Explore the vast range of titles available.

Predicting the trajectories of surrounding vehicles is an essential task in autonomous driving, especially in a highway setting, where minor deviations in motion can cause serious road accidents. The future trajectory prediction is often not only based on historical trajectories but also on a representation of the interaction between neighbouring vehicles. Current state-of-the-art methods have extensively utilized RNNs, CNNs and GNNs to model this interaction and predict future trajectories, relying on a very popular dataset known as NGSIM, which, however, has been criticized for being noisy and prone to overfitting issues. Moreover, transformers, which gained popularity from their benchmark performance in various NLP tasks, have hardly been explored in this problem, presumably due to the accumulative errors in their autoregressive decoding nature of time-series forecasting. Therefore, we propose MALS-Net, a Multi-Head Attention-based LSTM Sequence-to-Sequence model that makes use of the transformer’s mechanism without suffering from accumulative errors by utilizing an attention-based LSTM encoder-decoder architecture. The proposed model was then evaluated in BLVD, a more practical dataset without the overfitting issue of NGSIM. Compared to other relevant approaches, our model exhibits state-of-the-art performance for both short and long-term prediction.

This study addresses vehicle trajectory tracking control under tri‐modal cyber attacks, encompassing fixed sensor‐to‐controller/controller‐to‐actuator channel attacks in lateral dynamics and sparse multi‐sensor attacks in position tracking. A hybrid fuzzy modeling framework is developed, integrating fuzzy logic inference with Takagi‐Sugeno fuzzy techniques to approximate vehicle dynamics with time‐varying velocity, payload‐dependent mass, and unmeasurable cornering stiffness avoiding the conservatism inherent in conventional linear fractional transformation approaches for cornering stiffness parameterization. A dual‐observer architecture combining an extended state observer and a supervisory fuzzy reduced‐order observer (ESO‐SFRO) is proposed for simultaneous system state reconstruction and tri‐modal attack signal estimation. Based on the estimated states, a cyber‐resilient controller is designed to ensure lateral stability and trajectory tracking accuracy. Experimental validation via CarSim/Simulink co‐simulation demonstrates the proposed ESO‐SFRO based controller exhibits superior dynamic stability and trajectory tracking performance under coupled cyber‐physical disturbances. This study proposes a hybrid fuzzy modeling framework for vehicle trajectory tracking under tri‐modal cyber attacks, integrating Takagi‐Sugeno techniques to handle time‐varying dynamics and unmeasurable cornering stiffness. A dual‐observer architecture (ESO‐SFRO) simultaneously reconstructs system states and estimates attack signals, enabling a cyber‐resilient controller that ensures lateral stability and tracking accuracy. CarSim/Simulink co‐simulation validates the controller's robustness against coupled cyber‐physical disturbances.

Crowdsourcing trajectory data is an important approach for accessing and updating road information. In this paper, we present a novel approach for extracting road boundary information from crowdsourcing vehicle traces based on Delaunay triangulation (DT). First, an optimization and interpolation method is proposed to filter abnormal trace segments from raw global positioning system (GPS) traces and interpolate the optimization segments adaptively to ensure there are enough tracking points. Second, constructing the DT and the Voronoi diagram within interpolated tracking lines to calculate road boundary descriptors using the area of Voronoi cell and the length of triangle edge. Then, the road boundary detection model is established integrating the boundary descriptors and trajectory movement features (e.g., direction) by DT. Third, using the boundary detection model to detect road boundary from the DT constructed by trajectory lines, and a regional growing method based on seed polygons is proposed to extract the road boundary. Experiments were conducted using the GPS traces of taxis in Beijing, China, and the results show that the proposed method is suitable for extracting the road boundary from low-frequency GPS traces, multi-type road structures, and different time intervals. Compared with two existing methods, the automatically extracted boundary information was proved to be of higher quality.

The vehicle license plate data obtained from video-imaging detectors contains a huge volume of information of vehicle trip rules and driving behavior characteristics. In this paper, a real-time vehicle trajectory prediction method is proposed based on historical trip rules extracted from vehicle license plate data in an urban road environment. Using the driving status information at intersections, the vehicle trip chain is acquired on the basis of the topologic graph of the road network and channelization of intersections. In order to obtain an integral and continuous trip chain in cases where data is missing in the original vehicle license plate, a trip chain compensation method based on the Dijkstra algorithm is presented. Moreover, the turning state transition matrix which is used to describe the turning probability of a vehicle when it passes a certain intersection is calculated by a massive volume of historical trip chain data. Finally, a k-step vehicle trajectory prediction model is proposed to obtain the maximum possibility of downstream intersections. The overall method is thoroughly tested and demonstrated in a realistic road traffic scenario with actual vehicle license plate data. The results show that vehicles can reach an average accuracy of 0.72 for one-step prediction when there are only 200 historical training data samples. The proposed method presents significant performance in trajectory prediction.

To address the issue of safe, orderly, and efficient operation for unmanned vehicles within the apron area in the future, a hardware framework of aircraft–vehicle–airfield collaboration and a trajectory planning method for unmanned vehicles on the apron were proposed. As for the vehicle–airfield perspective, a collaboration mechanism between flight support tasks and unmanned vehicle departure movement was constructed. As for the latter, a control mechanism was established for the right-of-way control of the apron. With the goal of reducing waiting time downstream of the pre-selected path, a multi-agent reinforcement learning model with a collaborative graph was created to accomplish path selection among various origin–destination pairs. Then, we took Apron NO.2 in Ezhou Huahu Airport as an example for simulation verification. The results show that, compared with traditional methods, the proposed method improves the average vehicle speed and reduces average vehicle queue time by 11.60% and 32.34%, respectively. The right-of-way signal-switching actions are associated with the path selection behavior of the corresponding agent, fitting the created aircraft–vehicle collaboration. After 10 episodes of training, the Q-values can steadily converge, with the deviation rate decreasing from 40% to below 0.22%, making the balance between sociality and competitiveness. A single trajectory can be planned in just 0.78 s, and for each second of training, 7.54 s of future movement of vehicles can be planned in the simulation world. Future research could focus on online rolling trajectory planning for UGSVs in the apron area, and realistic verification under multi-sensor networks can further advance the application of unmanned vehicles in apron operations.

Sequential pattern mining (SPM) is a major class of data mining topics with a wide range of applications. The continuity and uncertain nature of trajectory data make it distinctively different from typical transactional data, which requires additional data transformation to prepare for SPM. However, little research focuses on comparing the performance of SPM algorithms and their applications in the context of trajectory data. This study selected some representative sequential pattern mining algorithms and evaluated them with various parameters to understand the effect of the involved parameters on their performances. We studied the resultant sequential patterns, runtime, and RAM consumption in the context of the taxi trajectory dataset, the T-drive dataset. It was demonstrated in this work that a method to discretize trajectory data and different SPM algorithms were performed on trajectory databases. The results were visualized on actual Beijing road maps, reflecting traffic congestion conditions. Results demonstrated contiguous constraint-based algorithms could provide a concise representation of output sequences and functions at low min_sup with balanced RAM consumption and execution time. This study can be used as a guide for academics and professionals when determining the most suitable SPM algorithm for applications that involve trajectory data.

With the development of information technology, massive traffic data-driven short-term traffic situation analysis of urban road networks has become a research hotspot in urban traffic management. Accurate vehicle trajectory and traffic flow prediction can provide technical support for vehicle path planning and road congestion warning. Unlike most studies that use GPS data to predict vehicle trajectories, this paper combines the broad coverage, high reliability, and lighter weight of traffic checkpoint data to propose a method that uses trajectory prediction technology to forecast the traffic flow in urban road networks accurately. The method adopts a checkpoint data-driven approach for data collection, combines graph convolutional neural network (GCN) and gated recurrent unit (GRU) models to more effectively learn and extract spatiotemporal correlation features of vehicle trajectories, which significantly improves the accuracy of vehicle trajectory prediction, and uses the output of the trajectory prediction model to forecast traffic flow more accurately. Firstly, transforming the checkpoint data into daily vehicle trajectories with time series characteristics, realizing the vehicle trajectory travel chain division. Secondly, the adjacency matrix is established by using the spatial relationship of each checkpoint, and the feature matrix of the vehicle’s driving trajectory over time is established, which is used as the input of GCN to learn the spatial characteristics of the vehicle while driving on the road network, and then GRU is added to further process the data after GCN training, constructing a GCN-GRU vehicle trajectory prediction model for vehicle trajectory prediction. Finally, the traffic flow of each checkpoint is calculated based on the prediction result of vehicle trajectory and compared with the real checkpoint flow. This paper conducts many experiments on the Qingdao City Shinan district checkpoint dataset. The results show that compared with the single models GCN, GRU, BiGRU, and BiLSTM, the GCN-GRU model has reduced the MAE by 0.75, 0.46, 0.52, and 0.57, and the RMSE by 0.76, 0.52, 0.58, and 0.68, respectively, demonstrating stronger spatial and temporal correlation characteristics and higher prediction accuracy. The MAPE between the forecasted flow and the real flow is 0.18, which verifies the reliability of the proposed method.

In heterogeneous traffic flow environments, it is critical to accurately predict the future trajectories of human-driven vehicles around intelligent vehicles in real time. This paper introduces a neural network model that integrates both spatial interaction information and the long-term and short-term characteristics of the time series. Initially, the historical state information of both the target vehicle and its surrounding counterparts, along with their spatial interaction relationships, are fed into a Graph Attention Network (GAT) encoder. The graph attention layer effectively manages the intricate relationships among vehicle nodes. Subsequently, this information undergoes processing through a Transformer encoder to extract global dependencies; additionally, residual connections are incorporated to enhance feature representation capabilities. Finally, these data are further captured by the LSTM encoder for capturing short-term features within the time series, and the LSTM decoder receives the hidden state and generates the future trajectory of the target vehicle. Validation conducted on a public dataset demonstrates that the predictive performance of this model significantly outperforms that of the baseline models.

This study investigates the critical control factors differentiating human-driven vehicles from IoT edge-enabled smart driving systems Real-time steering, throttle, and brake control are the main areas of emphasis. By combining many high-precision sensors and using edge computing for real-time processing, the research seeks to improve autonomous vehicle decision-making. The suggested system gathers real-time time-series data using LiDAR, radar, GPS, IMU, and ultrasonic sensors. Before sending this data to a cloud server, edge nodes preprocess it. There, a Convolutional Neural Network (CNN) creates predicted control vectors for vehicle navigation. The study uses a MATLAB 2023 simulation framework that includes 100 autonomous cars, five edge nodes, and a centralized cloud server. Multiple convolutional and pooling layers make up the CNN architecture, which is followed by fully linked layers. To enhance trajectory estimation, grayscale and optical flow pictures are used. Trajectory smoothness measures, loss function trends, and Root Mean Square Error (RMSE) are used to evaluate performance. According to experimental data, the suggested CNN-based edge-enabled driving system outperforms conventional autonomous driving techniques in terms of navigation accuracy, achieving an RMSE of 15.123 and a loss value of 2.114. The results show how edge computing may improve vehicle autonomy and reduce computational delay, opening the door for more effective smart driving systems. In order to better evaluate the system’s suitability for dynamic situations, future study will incorporate real-world validation.

Transformer-based models have demonstrated outstanding performance in trajectory prediction; however, their complex architecture demands substantial computing power, and their performance degrades significantly in long-term prediction. A transformer model was developed to predict vehicle trajectory in urban low-speed T-intersections. Microscopic traffic simulation data were generated to train the trajectory-prediction model; furthermore, validation data focusing on atypical scenarios were also produced. The appropriate loss function to improve prediction accuracy was explored, and the optimal input/output sequence length for efficient data management was examined. Various driving-characteristics data were employed to evaluate the model’s generalization performance. Consequently, the smooth L1 loss function showed outstanding performance. The optimal length for the input and output sequences was found to be 1 and 3 s, respectively, for trajectory prediction. Additionally, improving the model structure—rather than diversifying the training data—is necessary to enhance generalization performance in atypical driving situations. Finally, this study confirmed that the additional features such as vehicle position and speed variation extracted from the original trajectory data decreased the model accuracy by about 21%. These findings contribute to the development of applicable lightweight models in edge computing infrastructure to be installed at intersections, as well as the development of a trajectory prediction and accident analysis system for various scenarios.