Large-scale Trajectory Research Articles

A Distributed VMD-BiLSTM Model for Taxi Demand Forecasting with GPS Sensor Data.

With the ubiquitous deployment of mobile and sensor technologies in modes of transportation, taxis have become a significant component of public transportation. However, vacant taxis represent an important waste of transportation resources. Forecasting taxi demand within a short time achieves a supply-demand balance and reduces oil emissions. Although earlier studies have forwarded highly developed machine learning- and deep learning-based models to forecast taxicab demands, these models often face significant computational expenses and cannot effectively utilize large-scale trajectory sensor data. To address these challenges, in this paper, we propose a hybrid deep learning-based model for taxi demand prediction. In particular, the Variational Mode Decomposition (VMD) algorithm is integrated along with a Bidirectional Long Short-Term Memory (BiLSTM) model to perform the prediction process. The VMD algorithm is applied to decompose time series-aware traffic features into multiple sub-modes of different frequencies. After that, the BiLSTM method is utilized to predict time series data fed with the relevant demand features. To overcome the limitation of high computational expenses, the designed model is performed on the Spark distributed platform. The performance of the proposed model is tested using a real-world dataset, and it surpasses existing state-of-the-art predictive models in terms of accuracy, efficiency, and distributed performance. These findings provide insights for enhancing the efficiency of passenger search and increasing the profit of taxicabs.

Exploring the conflict risk characteristics of air weaving sections in Metroplex terminal areas with flight trajectory data and adaptive graph spatial-temporal transformer

Metroplex terminal areas is involved with numerous air weaving sections, where various types of arrival and departure traffic flows intersect or converge, leading to high-risk aircraft conflicts and inefficient Metroplex operation. The primary objective of this study is to explore the conflict risk characteristics of operational interactions between airports in Metroplex terminal areas with large-scale trajectory data, including risk evaluation, risk propagation and risk prediction. One complete month of ADS-B trajectory data is collected from a representative multi-airport system in Central and South China to illustrate the procedure. Specifically, flight trajectories are firstly clustered within Metroplex terminal areas, and a trajectory-tube model is then built to characterize the airport flows within the same cluster. Then, a clustering-based collision probability calculation method is proposed to evaluate the risk of air weaving sections. The spatial patterns of risks in air weaving sections reveal that operational interactions among Metroplex airports are quite different under various runway configurations. Furthermore, an adaptive graph spatial-temporal transformer (ASTT) network is developed to predict the future risk of each air weaving section in Metroplex terminal areas. The results indicate that the developed ASTT network can collaboratively encode the spatiotemporal characteristics in the air weaving section risk data, which achieves more accurate and robust prediction performance than other compared models during multiple look-ahead time steps. Moreover, the adaptive spatial graph technique designed in the ASTT can also reveal the hidden risk propagation effects among air weaving sections. The results of this study could provide insightful suggestions to air traffic authorities for developing effective coordination and conflict mitigation strategies, such as redesigning flight procedures, reallocating routes, and optimizing aircraft sequences to enhance the efficiency and safety of Metroplex operations.

ST-TrajGAN: A synthetic trajectory generation algorithm for privacy preservation

The rapid growth of large-scale trajectory data poses privacy risks for location-based services (LBS), primarily through centralized storage and processing of data, as well as insecure data transmission channels (such as the Internet and wireless networks), which can lead to unauthorized access or manipulation of users' location information by attackers. To enhance trajectory privacy protection while improving the trajectory utility, this paper proposes an efficient and secure deep learning model Semantic and Transformer-based Trajectory Generative Adversarial Networks (ST-TrajGAN) for trajectory data generation and publication. First, this article introduces a semantic trajectory encoding model for preprocessing trajectory points. Through this model, trajectory points can be transformed into vector representations with semantic information. Next, by learning the spatio-temporal and semantic features of real trajectory data, a deep learning model is used to generate synthetic trajectories with more uncertainty and practicality. Furthermore, a novel TrajLoss loss metric function was crafted to gauge the trajectory similarity loss within the trained deep learning model. Ultimately, the efficacy of the generated synthetic trajectories and the model's utility are assessed through Trajectory-User Linking (TUL) and Trajectory Sharing Percentage (TSP) values on three authentic Location-Based Services (LBS) datasets. Numerous experiments have shown that our method outperforms other methods in terms of privacy protection effectiveness and utility.

Non-Uniform Spatial Partitions and Optimized Trajectory Segments for Storage and Indexing of Massive GPS Trajectory Data

The presence of abundant spatio-temporal information based on the location of mobile objects in publicly accessible GPS mobile devices makes it crucial to collect, analyze, and mine such information. Therefore, it is necessary to index a large volume of trajectory data to facilitate efficient trajectory retrieval and access. It is difficult for existing indexing methods that primarily rely on data-driven indexing structures (such as R-Tree) or space-driven indexing structures (such as Quadtree) to support efficient analysis and computation of data based on spatio-temporal range queries as a service basis, especially when applied to massive trajectory data. In this study, we propose a massive GPS data storage and indexing method based on uneven spatial segmentation and trajectory optimization segmentation. Primarily, the method divides GPS trajectories in a large spatio-temporal data space into multiple MBR sequences by greedy algorithm. Then, a hybrid indexing model for segmented trajectories is constructed to form a global spatio-temporal segmentation scheme, called HHBITS index, to achieve hierarchical organization of trajectory data. Eventually, a spatio-temporal range query processing method is proposed based on this index. This paper implements and evaluates the index in MongoDB and compares it with two other spatio-temporal composite indexes for performing spatio-temporal range queries efficiently. The experimental results show that the method in this paper has high performance in responding to spatio-temporal queries on large-scale trajectory data.

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.

Improving Transferability for Cross-Domain Trajectory Prediction via Neural Stochastic Differential Equation

Multi-agent trajectory prediction is crucial for various practical applications, spurring the construction of many large-scale trajectory datasets, including vehicles and pedestrians. However, discrepancies exist among datasets due to external factors and data acquisition strategies. External factors include geographical differences and driving styles, while data acquisition strategies include data acquisition rate, history/prediction length, and detector/tracker error. Consequently, the proficient performance of models trained on large-scale datasets has limited transferability on other small-size datasets, bounding the utilization of existing large-scale datasets. To address this limitation, we propose a method based on continuous and stochastic representations of Neural Stochastic Differential Equations (NSDE) for alleviating discrepancies due to data acquisition strategy. We utilize the benefits of continuous representation for handling arbitrary time steps and the use of stochastic representation for handling detector/tracker errors. Additionally, we propose a dataset-specific diffusion network and its training framework to handle dataset-specific detection/tracking errors. The effectiveness of our method is validated against state-of-the-art trajectory prediction models on the popular benchmark datasets: nuScenes, Argoverse, Lyft, INTERACTION, and Waymo Open Motion Dataset (WOMD). Improvement in performance gain on various source and target dataset configurations shows the generalized competence of our approach in addressing cross-dataset discrepancies.

The Social Foundations of Academic Freedom: Heterogeneous Institutions in World Society, 1960 to 2022

This article analyzes academic freedom worldwide with newly available cross-national data. The literature principally addresses impingements on academic freedom arising from religion or repressive states. Academic freedom has broadly increased since 1945, but we see episodic reversals, including in recent years. Conventional work emphasizes the uniformity of international institutional structures and their influence on countries. We attend to the heterogeneity of international structures in world society and theorize how they contribute to ebbs and flows of academic freedom. Post-1945 liberal international institutions enshrined key rights and norms that bolstered academic freedom worldwide. Alongside them, however, illiberal alternatives coexisted. Cold War communism, for instance, anchored cultural frames that justified greater constraints on academia. We evaluate domestic and global arguments using regression models with country fixed effects for 155 countries from 1960 to 2022. Findings support conventional views: academic freedom is associated positively with democracy and negatively with state religiosity and militarism. We also find support for our argument regarding heterogeneous institutional structures in world society. Country linkages to liberal international institutions are positively associated with academic freedom. Illiberal international structures and organizations have the opposite effect. Heterogeneous institutions in world society, we contend, shape large-scale trajectories of academic freedom.

Evolutionary changes in the capacity for organismic autonomy.

Studies of macroevolution have revealed various trends in evolution - which have been documented and discussed. There is, however, no consensus on this topic. Since Darwin's time one presumption has persisted: that throughout evolution organisms increase their independence from and stability towards environmental influences. Although this principle has often been stated in the literature, it played no role in mainstream theory. In a closer examination, we studied this particular feature and described that many of the major transitions in animal evolution have been characterized by changes in the capacity for physiological regulation. Organisms gained in robustness, self-regulation, homeostasis and stabilized self-referential, intrinsic functions within their respective systems. This is associated with expanded environmental flexibility, such as new opportunities for movement and behaviour. Together, these aspects can be described as changes in the capacity for autonomy. There seems to be a large-scale trajectory in evolution during which some organisms gained in autonomy and flexibility. At the same time, adaptations to the environment emerged that were a prerequisite for survival. Apparently, evolution produced differential combinations of autonomy traits and adaptations. These processes are described as modifications in relative autonomy because numerous interconnections with the environment and dependencies upon it were retained. Also, it is not a linear trend, but rather an outcome of all the diverse processes which have been involved during evolutionary changes. Since the principle of regulation is a core element of physiology, the concept of autonomy is suitable to build a bridge from physiology to evolutionary research.

On-the-fly laser processing method with high efficiency for continuous large-scale trajectories

On-the-fly laser processing method with high efficiency for continuous large-scale trajectories

A framework for synthetic diagnostics using energetic-particle orbits in tokamaks

In fusion plasma physics, the large-scale trajectories of energetic particles in magnetic confinement devices are known as orbits. To effectively and efficiently be able to work with orbits, the Orbit Weight Computational Framework (OWCF) was developed. The OWCF constitutes a set of scripts, functions and applications capable of computing, visualizing and working with quantities related to fast-ion (FI) orbits in toroidally symmetric fusion devices. The current version is highly integrated with the DRESS code, which enables the OWCF to compute and analyze the orbit sensitivity for arbitrary neutron- and gamma-diagnostics. However, the framework is modular in the sense that any future codes (e.g. FIDASIM) can be easily integrated. The OWCF can also compute projected velocity spectra for FI orbits, which play a key role in many FI diagnostics. Via interactive applications, the OWCF can function both as a tool for investigative research but also for teaching. The OWCF will be used to analyze and simulate the diagnostic results of current and future fusion experiments such as ITER. The orbit weight functions computed with the OWCF can be used to reconstruct the FI distribution in terms of FI orbits from experimental measurements using tomographic inversion.

Large-scale stealth trajectory optimization based on hybrid A*-Gauss pseudospectral method

For airborne electronic countermeasures, a practical and feasible stealth trajectory with low observability significantly impacts mission success. However, for long-range and large-scale trajectory optimization problems, the significant increase in the state space size will affect the feasibility and optimality of the problem solution. This paper proposes a hybrid trajectory optimization method to address the above issues. First, the A* (A-star) algorithm and cubic B-spline curve fitting method are used to generate the corresponding waypoints in the predetermined grid map under the radar detection threat to satisfy the trajectory stealth effect at the macro level. Then, the optimal control model (OCP) with the shortest flight time is solved between the waypoints to obtain segmented trajectories. Finally, the above state-control variable sequences are further used to solve the optimal control problem of the micro-level stealth trajectory coupling the radar cross section (RCS) by Gauss pseudospectral method (GPM). The numerical simulation results validate the proposed hybrid optimization method.

Continuous Trajectory Generation Based on Two-Stage GAN

Simulating the human mobility and generating large-scale trajectories are of great use in many real-world applications, such as urban planning, epidemic spreading analysis, and geographic privacy protect. Although many previous works have studied the problem of trajectory generation, the continuity of the generated trajectories has been neglected, which makes these methods useless for practical urban simulation scenarios. To solve this problem, we propose a novel two-stage generative adversarial framework to generate the continuous trajectory on the road network, namely TS-TrajGen, which efficiently integrates prior domain knowledge of human mobility with model-free learning paradigm. Specifically, we build the generator under the human mobility hypothesis of the A* algorithm to learn the human mobility behavior. For the discriminator, we combine the sequential reward with the mobility yaw reward to enhance the effectiveness of the generator. Finally, we propose a novel two-stage generation process to overcome the weak point of the existing stochastic generation process. Extensive experiments on two real-world datasets and two case studies demonstrate that our framework yields significant improvements over the state-of-the-art methods.

PateGail: A Privacy-Preserving Mobility Trajectory Generator with Imitation Learning

Generating human mobility trajectories is of great importance to solve the lack of large-scale trajectory data in numerous applications, which is caused by privacy concerns. However, existing mobility trajectory generation methods still require real-world human trajectories centrally collected as the training data, where there exists an inescapable risk of privacy leakage. To overcome this limitation, in this paper, we propose PateGail, a privacy-preserving imitation learning model to generate mobility trajectories, which utilizes the powerful generative adversary imitation learning model to simulate the decision-making process of humans. Further, in order to protect user privacy, we train this model collectively based on decentralized mobility data stored in user devices, where personal discriminators are trained locally to distinguish and reward the real and generated human trajectories. In the training process, only the generated trajectories and their rewards obtained based on personal discriminators are shared between the server and devices, whose privacy is further preserved by our proposed perturbation mechanisms with theoretical proof to satisfy differential privacy. Further, to better model the human decision-making process, we propose a novel aggregation mechanism of the rewards obtained from personal discriminators. We theoretically prove that under the reward obtained based on the aggregation mechanism, our proposed model maximizes the lower bound of the discounted total rewards of users. Extensive experiments show that the trajectories generated by our model are able to resemble real-world trajectories in terms of five key statistical metrics, outperforming state-of-the-art algorithms by over 48.03%. Furthermore, we demonstrate that the synthetic trajectories are able to efficiently support practical applications, including mobility prediction and location recommendation.

Self-supervised contrastive representation learning for large-scale trajectories

Trajectory representation learning aims to embed trajectory sequences into fixed-length vector representations while preserving their original spatio-temporal feature proximity. Existing works either learn trajectory representations for specific mining tasks or fail to utilize large amounts of unlabeled trajectory data for representation learning. In this work, we propose a self-supervised Trajectory representation learning based on Reconstruction Contrastive Learning called TrajRCL. To be specific, TrajRCL first obtains low-distortion and high-fidelity views of trajectories through trajectory augmentation. Then, TrajRCL leverages a Transformer based encoder–decoder network to reconstruct low-distortion view trajectories to approximate high-fidelity trajectories. Self-supervised contrastive learning is finally used to enhance the consistency of the two view’s trajectory representations. Extensive experiments on two real-world demonstrate the superiority of our model over state-of-the-art baselines and significant efficiency on similarity trajectory search and k-NN query.

Large-scale trajectory prediction via relationship-aware adaptive hierarchical graph learning

Large-scale trajectory prediction via relationship-aware adaptive hierarchical graph learning

Collision risk quantification for pairs of recorded aircraft trajectories

AbstractComplex domestic airspace requires collision risk models and monitoring tools suitable for arbitrary aircraft trajectories. This paper presents a new mathematically based collision risk approach that extends the International Civil Aviation Organisation (ICAO) models to full aircraft encounters based on real trajectory data. A new continuous time intervention model is presented, along with a position uncertainty propagation model that better reflects aircraft behaviour and allows generalisation to all trajectories to eliminate degenerate cases. The proposed risk model is computationally efficient compared to the models it is based on and can be applied to large-scale trajectory data. The utility of the model is demonstrated through a series of case studies using real aircraft trajectories.

Mobility Inference on Long-Tailed Sparse Trajectory

Analyzing the urban trajectory in cities has become an important topic in data mining. How can we model the human mobility consisting of stay and travel states from the raw trajectory data? How can we infer these mobility states from a single user’s trajectory information? How can we further generalize the mobility inference to the real-world trajectory data that span multiple users and are sparsely sampled over time? In this article, based on formal and rigid definitions of the stay/travel mobility, we propose a single trajectory inference algorithm that utilizes a generic long-tailed sparsity pattern in the large-scale trajectory data. The algorithm guarantees a 100% precision in the stay/travel inference with a provable lower bound in the recall metric. Furthermore, we design a transformer-like deep learning architecture on the problem of mobility inference from multiple sparse trajectories. Several adaptations from the standard transformer network structure are introduced, including the singleton design to avoid the negative effect of sparse labels in the decoder side, the customized space-time embedding on features of location records, and the mask apparatus at the output side for loss function correction. Evaluations on three trajectory datasets of 40 million urban users validate the performance guarantees of the proposed inference algorithm and demonstrate the superiority of our deep learning model, in comparison to sequence learning methods in the literature. On extremely sparse trajectories, the deep learning model improves from the single trajectory inference algorithm with more than two times of overall and F1 accuracy. The model also generalizes to large-scale trajectory data from different sources with good scalability.

A Bounded Near-Bottom Cruise Trajectory Planning Algorithm for Underwater Vehicles

The trajectory planning algorithm of underwater vehicle near-bottom cruise is important to scientific investigation, industrial inspection, and military affairs. An autonomous underwater vehicle (AUV) often faces the problems of complex underwater environment and large cruise area in a real environment, and some robots must hide themselves during the cruise. However, to the best of our knowledge, few studies have focused on trajectory planning algorithms for AUVs with multiple constraints on large-scale maps. The currently used algorithms are not effective at solving length-constraint problems, and the mainstream trajectory planning algorithms for robots cannot be directly applied to the needs of underwater vehicle sailing near the bottom. Therefore, we present a bounded ridge-based trajectory planning algorithm (RA*) for an AUV to go on a near-bottom cruise. In the algorithm, we design a safety map based on a spherical structure to ensure the safe operation of the robot. In addressing the length-constraint problem and large-scale map planning problem, this paper proposes a two-stage framework for RA*, which designs map compression and parallel computation using a coarse-fine planning framework to solve the large-scale trajectory planning problem and uses a bounded search method to meet the trajectory planning requirements of length constraint. In this study, experiments based on the virtual ocean ridge are conducted, and the results validate the effectiveness and efficiency of the proposed RA* with MCPC algorithm framework.

PreCLN: Pretrained-based contrastive learning network for vehicle trajectory prediction

Trajectory prediction of vehicles is of great importance to various smart city applications ranging from transportation scheduling, vehicle navigation, to location-based advertisements. Existing methods all focus on modeling spatiotemporal relations with explicit contextual semantics from labeled trajectory data, and rarely consider the effective use of large amounts of available unlabeled trajectory data with the assistance of contrastive learning and pre-training techniques. To this end, we develop a novel Pretrained-based Contrastive Learning Network (PreCLN) for vehicle trajectory prediction. Specifically, we propose a dual-view trajectory contrastive learning framework to achieve self-supervised pre-training. A Transformer-based trajectory encoder is designed to effectively capture the long-term spatiotemporal dependencies in trajectories to embed input trajectories into fixed-length representation vectors. Moreover, three auxiliary pre-training tasks, i.e., trajectory imputation, trajectory destination prediction, and trajectory-user linking, are used to assist the training of PreCLN with the dual-view trajectory contrastive learning framework. After pre-training, the result trajectory encoder is used to generate trajectory representations for future trajectory prediction. Extensive experiments on two real-world large-scale trajectory datasets demonstrate the significant superiority of PreCLN against state-of-the-art trajectory prediction baselines in terms of all evaluation metrics.

Experiments and Analyses of Anonymization Mechanisms for Trajectory Data Publishing.

With the advancing of location-detection technologies and the increasing popularity of mobile phones and other location-aware devices, trajectory data is continuously growing. While large-scale trajectories provide opportunities for various applications, the locations in trajectories pose a threat to individual privacy. Recently, there has been an interesting debate on the reidentifiability of individuals in the Science magazine. The main finding of Sánchez et al. is exactly opposite to that of De Montjoye et al., which raises the first question: “what is the true situation of the privacy preservation for trajectories in terms of reidentification?” Furthermore, it is known that anonymization typically causes a decline of data utility, and anonymization mechanisms need to consider the trade-off between privacy and utility. This raises the second question: “what is the true situation of the utility of anonymized trajectories?” To answer these two questions, we conduct a systematic experimental study, using three real-life trajectory datasets, five existing anonymization mechanisms (i.e., identifier anonymization, grid-based anonymization, dummy trajectories, k-anonymity and ε-differential privacy), and two practical applications (i.e., travel time estimation and window range queries). Our findings reveal the true situation of the privacy preservation for trajectories in terms of reidentification and the true situation of the utility of anonymized trajectories, and essentially close the debate between De Montjoye et al. and Sánchez et al. To the best of our knowledge, this study is among the first systematic evaluation and analysis of anonymized trajectories on the individual privacy in terms of unicity and on the utility in terms of practical applications.Supplementary InformationThe online version contains supplementary material available at 10.1007/s11390-022-2409-x.