IET Intelligent Transport Systems最新文献

In the cooperative vehicle-infrastructure system (CVIS), due to its computation limitation, vehicles are difficult to handle computing-intensive delay-sensitive tasks, so offload tasks to roadside unit (RSU) become popular. Due to the complexity of vehicles’ tasks and tasks generated by different vehicles have different delay constraints, minimize energy consumption of RSUs under task dependence and delay constraints is challenging. This paper defines the task priority queuing criterion for the task priority division problem, proposes a task scheduling strategy for energy-packet queue length tradeoff (TSET) in CVIS under RSUs distributed task scheduling problem and establishes the vehicle speed state model, task model, data queue model, task computing model and energy consumption model. After Lyapunov optimization theory transformed the optimization model, a knapsack problem was described. The simulation results verify that TSET reduces the average energy consumption of roadside units and ensures the stability of the data queue under task dependence and deadline conditions.

The purpose of signal control is to allocate time for competing traffic flows to ensure safety. Artificial intelligence has made transportation researchers more interested in adaptive traffic signal control, and recent literature confirms that deep reinforcement learning (DRL) can be effectively applied to adaptive traffic signal control. Deep neural networks enhance the learning potential of reinforcement learning. This study applies the DRL method, Double Deep Q-Network, to train local agents. Each local agent learns independently to accommodate the regional traffic flows and dynamics. After completing the learning, a global agent is created to integrate and unify the action policies selected by each local agent to achieve the purpose of traffic signal coordination. Traffic flow conditions are simulated through the simulation of urban mobility. The benefits of the proposed approach include improving the efficiency of intersections and minimizing the overall average waiting time of vehicles. The proposed multi-agent reinforcement learning model significantly improves the average vehicle waiting time and queue length compared with the results from PASSER-V and pre-timed signal setting strategies.

This study addresses the challenge of quantitatively assessing ride comfort in tram travel in Growing Urban Environments, where multiple influencing factors complicate developing a unified evaluation index system. A comprehensive evaluation framework based on cloud theory is proposed to overcome this challenge. The approach involves defining five-level comfort evaluation grades to capture passengers' experiences and perceptions accurately. The Criteria Importance through Inter-Criteria Correlation (CRITIC) method is employed to ensure objectivity to establish objective weights for evaluation indices. Subsequently, a cloud model algorithm is utilized to generate evaluation benchmark and actual result clouds, providing intuitive representations of the evaluation outcomes. The efficacy and rationality of the methodology is illustrated through a case study focusing on Suzhou Tram Line 2. This research contributes valuable insights for enhancing public transportation experiences in new urban settings by offering a systematic and objective approach to assessing tram ride comfort.

Connected and autonomous driving technologies offer a novel solution for intersection control optimization. Connected and autonomous vehicles (CAVs) can access signal plans and optimize trajectories to minimize delays and reduce fuel consumption. However, optimizing trajectories for individual vehicles significantly increases complexity, especially for joint optimization of traffic signals and vehicle trajectories. Given the current technical, regulatory, and policy constraints, a superior intersection management approach is necessary before fully automated driving is achieved. This paper introduces an adaptive coupling control (ACC) method based on vehicle platooning to optimize signal timings and vehicle trajectories in mixed traffic. Initially, vehicle platoon segmentation is conducted, led by CAVs. The study then proposes a single-layer coupled optimization model based on vehicle platoons, simplifying the joint optimization model. To address logistic constraint difficulties, a linearization of the coupled model (LCM) method is developed. Numerical experiments demonstrate that the ACC method significantly reduces vehicle delay and fuel consumption. At high CAV penetration rates (0.8 < R <1) and high traffic volumes (over 900 pcu/h), vehicle platoon control delivers excellent performance, with delays and fuel consumption even lower than in a fully automated environment (R = 1). This surprising result suggests that the mixed platoon system (ACC method) positively impacts mixed traffic.

Four-dimensional trajectory prediction is a crucial component of air traffic management, and its accuracy is closely related to the efficiency and safety of air transportation. Although long short-term memory (LSTM) or its variants have been widely used in recent studies, they may produce unacceptable results in long-term prediction due to the iterative output that accumulates error. To address this issue, a transformer-based long-term trajectory prediction model is proposed here, which utilizes the self-attention mechanism to extract time series features from historical trajectory data. For long-term prediction scenarios, we a trajectory stabilization module is introduced to ensure the stationarity of the time series for better predictability. Additionally, the transformer output strategy is improved to generate the prediction sequence by a single step instead of serial dynamic decoding, thus effectively enhancing the precision and inference speed. The proposed model is validated using real data obtained from China's Southwest Air Traffic Management Bureau. The experimental results demonstrate that this model outperforms the benchmark model. Further ablation experiments and visualizations are performed to analyze the impact of trajectory stabilization and one-step inference strategy.

A lightweight, high-definition vector map (HDVM) enables fully autonomous vehicles. However, the generation of HDVM remains a challenging problem, especially in complex urban scenarios. Moreover, numerous factors in the urban environment can degrade the accuracy of HDVM, necessitating a reliable error quantification. To address these challenges, this paper presents an open-source and generic HDVM generation pipeline that integrates the global navigation satellite system (GNSS), inertial navigation system (INS), light detection and ranging (LiDAR), and camera. The pipeline begins by extracting semantic information from raw images using the Swin Transformer. The absolute 3D information of semantic objects is then retrieved using depth from the 3D LiDAR, and pose estimation from GNSS/INS integrated navigation system. Vector information (VI), such as lane lines, is extracted from the semantic information to construct the HDVM. To assess the potential error of the HDVM, this paper systematically quantifies the impacts of two key error sources, segmentation and LiDAR-camera extrinsic parameter error. An error propagation scheme is first formed to illustrate how these errors fundamentally influence the accuracy of the HDVM. The effectiveness of the proposed pipeline is demonstrated through our codeavailable at https://github.com/ebhrz/HDMap. The performance is verified using typical datasets, including indoor garages and complex urban scenarios.

Explicit signal coordination carries prior knowledge of traffic engineering and is widely accepted for global implementation. With the recent popularity of reinforcement learning, numerous researchers have turned to implicit signal coordination. However, these methods inevitably require learning coordination from scratch. To maximize the use of prior knowledge, this study proposes an explicit coordinated signal control (ECSC) method using a soft actor–critic for cycle length determination. This method can fundamentally solve the challenges encountered by traditional methods in determining the cycle length. Soft actor–critic was selected among various reinforcement learning methods. A single agent was administered to the arterials. An action is defined as the selection of a cycle length from among the candidates. The state is represented as a feature vector, including the cycle length and features of each leg at every intersection. The reward is defined as departures that indirectly minimize system vehicle delays. Simulation results indicate that ECSC significantly outperforms the baseline methods, as evident in system vehicle delay across nearly all demand scenarios and throughput in high demand scenarios. The ECSC revitalizes explicit signal coordination and introduces new perspectives on the application of reinforcement learning methods in signal coordination.

The increasing level of air pollution caused by the transport sector necessitates countries to adopt Electric Vehicles (EVs). To espouse EVs, the charging infrastructures' location should be optimal to fulfill the mass-market consumer needs and reduce the governmental expenses. In this work, the placement of two categories of charging infrastructures, specifically Charging Station (CS) and Dynamic Wireless Charging (DWC) infrastructure is planned in Dubai, United Arab Emirates (UAE) as a case study. For this study, Dubai is divided into 14 districts as per its new addressing system, and the allocation of the two types of charging infrastructures is based on the projection of population growth, EVs adoption forecasting, and other factors with the objective of meeting the consumers' needs and minimizing the government's expenditure. The proposal introduces a novel hybrid model for forecasting, integrating the strengths of the Seasonal AutoRegressive Integrated Moving Average with eXogenous regressors (SARIMAX) model for capturing time-series statistical characteristics, and the deep learning Attention-based Convolutional Neural Network (ACNN) for modeling nonlinear relationships in time-series data. The model's effectiveness was validated through comparative analyses against state-of-the-art (SOTA) models on standard benchmarks, showing significant improvements: 29.70% reduction in Mean Absolute Error (MAE), and 19.15% reduction in Root Mean Square Error (RMSE).

Aiming to address the challenge where existing methods struggle to predict accurate disparities for imperfectly rectified stereo images, and that supervised training requires a considerable amount of ground truth, a self-supervised binocular depth estimation algorithm with self-rectification for autonomous driving is proposed. Firstly, a subnetwork dedicated to stereo rectification, aiming to estimate the homography between stereo images is developed. This homography facilitates the transformation of stereo image pairs, aligning their corresponding pixels horizontally. Secondly, a foundational self-supervised framework primarily centred on minimizing errors in stereo image reconstruction, combined with the generative-adversarial strategy is introduced. Finally, a vertical offset prediction module (VOPM) is incorporated into the basic framework to further enhance the resistance of the stereo matching network to pixel-level vertical offset errors. Experimental results on the public KITTI dataset for autonomous driving demonstrate the effectiveness of this approach in improving the disparity prediction performance for imperfectly rectified stereo images. Moreover, the self-supervised training framework exhibits superiority over state-of-the-art methods.

To standardize driver behaviour and enhance transportation system safety, a dynamic driver behaviour recognition method based on the Recurrent All-Pairs Field Transforms (RAFT) temporal model is proposed. This study involves the creation of two datasets, namely, Driver-img and Driver-vid, including driver behaviour images and videos across various scenarios. These datasets are subject to preprocessing using RAFT optical flow techniques to enhance the cognitive process of the network. This approach employs a two-stage temporal model for driver behaviour recognition. In the initial stage, the MobileNet network is optimized and the GYY module is introduced, which includes residuals and global average pooling layers, thereby enhancing the network's feature extraction capabilities. In the subsequent stage, a bidirectional GRU network is constructed to learn driver behaviour video features with temporal information. Additionally, a method for compressing and padding video frames is proposed, which serves as input to the GRU network and enables intent prediction 0.2 s prior to driver actions. Model performance is assessed through accuracy, recall, and F1 score, with experimental results indicating that RAFT preprocessing enhances accuracy, reduces training time, and improves overall model stability, facilitating the recognition of driver behaviour intent.