Traffic Trajectory Research Articles

Traffic trajectory data analysis technology based on HMM model map matching algorithm.

The rapid growth of traffic trajectory data and the development of positioning technology have driven the demand for its analysis. However, in the current application scenarios, there are some problems such as the deviation between positioning data and real roads and low accuracy of existing trajectory data traffic prediction models. Therefore, a map matching algorithm based on hidden Markov models is proposed in this study. The algorithm starts from the global route, selects K nearest candidate paths, and identifies candidate points through the candidate paths. It uses changes in speed, angle, and other information to generate a state transition matrix that match trajectory points to the actual route. When processing trajectory data in the experiment, K = 5 is selected as the optimal value, the algorithm takes 51 ms and the accuracy is 95.3%. The algorithm performed well in a variety of road conditions, especially in parallel and mixed road sections, with an accuracy rate of more than 96%. Although the time loss of this algorithm is slightly increased compared with the traditional algorithm, its accuracy is stable. Under different road conditions, the accuracy of the algorithm is 98.3%, 97.5%, 94.8% and 96%, respectively. The accuracy of the algorithm based on traditional hidden Markov models is 95.9%, 95.7%, 95.4% and 94.6%, respectively. It can be seen that the accuracy of the algorithm designed has higher precision. The experiment proves that the map matching algorithms based on hidden Markov models is superior to other algorithms in terms of matching accuracy. This study makes the processing of traffic trajectory data more accurate.

Data-Driven Insights Into Urban Intersections: Visual Analytics of High-Value Scene.

In this article, we propose TraVis, an interactive system that allows users to explore and analyze complex traffic trajectory data at urban intersections. Trajectory data contain a large amount of spatio-temporal information, and while previous studies have mainly focused on the macroscopic aspects of traffic flow, TraVis employs visualization methods to investigate and analyze microscopic traffic events (i.e., high-value scenes in trajectory data). TraVis contains a novel view design and provides multiple interaction modalities to offer users the most intuitive insights into high-value scenes. With this system, users can gain a better understanding of urban intersection traffic information, identify different types of high-value scenes, explore the reasons behind their occurrence, and gain deeper insights into urban intersection traffic. Through two case studies, we illustrate how to use the system and validate its effectiveness.

Traffic trajectory generation via conditional Generative Adversarial Networks for transportation Metaverse

The transportation Metaverse, by integrating real and virtual vehicular networks, brings significant benefits to the development of smart cities. However, the difficulty and high cost of conducting large-scale traffic and driving simulations in the transportation Metaverse via realistic data collection and fusion from the physical world directly result in the lack of spatial–temporal traffic data and privacy concerns, which significantly hinder the development of the transportation Metaverse. Hence, in these situations, it becomes essential to produce high-quality, large-scale trajectory data to support relevant applications. However, the deficiency of data-driven method is the heavy dependence on high-quality historical data. Prior knowledge can help reduce learning difficulties and overfitting problems with small amounts of data. In our study, we use a hybrid framework, the Travel Demand Conditioning Generative Adversarial Network (TD-GAN), which combines data-driven and knowledge-driven approaches to address the issue of traffic trajectory generation. First, we employ a conditional mechanism to incorporate prior knowledge of travel demand to reduce learning difficulties. Second, non-standard convolutional module and multi-headed self-attention module are developed to capture spatial–temporal correlations. The experimental results show that our model outperforms the baseline models.

Graph deep learning recognition of port ship behavior patterns from a network approach

The detection and recognition of ship mobile behavior patterns based on automatic identification system (AIS) data are crucial for ship navigation and maritime supervision. However, present methods, such as rule-based constraints and density clustering extraction, still suffer from restrictions imposed by artificial settings of parameters and thresholds. The lack of neighborhood context information in unstructured and serialized ship trajectory vector data makes it challenging to incorporate advanced methods such as deep learning for pattern learning. This study builds multiple semi-supervised deep learning graph neural network (GNN) models based on the message passing paradigm for recognizing ship mobile behavior patterns by constructing an AIS trajectory network and computing multi-order node features through Delaunay triangulation. It can get rid of the dependence on parameters of traditional rule-based and unsupervised learning methods. It also reduces the dependence on auxiliary information in trajectory qualitative by introducing multi-order node features. We conducted the experiments on cargo ship data from New York and Singapore to test our method. The model's classification accuracy is more than 99% for the New York dataset and more than 95% for the Singapore dataset. This method can be extended to other types of ships and traffic trajectory vector data with the excellent application potential of GNN in pattern recognition of vector mobile data. The code and experimental data are available at: https://github.com/destiny1103/DT-GNN.

How Has the Concept of Air Traffic Complexity Evolved? Review and Analysis of the State of the Art of Air Traffic Complexity

Air traffic complexity is an indicator that allows air traffic controllers to understand the airspace situation. Controllers need support tools to reduce their workload. For this reason, complexity is a parameter that is being studied more and more, as it makes it possible to know a large amount of information about air traffic. In this article, we perform a bibliometric analysis in the field of air traffic complexity. Through Web of Science (WoS), a collection of complexity-related articles from 2001 to 2022 is compiled. Subsequently, the bibliometric analysis itself is performed. Then, a summary of five main contributions is presented, identifying the strengths and weaknesses of the contributions, and thus the topic. The results of the bibliometric analysis show that future air traffic complexity indicators should consider aircraft trajectories but also take into account other aspects, such as regulations. In addition, future complexity indicators should introduce artificial intelligence predictions to foresee areas of conflict in airspace but taking into account the main limitations, such as uncertainty of the air traffic trajectories. This study helps in the study of complexity due to being able to know previous studies in a summarised form and being able to draw conclusions on future lines.

Spatiotemporal gated traffic trajectory simulation with semantic-aware graph learning

Traffic trajectories of various vehicles, bicycles and pedestrians can help understand the traffic dynamics in a fine-grained manner like traffic flow, traffic congestion and ride-hailing demand. The comprehensive usage of traffic trajectory data has not been fully investigated due to the prevalent privacy concerns and commercial limitations. The traffic trajectory simulation task has emerged to generate high-fidelity trajectories in demand for downstream tasks to fill the gap between the scarce trajectory data and the widespread applications. Previous state-of-the-art methods build the spatiotemporal dependencies of trajectories with Graph Neural Networks (GNNs) under generative adversarial training, yielding better yet unstable trajectory quality. We observe that the unsatisfied synthetic trajectories are caused by the insufficient spatiotemporal modeling of road networks and trajectory semantics. In this paper, we propose a novel SpatioTEmporal GAted (STEGA) framework equipped with semantic-aware graph learning for traffic trajectory simulation to enable the explicit modeling of spatiotemporal dependencies throughout the learning pipeline. On the one hand, STEGA employs a graph encoder with the semantics of road networks for the spatial points of a trajectory, together with a time encoder for the time points. On the other hand, STEGA devises two spatiotemporal gates with the semantic graphs for the predictions of the future trajectory. Boosted by the semantic-aware graph learning, the proposed STEGA outperforms the state-of-the-art counterparts consistently at both macro- and micro-level metrics on two datasets. Elaborate ablation studies and downstream tasks of the synthetic trajectories further demonstrate the superiority of STEGA. Our code is available at https://github.com/Star607/STEGA.

Optimization of isolated intersection signal timing and trajectory planning under mixed traffic environment: The flexible catalysis of connected and automated vehicles

With the development of connected and automated vehicles (CAVs) enables real-time interaction between intersection signals and vehicle trajectories. The full use of this technological breakthrough will help traffic managers improve the performance of intersections. Most previous research focuses on the 100% CAV environment and the single lateral or longitudinal optimization of CAVs. Based on the flexible characteristics of CAVs, this paper proposes that CAV is regarded as the catalyst of vehicle platoon in mixed traffic environment and considers the uncertainty of CAVs and CHVs’ interaction in the real-world, which can promote the generation of controllable platoon through the “catalytic” mode of cooperative, accelerated, or direct lane-changing, and cooperative or direct overtaking. Simultaneously, a two-stage optimization model of mixed traffic trajectory and signal timing is proposed. Stage I: Based on the predicted vehicle platoon information, a dynamic NEMA signal timing scheme without duplicate structures is generated to minimize vehicle delays. Stage II: Based on the timing scheme, the generation of controllable and stable platoon and vehicle trajectory optimization model are established to minimize vehicle emissions. Dynamic programming with NEMA signal groups as sub-states is designed to solve the proposed model. The performance of the proposed model under different scenarios is investigated through numerical experiments and compared with benchmark models. Results show that the proposed model will outperform the benchmark models regarding average vehicle delay and emission under more realistic traffic demands. The average vehicle delay can be reduced by 54.32% and 7.33%, and the average vehicle emissions can be reduced by 19.1% and 0.8%, respectively. Meanwhile, the sensitivity analysis of CAV market penetration shows that the proposed model can perform satisfactorily at 20% CAV market penetration. Notedly, with increased market penetration, the proposed model will obtain better performance.

Using Kolmogorov Entropy to Verify the Description Completeness of Traffic Dynamics of Highly Autonomous Driving

In this paper, we outline the analysis of a fully provable traffic system based on the Kolmogorov entropy. The completeness of the traffic node dynamics is realized in the form of a nonlinear dynamical model of the participating transport objects. The goal of this study is to determine the completeness of transport nodes based on the Kolmogorov entropy of the traffic trajectories of a node with an unspecified number of actors, like cars and pedestrians. The completeness of a highly autonomous driving detection system describing a traffic node could be realized if the entropy-based error-doubling time of the trajectories of the Euler–Lagrange equation interpreted at the transport junction is less than 1.3.

Interval reservoir computing: theory and case studies

The time series data in many applications, for example, wind power and vehicle trajectory, show significant uncertainty. Using a single prediction value of wind power as feedback information for wind turbine control or unit commitment is not enough since the uncertainty of the prediction is not described. This paper addresses the uncertainty issue in time series data forecasting by proposing the novel interval reservoir computing method. The proposed interval reservoir computing can capture the underlying evolution of the stochastic dynamical system for time series data using the recurrent neural network (RNN). On the other hand, by formulating a chance-constrained optimization problem, interval reservoir computing outputs a set of parameters in the RNN, which maps to an interval of prediction values. The capacity of the interval is the smallest one satisfying the condition that the probability of having a prediction inside the interval is lower than the required level. The scenario approach solves the formulated chance-constrained optimization problem. We implemented an experimental data-based validation to evaluate the proposed method. The validation results show that the proposed interval reservoir computing can give a tight interval of time series data forecasting values for wind power and traffic trajectory. In addition, the confidence probability over the feasibility goes to 1 very quickly as the sample number increases.

Visual Analysis Method for Traffic Trajectory with Dynamic Topic Movement Patterns Based on the Improved Markov Decision Process

The visual analysis of trajectory topics is helpful for mining potential trajectory patterns, but the traditional visual analysis method ignores the evolution of the temporal coherence of the topic. In this paper, a novel visual analysis method for dynamic topic analysis of traffic trajectory is proposed, which is used to explore and analyze the traffic trajectory topic and evolution. Firstly, the spatial information is integrated into trajectory words, calculating the dynamic trajectory topic model based on dynamic analysis modeling and, consequently, correlating the evolution of the trajectory topic between adjacent time slices. Secondly, in the trajectory topic, a representative trajectory sequence is generated to overcome the problem of the trajectory topic model not considering the word order, based on the improved Markov Decision Process. Subsequently, a set of meaningful visual codes is designed to analyze the trajectory topic and its evolution through the parallel window visual model from a spatial-temporal perspective. Finally, a case evaluation shows that the proposed method is effective in analyzing potential trajectory movement patterns.

Collaborative Scheduling Algorithm for Dependent Tasks based on Multi-Agent RL in VEC Environment

To address the problem of limited computing power of vehicles, Vehicle Edge Computing (VEC) allows vehicles to schedule tasks to edge nodes with sufficient resources. In this paper, we propose a multi-agent reinforcement learning (MARL) approach to solve the multi-task scheduling problem in a dynamic VEC environment. First, we model the cooperative scheduling problem of dependent tasks in the VEC environment, considering the task priority and edge node load balancing in the task scheduling process. We define the optimization objective as minimizing the task processing delay and find it is an NP-hard problem. Then, we design a distributed algorithm SCMA based on MARL. The algorithm enables vehicles to find the optimal scheduling strategy by cooperating and sharing resources with each other. Finally, we use SUMO to simulate the road network topology and generate vehicle traffic trajectories. We construct heterogeneous vehicular applications for simulation experiments using the DAG generator. Compared with existing algorithms, the simulation results validate the superiority of the SCMA algorithm.

Analisis Volume Lalu Lintas Pada Simpang Bersinyal Studi Kasus Persimpangan Jl. Rajawali – Jl. Hiu Putih Di Kota Palangka Raya

Crossroads are nodes in the road network where road segments meet and vehicle traffic trajectories intersect. At the intersection of Jl. Rajawali – Jl. Hiu Putih, traffic flow during peak hours will increase so it needs to be handled. The purpose of this study was to determine the traffic volume at the signalized intersection at Jl. Rajawali – Jl. Hiu Putih which will later be useful as information needed for the planning, design, management and operation phases of the road. The research method used is a direct survey in the field to obtain primary data in the form of road geometry, environmental conditions, and traffic volume. Secondary data is in the form of a map of field conditions around the intersection, and population data. Data collection was carried out for one week from Monday 05 September 2022 to Sunday 11 September 2022. The data taken was in the form of road width and the amount of traffic flow at each intersection. The research results obtained are the highest traffic volume at the intersection of four Jl. Rajawali – Jl. Hiu Putih is on Friday (north) approach of 256 lvu/hour, on Sunday (east) approach of 238 lvu/hour, on Monday (south) approach of 299 lvu/hour and on Thursday (west) approach of 142 lvu/hour. This data is used as an analysis to determine traffic volume. Data were analyzed using the Indonesian Road Capacity Guidelines (PKJI) 2014.

FedSTN: Graph Representation Driven Federated Learning for Edge Computing Enabled Urban Traffic Flow Prediction

Predicting traffic flow plays an important role in reducing traffic congestion and improving transportation efficiency for smart cities. Traffic Flow Prediction (TFP) in the smart city requires efficient models, highly reliable networks, and data privacy. As traffic data, traffic trajectory can be transformed into a graph representation, so as to mine the spatio-temporal information of the graph for TFP. However, most existing work adopt a central training mode where the privacy problem brought by the distributed traffic data is not considered. In this paper, we propose a Federated Deep Learning based on the Spatial-Temporal Long and Short-Term Networks (FedSTN) algorithm to predict traffic flow by utilizing observed historical traffic data. In FedSTN, each local TFP model deployed in an edge computing server includes three main components, namely Recurrent Long-term Capture Network (RLCN) module, Attentive Mechanism Federated Network (AMFN) module, and Semantic Capture Network (SCN) module. RLCN can capture the long-term spatial-temporal information in each area. AMFN shares short-term spatio-temporal hidden information when it trains its local TFP model by the additive homomorphic encryption approach based on Vertical Federated Learning (VFL). We employ SCN to capture semantic features such as irregular non-Euclidean connections and Point of Interest (POI). Compared with existing baselines, several simulations are conducted on practical data sets and the results prove the effectiveness of our algorithm.

Traj2Traj: A road network constrained spatiotemporal interpolation model for traffic trajectory restoration

AbstractIn transportation, the trajectory data generated by various mobile vehicles equipped with GPS modules are essential for traffic information mining. However, collecting trajectory data is susceptible to various factors, resulting in the lack and even error of the data. Missing trajectory data could not correctly reflect the actual situation and also affect the subsequent research work related to the trajectory. Although increasing efforts are paid to restore missing trajectory data, it still faces many challenges: (1) the difficulty of data restoration because traffic trajectories are unstructured spatiotemporal data and show complex patterns; and (2) the difficulty of improving trajectory restoration efficiency because traditional trajectory interpolation is computationally arduous. To address these issues, a novel road network constrained spatiotemporal interpolation model, namely Traj2Traj, is proposed in this work to restore the missing traffic trajectory data. The model is constructed with a seq2seq network and integrates a potential factor module to extend environmental factors. Significantly, the model uses a spatiotemporal attention mechanism with the road network constraint to mine the latent information in time and space dimensions from massive trajectory data. The Traj2Traj model completes the road‐level restoration according to the entire trajectory information. We present the first attempt to omit the map‐matching task when the trajectory is restored to solve the time‐consuming problem of map matching. Extensive experiments conducted on the provincial vehicle GPS data sets from April 2018 to June 2018 provided by the Fujian Provincial Department of Transportation show that the Traj2Traj model outperforms the state‐of‐the‐art models.

TraGCAN: Trajectory Prediction of Heterogeneous Traffic Agents in IoV Systems

As a core component of the Internet of Vehicles, reasoning about the trajectory of pedestrians or vehicles in complex road conditions plays a critical role in autonomous driving and socially aware robotic navigation. Most existing methods do not adequately consider the effects of heterogeneous traffic agents. Toward this end, we propose the traffic trajectory prediction algorithm based on the convolutional attention network (TraGCAN) to predict the trajectories of heterogeneous traffic agents in dense traffic. The algorithm of the proposed method examines the behavior of different traffic agents in terms of both time and space dimensions to identify their movement patterns and interactions. We construct the spatial relationship of traffic agents as a graph structure and introduce a graph convolutional network to extract spatial interactions. In addition, we design a spatial attention mechanism to adaptively calculate weights for all spatial interactions to capture different influences from neighboring agents. To improve the accuracy of trajectory prediction, the algorithm considers the influence of the heterogeneous characteristics of traffic agents on their motion behaviors. We evaluated the performance of the proposed TraGCAN on heterogeneous traffic data sets, and the results demonstrate that the error of TraGCAN is reduced by 15% compared to existing methods.

Analysis of the construction of a port-storm mathematical model of a articulated two-link road train regarding the vertical storage

The article considers possible ways of development and improvement of a flat mathematical model of the movement of an articulated two-link road train considering the track and bringing this model to a spatial model that could consider the change in vertical loads and the subsequent change in the lateral deflection forces, which affect the indicators of turning and controllability of the articulated vehicle. This article proposes constructing a spatial mathematical model of a two-link road train considering the vertical component. The authors consider the problems associated with the movement of a two-track train over uneven terrain and height differences that may occur on the track. They consider the gravitational force's influence on the train's movement and develop a mathematical model that describes this process. The article presents mathematical equations describing the direction of a two-track train in three-dimensional space. They consider the mass of the train, traction forces, air resistance, gravitational force, and reactions from the ground. The authors use numerical methods to solve these equations and conduct computer simulations to study train motion under various conditions. The results of the study demonstrate that the vertical component significantly impacts the movement of a two-track train. It can affect the train's speed, energy efficiency, and stability. The authors conclude with the need to consider the vertical component when building mathematical models of double-track road trains. This paper is essential for researchers and engineers developing and designing road trains. Considering the vertical part will help improve the accuracy of mathematical models and increase the efficiency of two-track road trains in actual operating conditions. The obtained results are essential for developing and improving control systems for two-track road trains, particularly in transport, logistics, and mobile robots. The proposed model can be used to optimize the traffic trajectory and improve the efficiency and safety of the operation of road trains in natural conditions. The proposed model is designed for circular stationary and transient modes of movement of an articulated road train with the possibility of conducting a comparative analysis with a full-scale experiment. Keywords: spatial mathematical model, circular modes, vertical oscillations, articulated train.

A Calibrated Force-Based Model for Mixed Traffic Simulation.

Virtual traffic benefits a variety of applications, including video games, traffic engineering, autonomous driving, and virtual reality. To date, traffic visualization via different simulation models can reconstruct detailed traffic flows. However, each specific behavior of vehicles is always described by establishing an independent control model. Moreover, mutual interactions between vehicles and other road users are rarely modeled in existing simulators. An all-in-one simulator that considers the complex behaviors of all potential road users in a realistic urban environment is urgently needed. In this work, we propose a novel, extensible, and microscopic method to build heterogeneous traffic simulation using the force-based concept. This force-based approach can accurately replicate the sophisticated behaviors of various road users and their interactions in a simple and unified manner. We calibrate the model parameters using real-world traffic trajectory data. The effectiveness of this approach is demonstrated through many simulation experiments, as well as comparisons to real-world traffic data and popular microscopic simulators for traffic animation.

Complete trajectory extraction for moving targets in traffic scenes that considers multi-level semantic features

Complex traffic scenes are susceptible to the occlusion of moving targets and blurred target images, resulting in incomplete extraction of target trajectories within the field of view (FOV). To address this issue, we proposed a complete trajectory extraction algorithm for moving targets (TraEA) that considers the multi-level semantic features of traffic scenes following the FOV of single-camera surveillance videos. TraEA utilizes semantic information from the multi-level scene structure, such as image pixel features, geometric features, as well as temporal and spatial relationships between targets within each keyframe image. The semantic information helps extract and optimize the complete trajectory of a target, to assemble the target’s moving trajectory with improved integrity. An experiment with real-world traffic videos collected in Beijing, China validated the proposed algorithm and showed that TraEA improved the completeness, accuracy and robustness of target trajectory extraction. Traffic trajectories from the experiment can facilitate traffic supervision by analyzing the moving behaviors of individual targets. While the proposed TraEA algorithm is applicable to extract trajectories from videos in other domains, such as animal movements, potential privacy infringement and abusive applications warrant cautions of ethical considerations.

A Hybrid DNN Model for Travel Time Estimation from Spatio-Temporal Features

Due to recent advances in the Vehicular Internet of Things (VIoT), a large volume of traffic trajectory data has been generated. The trajectory data is highly unstructured and pre-processing it is a very cumbersome task, due to the complexity of the traffic data. However, the accuracy of traffic flow learning models depends on the quantity and quality of preprocessed data. Hence, there is a significant gap between the size and quality of benchmarked traffic datasets and the respective learning models. Additionally, generating a custom traffic dataset with required feature points in a constrained environment is very difficult. This research aims to harness the power of the deep learning hybrid model with datasets that have fewer feature points. Therefore, a hybrid deep learning model that extracts the optimal feature points from the existing dataset using a stacked autoencoder is presented. Handcrafted feature points are fed into the hybrid deep neural network to predict the travel path and travel time between two geographic points. The chengdu1 and chengdu2 standard reference datasets are used to realize our hypothesis of the evolution of a hybrid deep neural network with minimal feature points. The hybrid model includes the graph neural networks (GNN) and the residual networks (ResNet) preceded by the stacked autoencoder (SAE). This hybrid model simultaneously learns the temporal and spatial characteristics of the traffic data. Temporal feature points are optimally reduced using Stacked Autoencoder to improve the accuracy of the deep neural network. The proposed GNN + Resnet model performance was compared to models in the literature using root mean square error (RMSE) loss, mean absolute error (MAE) and mean absolute percentile error (MAPE). The proposed model was found to perform better by improving the travel time prediction loss on chengdu1 and chengdu2 datasets. An in-depth comprehension of the proposed GNN + Resnet model for predicting travel time during peak and off-peak periods is also presented. The model’s RMSE loss was improved up to 22.59% for peak hours traffic data and up to 11.05% for off-peak hours traffic data in the chengdu1 dataset.

Spatio‐temporal Keyframe Control of Traffic Simulation using Coarse‐to‐Fine Optimization

AbstractWe present a novel traffic trajectory editing method which uses spatio‐temporal keyframes to control vehicles during the simulation to generate desired traffic trajectories. By taking self‐motivation, path following and collision avoidance into account, the proposed force‐based traffic simulation framework updates vehicle's motions in both the Frenet coordinates and the Cartesian coordinates. With the way‐points from users, lane‐level navigation can be generated by reference path planning. With a given keyframe, the coarse‐to‐fine optimization is proposed to efficiently generate the plausible trajectory which can satisfy the spatio‐temporal constraints. At first, a directed state‐time graph constructed along the reference path is used to search for a coarse‐grained trajectory by mapping the keyframe as the goal. Then, using the information extracted from the coarse trajectory as initialization, adjoint‐based optimization is applied to generate a finer trajectory with smooth motions based on our force‐based simulation. We validate our method with extensive experiments.