using the complete feature set, we applied recursive feature elimination (RFE) to select an informative subset and re-evaluated all methods. With all features, the best configuration of the proposed algorithm achieved an R-squared (R²) of 0.84, a root mean square error (RMSE) of 14.38, a mean absolute error (MAE) of 7.70, and a mean squared error (MSE) of 220.12. Using the selected subset of seven features, the proposed model reached an R² of 0.84, with an RMSE of 14.88, an MAE of 6.75, and an MSE of 221.53. Finally, the contribution of each feature's to the predicted driving range was analysed using shapely additive explanations (SHAP). The findings of the study emphasize the value of integrating machine learning (ML) models and hyperparameter search methods into electric vehicle range-estimation systems to improve driver confidence and support sustainable transportation.This study advances the current understanding of range prediction and contributes to reducing range anxiety, thereby supporting extensive adoption of EVs. The findings of the study indicate that the integration of ML approaches in the range estimation of EVs can play a critical role in increasing driver confidence and supporting sustainable transportation. This study contributes to the existing knowledge in the field of range estimation and is an important step toward the broader adoption of EVs.