IET Intelligent Transport Systems最新文献

Peri-urban and rural mobility presents unique challenges due to its reliance on fossil fuels and the lack of comprehensive studies on its externalities. Furthermore, the provision of efficient public transport in peri-urban areas is complicated due to fluctuating demand patterns. In this context, this paper explores the optimisation of a bimodal (bus line and a diesel railway line) public transport corridor in the peri-urban area of a European medium-sized city. A four-stage research methodology is employed: initial system characterisation, energy and environmental performance analysis, operational efficiency assessment, and the development and evaluation of alternative transport strategies. The study concludes that the variability in demand necessitates the implementation of innovative, complementary services that can adapt to changing passenger numbers while optimising existing resources. Findings of the case study indicate that aligning bus types with demand variability and integrating electric buses can lead to substantial reductions in CO₂ emissions. The use of minibuses during off-peak hours could achieve a 50% reduction in emissions, while the adoption of a bus rapid transit (BRT) system may result in a 90% decrease compared to conventional diesel trains. The research underlines the potential for innovative service models to utilise existing infrastructure more efficiently.

The complex interaction between traffic participants brings safety problems for autonomous driving in mixed-traffic environment. Current state-of-the-art (SOTA) vehicle trajectory prediction models suffer significant performance degradation when high-definition (HD) map inputs are excluded, which may compromise the safety of decision-making and planning for autonomous driving systems in real-world traffic environments. To address this challenge, this paper proposes a novel dual-channel interactive modelling framework, termed the DCSTNet (dual-channel spatio-temporal information fusion network), specifically designed for vehicle trajectory prediction without relying on HD map information. Unlike previous trajectory prediction models that model temporal and spatial interactions interlacing or hierarchically, DCSTNet decoupling temporal and spatial interaction modules through a specially designed encoding network. This practice enables the model to more fully extract interaction features without increasing computational complexity when map information is not considered. To verify the validity of the dual-channel spatio-temporal information fusion framework, our study uses the publicly available Argoverse motion forecasting dataset. The comparison of results demonstrates that DCSTNet outperforms many SOTA approaches, including those that use map-based priors. To further validate that decoupling temporal and spatial interaction modelling enhances feature extraction capabilities, we conduct rigorous ablation studies and sensitivity analysis on the dataset to dissect architectural components of the DCST network. To explore the adaptability of the framework, we also develop a map-based variant of DCSTNet and compare its predictions with the map-free version in complex road environments.

This paper introduces a vehicle-assisted multi-drone inspection routing problem (VAMDIRP), which enables the vehicle to repeatedly traverse roads, thereby reducing task completion time. Firstly, a mixed-integer linear programming (MILP) model is constructed for the problem using a series of decision variables and auxiliary variables. The model can be solved by GUROBI for small-scale instances. Secondly, a two-stage heuristic algorithm is proposed to solve large-scale instances. Experimental results show that this algorithm improves the solution quality by an average of 20.71% and reduces the running time by an average of 60.31% compared to existing algorithms. Finally, a sensitivity analysis is conducted on relevant parameters, revealing that changes in the number and speed of drones significantly affect the solution quality.

This case study presents state-of-the-art, multimodal structural reliability and risk evaluation methodology, particularly suitable for naval architecture, transportation and marine engineering applications.

Existing reliability methods do not easily tackle systems with a number of critical components higher than 2, while the advocated multimodal reliability and risk evaluation methodology has no limitations on the system's number of dimensions, parts or components. The 4400 TEU container vessel's onboard measured deck panel stresses raw data, collected during numerous vessel's trans-Atlantic crossings, was analysed. Risk of ship hull and panel structural damage caused by excessive whipping (slamming and springing) wave loads, representing types of highly nonlinear wave-induced vibrations, are among primary safety concerns for the contemporary marine transportation industry. It is often challenging to accurately forecast excessive vessel's deck panel hot-spot stresses, possessing complex nonlinear, nonstationary properties. The proposed multimodal hypersurface reliability method fully accounts for a large number of structural components, as well as dynamic nonlinearities. Lab testing may often be disputed, as obtained measurements will depend on biased incident wave properties and model scales. As a result, the onboard dataset, obtained from a particular cargo ship, operating in the North Atlantic provides especially valuable insights into an overall dynamic vessel hull system's durability and reliability.

This investigation aimed at providing generic state-of-the-art reliability methodology, enabling accurate extraction of pertinent information about vessel hull system's dynamics, e.g., deck panel hot-spot stresses, derived from the onboard sensor-recorded time histories. Utilising proposed hypersurface reliability methodology, structural failure, hazard or damage risks may be effectively yet accurately forecasted, based on spatially distributed vessel deck panel stresses. The presented multimodal state-of-the-art reliability methodology may be particularly suitable for the evaluation of structural hazards of large dynamic systems, having virtually unlimited numbers of principal/key components. The presented study made use of the full scale onboard measured dataset, kindly provided by Det Norske Veritas, Oslo, Norway (DNV), which is commercially valuable on its own.

Work zones for road maintenance in traffic networks can significantly impact the traffic distribution and route choice behaviour of travellers. This study proposes an approach to evaluate and predict the broad-scale effects of work zones on large-scale traffic networks. For the requirement of the efficient evaluation of the various impacts of work zones on traffic networks, this study defines the road maintenance sensitivity factor (RMSF) to represent the joint impact of work zones. A simulation-based optimization method for calibrating the RMSF is formulated. The original objective function is replaced by an analytical metamodel that builds the approximate relationship between the RMSFs and traffic flow distribution with the effect of work zones. A derivative-free trust-region algorithm is used to obtain the optimal solution. Numerical experiments are conducted on a small test network and a large-scale freeway network. The proposed method shows the accuracy and effectiveness with tight computational resources than the simultaneous perturbation stochastic approximation method in both experiments, giving the RMSF results and map the traffic redistribution of large-scale networks with work zones accurately and efficiently, which can help traffic managers to optimize maintenance plans and traffic management measures with the assistance of the traffic management system.

A novel scheme is proposed for the distributed multi-ship collision avoidance (CA) problem with consideration of the autonomous, dynamic nature of the real circumstance. All the ships in the envisioned scenarios can share their decisions or intentions through route exchange, allowing them to make subsequent decisions based on the route planning in each iteration. By leveraging route exchange, the multi-ship CA problem involves iterations for negotiation, and is regarded as a staged cooperative game under conditions of complete information. The concept of closest spatio-temporal distance (CSTD) is introduced to more accurately assess collision risk between ships. A coordinated CA mechanism is established when a collision risk is identified, which further incorporates considerations including the stand-on/give-way relationships, negotiation rounds, route re-planning calculation, as well as the cost factor for route evaluation. The Nash bargaining solution (NBS) is elaborated to achieve Pareto-optimal CA routes in the scenarios. In the proposed model, while the individual interest of each ship are maximized, the economic fairness and global optimization of the overall system are also maintained. Simulation results indicate that the NBS shows good flexibility and adaptability, and that when all ships comply with route re-planning solution, the proposed scheme can bring out normal solutions within a limited number of re-planning iterations.

Automated guided vehicles (AGVs) serve as pivotal equipment for horizontal transportation in automated container terminals (ACTs), necessitating the optimization of AGV scheduling. The dynamic nature of port operations introduces uncertainties in AGV energy consumption, while battery constraints pose significant operational challenges. However, limited research has integrated charging and discharging behaviors into AGV operations. This study innovatively proposes an AGV scheduling model that incorporates a resilient and adaptive charging strategy, adjusting the balance between vehicle charging and the completion of transportation tasks, enabling AGVs to complete fixed container transportation tasks in the shortest time. Differing from most existing research primarily based on OR-typed algorithms, this study proposes a reinforcement learning-based AGV scheduling method. Finally, a series of numerical experiments, which is based on a real large-scale automated terminal in the Pearl River Delta (PRD) region of Southern China, are conducted to verify the effectiveness and efficiency of the model and the algorithm. Some beneficial management insights are obtained from sensitivity analysis for practitioners. Notably, the paramount observation is that the operational efficacy of AGVs does not necessarily correlate positively with their number. Instead, it follows a “U-shaped” curve trend, indicating an optimal range beyond which performance diminishes.

Recent advancements on digital technologies, particularly artificial intelligence, have been resulted into remarkable transformations in automobile industry. One of these technologies is artificial intelligence (AI). AI plays a key role in the development of autonomous vehicles. In this paper, the role of AI in autonomous vehicle (AV) platform layers is studied. The focus of this paper is on the indexed papers in Scopus database. The most relevant keywords are selected and searched. 628 articles, between 2014 and 2024 were selected for analysing and reviewing. Articles were analysed based on source type, topics, and AI algorithms. Text mining and content analysis of articles revealed that 233 journals published 628 articles, and the most top 185 are selected to assess. The topics of paper are classified into perception, localization and mapping, planning, decision making, control, communication, security, data management, and general topics. Each of these areas consisted of many roles, or tasks and use AI to realize their tasks. Convolutional neural network in the perception, control, and localization and mapping layers have been more used. Deep reinforcement learning had the most application in planning and decision-making areas. The main result of this paper is recognition of AVs platform layers classification, designing a data-driven digital twin AI-based model of autonomous vehicles architecture, containing physical world, virtual world, and communication space, and mapping of applied AI algorithms each layer, which aid researchers to choose the suitable methods in the field of autonomous vehicles. This study provided a comprehensive map of research projects related to from 1985 to 2022. Finally, some research directions are suggested.

In the present work, an energy-efficient medium access control (MAC) protocol is proposed for the adaptive data traffic condition in VANET. The proposed adaptive collision free MAC-bit map assisted (ACFM-BMA) protocol represents a significant advancement in vehicular communication systems by integrating strategies focused on electric vehicle (EV) battery levels and buffer status. This protocol optimizes communication efficiency and energy conservation through a holistic approach that considers the dynamic nature of both the vehicles' energy resources and their data buffering capabilities. By incorporating real-time data about EV battery levels, the protocol ensures that communication tasks are scheduled in a manner that conserves energy, extending the operational lifespan of vehicles in the network. Additionally, the protocol takes into account the buffer status of each vehicle, preventing data congestion and loss and enhancing the reliability of data transmission. The integration of battery and buffer status information enables more efficient use of the communication channel, reducing idle times and improving overall throughput. The performance of the proposed method is analyzed based on overall vehicle density, the number of vehicles generating periodic data traffic, and the event occurrence probability of vehicles generating event data traffic. Three different scenarios are considered: low, medium, and high data traffic, corresponding to varying numbers of vehicles. The results demonstrate that the proposed method significantly conserves energy across all scenarios.

The traditional distributed control system of trains faces challenges such as weak functional coordination, limited information sharing, significant control response delays, and low speed control accuracy, thereby impeding the efficient and energy-saving operation of trains. This paper proposes a novel integrated control system architecture and approach for trains, facilitating rapid interaction and reuse of control information through the integration of data and computations from onboard signals, traction, braking, and network subsystems. Initially, a sophisticated software architecture for integrated control is developed. Subsequently, leveraging optimal control theory, the paper outlines a strategy for optimising the train's manipulation curve and employs the LQR control algorithm for speed tracking control. Finally, the effectiveness of the proposed integrated control method is rigorously validated through experiments. The results demonstrate that the proposed approach effectively reduces the need for frequent train operation condition switching, resulting in a 16.1% energy-saving rate in speed curve optimisation and maintaining a speed control error of less than 0.2 km/h, thus substantially enhancing energy efficiency and passenger comfort during train operations.