IET Intelligent Transport Systems最新文献

Unmanned aerial vehicles (UAVs) play a crucial role in various domains such as military, civil, industrial, and so on. However, the coordination and task allocation of multiple UAVs in engineering practices face numerous challenges. As the scale of battlefields expands, and the diversity of UAV missions and constraints increases, the existing task allocation methods suffer from issues such as a mismatch between theoretical models and real-world applications, low task execution efficiency, and poor responsiveness in dynamic environments. To address these challenges, this paper proposes an improved genetic algorithm (GA)-based approach for multi-UAV cooperative task allocation. By collecting battlefield information, decomposing tasks, and considering UAV resource types, an optimization model for multi-UAV cooperative task allocation is constructed. The proposed method, using an improved GA, generates a set of Pareto-optimal task solutions for decision-makers. Case studies demonstrate that this approach effectively enhances task execution efficiency and reduces the total flight distance cost of UAVs.

Most current RM approaches are developed for fixed bottlenecks. However, the number and locations of bottlenecks are usually uncertain and even time-varying due to some unexpected phenomena, such as severe accidents and temporal lane closures. Thus, the RM approach should be able to enhance traffic flow stability by effectively handling the time-delay effect and fluctuations in traffic flow rate caused by uncertain bottlenecks. This study proposed a novel approach called deep reinforcement learning with curriculum learning (DRLCL) to improve ramp metering efficacy under uncertain bottleneck conditions. The curriculum learning method transfers an optimal control policy from a simple on-ramp bottleneck case to more challenging bottleneck tasks, while DRLCL agents explore and learn from the tasks gradually. Four RM control tasks were developed in the modified cell transmission model, including typical on-ramp bottleneck, fixed downstream bottleneck, random-location bottleneck, and multiple bottlenecks. With curriculum learning, the entire training process was reduced by 45.1% to 64.5%, while maintaining a similar maximum reward level compared to DRL-based RM control with full learning from scratch. Specifically, the results also demonstrated that the proposed DRLCL-based RM outperformed the feedback-based RM due to its stronger predictive ability, faster response, and higher action precision.

Autonomous vehicles navigating urban roads require technology that combines low latency with high computing power. The limited resources of the vehicle itself compel it to offload task requirements to edge server (ES) for processing assistance. However, as the number of vehicles continues to increase, how edge servers reasonably allocate limited resources to autonomous vehicles becomes critical to the success of urban intelligent transportation services. This paper establishes an urban road scenario with multiple autonomous vehicles and an edge computing server and considers two main driving behaviour transition resource requests, namely car-following behaviour requests and lane-changing behaviour requests. Simultaneously, acknowledging that vehicles may encounter unforeseen traffic hazards when switching driving behaviours, a safety redundancy setting strategy is employed to allocate additional resources to the vehicle to ensure safety and model the vehicle resource allocation problem in the autonomous driving system. Double-deep Q-network (DDQN) is then used to solve this model and maximize the total system utility by comprehensively considering resource costs, system revenue, and autonomous vehicle safety. Finally, results from the simulation experiment indicate that the proposed dynamic resource allocation scheme, based on deep reinforcement learning for autonomous vehicles under edge computing, not only greatly improves the system's benefits and reduces processing delays compared to traditional greedy algorithms and value iteration, but also effectively ensures security.

On the cover: The cover image is based on the Research Article A multi-emission-driven efficient network design for green hub-and-spoke airline networks by Mengyuan Sun et al., https://doi.org/10.1049/itr2.12455.

Pedestrian flow refers to the spatiotemporal distribution of people moving in a defined area. At crosswalks, pedestrian dynamics exhibit complex self-organization patterns resulting from interactions between individuals. This paper proposes a novel crosswalk pedestrian flow model based on the concept of directional fuzzy visual field (DFVF) to capture pedestrian heterogeneity. The DFVF defines fuzzy distributions of personal space and information processing capabilities, enabling improved representation of diversity compared to previous models. Incorporating k-nearest neighbour rules in the DFVF pedestrian network topology also better mimics real-world interactions. Using a cellular automata framework, pedestrian self-organization effects like stratification and bottleneck oscillation are simulated at intersections. The model replicates empirically observed dynamics of density, velocity, and evacuation time. Results demonstrate that controlling pedestrian conflicts can effectively enhance crosswalk flow efficiency. This research introduces new techniques for simulating pedestrian psychology and behaviour, providing a valuable contribution to pedestrian flow theory and supporting crosswalk design optimization.

With the expansion of the metropolitan area, the application of express/local mode is gradually increasing. In contrast to the normal mode, the express/local mode has advantages in reducing energy consumption and saving total travel time by having express trains skipping some stops. This paper aims to minimize the total energy consumption of express and local train throughout the day by optimizing the train operation strategy in the same power supply section and increasing the overlap time between train traction acceleration and train regenerative braking to obtain the optimal energy-efficient timetable. As the consumed energy of a train is highly dependent on the rolling stock weight and the on-board passengers’ weight. An integer programming model is proposed with on-board passengers considered accurately, in which the dwell times, departure headway, and total turnaround time of express and local trains are determined. An improved grey wolf algorithm is designed by improving convergence factor and incorporating differential evolution to solve the proposed problem. The real data on Guangzhou Metro Line 18 is adopted for numerical studies. The results show that the optimized timetable increases the regenerative energy utilization rate by 21.37% and reduces the total energy consumption by 5.02% compared to the operational timetable.

For complex and dynamic high-speed driving scenarios, an adaptive model predictive control (MPC) controller is designed to ensure effective path tracking for automated vehicles. Firstly, in order to prevent model mismatch in the MPC controller, a tire cornering stiffness estimation algorithm is designed and a soft constraint on slip angle is added to further enhance the controller's precision in tracking trajectories and the vehicle's driving stability. Secondly, the improved particle swarm optimization (IPSO) method with dynamic weights and penalty functions is suggested to address the issue of insufficient accuracy in solving quadratic programming. Additionally, the standard particle swarm optimization (PSO) algorithm is used to seek the most suitable time horizon parameters offline to obtain the best time horizon data set under different vehicle speeds and adhesion coefficients, and then it is optimized online by an adaptive network-based fuzzy inference system (ANFIS) to enhance the model predictive controller's adaptability in different operating conditions. Finally, simulation experiments are conducted under three different operating conditions: docked roads, split roads, and variable vehicle speeds. The results indicate that the designed adaptive MPC controller can accurately and stably track the reference trajectory in various scenarios.

In this work, the connected vehicle's messages are used to create an enhanced adaptive traffic signal control (ATSC) system for improved traffic flow. Few existing studies use connected and automated vehicles (CAVs) to develop traffic signal control algorithms under hybrid connected and autonomous conditions. The proposed approach focuses on a four-phase traffic intersection with both CAVs and human-driven vehicles (HVs). CAVs share real-time state information, and a model called Roads Dynamic Segmentation estimates queuing procedures and vehicle fleet numbers on dynamic road sections. This information is used in the Store and Forward Model (SFM) to predict intersection queuing length. The ATSC system, based on model predictive control (MPC), aims to minimize intersection queue length while considering traffic constraints (undersaturated, saturated, and oversaturated) and avoiding free-flow problems due to queue overflow. To reduce computational complexity, a linear-quadratic-regulator (LQR) is used. Real-world vehicle trajectories and the SUMO tool are used for experimental purposes. Results show that the proposed method reduces average delay by 38.50% and 33.42% compared to fixed timing and traditional MPC in cases of oversaturated traffic flow with 100% CAV penetration. Even with a penetration rate of only 20%, average delay decreases by 13.65% and 6.50%, respectively. This study showcases not only the potential benefits of CAV in enhancing traffic, but also enables the optimal utilization of green duration in signalized intersection control systems. This helps prevent traffic congestion and ensures the efficient and smooth movement of traffic flow.

Metro systems play an important role in reducing urban traffic congestion and promoting the sustainable development of urban transport in megacities. With the expansion of a metro network, transfer stations are necessary for increasing the service connectivity of a metro network. An accurate estimation of transfer passenger flow can help improve the operations management of a metro system. This study proposes a data-driven methodology for estimating the transfer passenger flow volume of each transfer station in a metro network by mining smart card data. The estimated transfer passenger flow data are visualized to show the spatial-temporal distribution characteristics of metro transfer passenger flow. The case study results of the Shenzhen Metro network demonstrate that the proposed data-driven methodological framework is very effective in estimating different types of transfer passenger flows, such as total transfer passenger flow, hourly transfer passenger flow, and inbound and outbound transfer flows at each transfer station. The spatial-temporal distribution characteristics of transfer passenger flow can be very useful for designing effective and efficient passenger flow management measures to ensure the safe and efficient operation of a metro system.

With the increasing concerns about railway energy efficiency, two typical driving strategies have been used in actual train operation. One includes a sequence of full power traction, cruising, coasting, and full braking (CC). The other uses coasting–remotoring (CR) to replace cruising in CC. However, energy-saving performance by CC and CR, which can be affected by route parameters of gradients and speed limits, has not been fully compared and studied. This paper analyses the energy distribution of CC and CR considering various route parameters and proposes an improved strategy for different gradients and speed limits. The detailed energy flow of CC and CR is analysed by Cauchy–Bunyakovsky–Schwarz inequality and the generalised Hölder's inequality, and then, a novel driving strategy CC_CR is designed. To verify the theoretical results and the effectiveness of the proposed strategy, three simulators with CC, CR, and CC_CR driving modes have been developed and implemented into case studies of four scenarios as well as a real-world metro line. Simulation results demonstrate that CR can only outperform CC on routes with steep downhill and CC_CR is always the best strategy. The energy savings of CC_CR can be as much as 15% more than CR and 42% greater than CC.