Trajectory Data Research Articles

Assessing the collision risk of mixed lane-changing traffic in the urban inter-tunnel weaving section using extreme value theory

Urban inter-tunnel weaving (UIW) sections are characterized by short lengths and frequent lane-changing behaviors in the area, commonly used for fast through traffic. These features increase the likelihood of collisions, however, collision risk assessment in this area has been inadequate. The aim of this study was to evaluate the potential collision risk of urban inter-tunnel weaving (UIW) sections in mixed lane-changing traffic conditions in morning rush hours, utilizing surrogate safety measures. The investigation involved the collection of trajectory data via an unmanned aerial vehicle (UAV). Time to collision (TTC) and extended time to collision (ETTC) were chosen as surrogate safety indicators. The estimation of collision risk was conducted using Extreme Value Theory (EVT) by means ofsurrogate safety indicators. It was found that the threshold of TTC and ETTC in this area was 1.25 s. Furthermore, a comprehensive evaluation of collision risks associated with various vehicle types was performed, revealing an inverse relationship between thecollisions riskof vehicles in mixed traffic and their size. It was worth noting that while heavy vehicles exhibit a lower collision risk, they resulted in the highest energy loss and inflicted greater harm in the event of a collision. By an examination of the distribution features pertaining to conflict types during the operation of heavy vehicles, it showed that the highest likelihood of conflict with heavy vehicles occurred when adjacent lanes are involved. Consequently, the implementation of assisted driving technology for heavy vehicles was imperative in order to mitigate the risk associated with side collisions.

Travel Characteristics of Urban Residents Based on Taxi Trajectories in China: Beijing, Shanghai, Shenzhen, and Wuhan

With the advancement of urban modernization, more and more residents are flocking to large cities, leading to problems such as severe traffic congestion, uneven distribution of spatial resources, and deterioration of the urban environment. These challenges pose a serious threat to the coordinated development of cities. In order to better understand the travel behavior of metropolitan residents and provide valuable insights for urban planning, this study utilizes taxi trajectory data from the central areas of Beijing, Shanghai, Shenzhen, and Wuhan. First, the relationship between daytime taxi drop-off points and urban amenities is explored using Ordinary Least Squares (OLS). Subsequently, Geographically Weighted Regression (GWR) techniques were applied to identify spatial differences in these urban drivers. The results show that commonalities emerge across the four cities in the interaction between external transport stops and commercial areas. In addition, the average daily travel patterns of residents in these four cities show a trend of “three peaks and three valleys”, indicating the commonality of travel behavior. In summary, this study explores the travel characteristics of urban residents, which can help urban planners understand travel patterns more effectively. This is crucial for the strategic allocation of transport resources across regions, the promotion of sustainable urban transport, and the reduction in carbon emissions.

Sustainable impact analysis of freight pooling strategies on city crowdsourcing logistics platform

This study investigates the effects of freight pooling strategies on urban crowdsourcing logistics, focusing on economic, social, and environmental outcomes. Utilising a mixed-integer linear programming model with an adaptive large neighbourhood search algorithm, our goal is to optimise the cost-efficiency of the freight pooling system. Real-world delivery and driver trajectory data from a major Chinese crowdsourcing logistics platform, along with high-resolution vehicle telematics data, validate our model in five scenarios, each defined by distinct cost coefficients reflecting diverse stakeholder priorities. Results show potential for up to a 21.3% reduction in carbon emissions, a 28.3% decrease in truck activity spatial coverage, and a 7.6% increase in available drivers. However, deadheading trips, due to order consolidation into fewer vehicles without an increase in overall demand, could offset maximum carbon reduction benefits by 16.4%. Other effects on customers’ and drivers’ welfare are explored for a comprehensive quantitative assessment of freight pooling strategies’ sustainability benefits.

Visual Analysis of Epidemic Epidemiological Investigation Track Data

The visualization analysis of the flow data of the novel coronavirus pneumonia epidemic can intuitively show the development dynamics of the epidemic, explore the law of epidemic transmission, and provide a new way of thinking and method for the analysis of the epidemic situation. Firstly, the convection-modulated trajectory data is preprocessed, and then the convection-modulated data is theoretically transferred on the basis of expectation maximization statistics to realize multi-trajectory fusion algorithm, and finally the trajectory fitting of infected population is carried out. Finally, the multi-type thematic map is used to combine the flow data with the map system to realize the visualization of flow data and conduct in-depth analysis, so as to dig out the distribution characteristics of the flow data, provide a reference for the prevention and control of the novel coronavirus epidemic in a place, enable people to correctly understand the spread of the epidemic, and promote the development of preventive medicine.

Multi-ship encounter situation graph structure learning for ship collision avoidance based on AIS big data with spatio-temporal edge and node attention graph convolutional networks

With the increasing number of ships on the sea, the frequency multi-ship encounters situation was becoming more common than two-ship encounter. The complexity and risk of the navigation will exponentially increase with the more ships involved. Relying solely on the International Regulations for Preventing Collisions at Sea (COLREGS) (objective knowledge) was insufficient to handle the multi-ship intelligent collision avoidance problem, also needed the ship officer's good seamanship (subjective knowledge). In this study, we propose a methodology that combines subjective insights from AIS big data with objective analysis through multi-ship encounters recognition with graph convolutional networks (GCN). (1) The ship encounter 8-azimuths map was utilized to identify the two-ship encounter situation (25 types) from the AIS data. (2) Identify the multi-ship encounters trajectory data by cross-matching the two-ship encounter data. (3) To handle the intricate relationship information between the multiple ships which were transformed into a graph structure using graph theory. (4) Finally, a spatial-temporal edge and node attention graph convolutional network (ST-ENAGCN) was proposed with the graph convolutional unit and long short-term memory (LSTM) unit. The 2022 Ningbo Sea area AIS big data was utilized to achieve graph-structured learning regarding human experiences during the multi-ship encounters situation. The results indicate that the ST-ENAGCN model can understand the complex marine traffic situation to make the own ship collision avoidance decisions. This study contributes significantly to the increased efficiency and safety of sea operations in complex marine traffic conditions and support autonomous navigation of swarm of MASSs under the human-machine hybrid (HMH) conditions to better understand the collision avoidance intention of the ship officer in the multi-ship encounters situation.

MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components

Meta-Reinforcement Learning (Meta-RL) aims to reveal shared characteristics in dynamics and reward functions across diverse training tasks. This objective is achieved by meta-learning a policy that is conditioned on task representations with encoded trajectory data or context, thus allowing rapid adaptation to new tasks from a known task distribution. However, since the trajectory data generated by the policy may be biased, the task inference module tends to form spurious correlations between trajectory data and specific tasks, thereby leading to poor adaptation to new tasks. To address this issue, we propose the Meta-RL with task unCertAinty feedback through decoupled context-aware Reward and Dynamics components (MetaCARD). MetaCARD distinctly decouples the dynamics and rewards when inferring tasks and integrates task uncertainty feedback from policy evaluation into the task inference module. This design effectively reduces uncertainty in tasks with changes in dynamics or/and reward functions, thereby enabling accurate task identification and adaptation. The experiment results on both Meta-World and classical MuJoCo benchmarks show that MetaCARD significantly outperforms prevailing Meta-RL baselines, demonstrating its remarkable adaptation ability in sophisticated environments that involve changes in both reward functions and dynamics.

TAU: Trajectory Data Augmentation with Uncertainty for Next POI Recommendation

Next Point-of-Interest (POI) recommendation has been proven effective at utilizing sparse, intricate spatial-temporal trajectory data to recommend subsequent POIs to users. While existing methods commonly alleviate the problem of data sparsity by integrating spatial-temporal context information, POI category features, and social relationships, they largely overlook the fact that the trajectory sequences collected in the datasets are often incomplete. This oversight limits the model’s potential to fully leverage historical context. In light of this background, we propose Trajectory Data Augmentation with Uncertainty (TAU) for Next POI Recommendation. TAU is a general graph-based trajectory data augmentation method designed to complete user mobility patterns by marrying uncertainty estimation into the next POI recommendation task. More precisely, TAU taps into the global transition pattern graph to identify sets of intermediate nodes located between every pair of locations, effectively leveraging edge weights as transition probabilities. During trajectory sequence construction, TAU selectively prompts intermediate nodes, chosen based on their likelihood of occurrence as pseudo-labels, to establish comprehensive trajectory sequences. Furthermore, to gauge the certainty and impact of pseudo-labels on the target location, we introduce a novel confidence-aware calibration strategy using evidence deep learning (EDL) for improved performance and reliability. The experimental results clearly indicate that our TAU method achieves consistent performance improvements over existing techniques across two real-world datasets, verifying its effectiveness as the state-of-the-art approach to the task.

I-Rebalance: Personalized Vehicle Repositioning for Supply Demand Balance

Ride-hailing platforms have been facing the challenge of balancing demand and supply. Existing vehicle reposition techniques often treat drivers as homogeneous agents and relocate them deterministically, assuming compliance with the reposition. In this paper, we consider a more realistic and driver-centric scenario where drivers have unique cruising preferences and can decide whether to take the recommendation or not on their own. We propose i-Rebalance, a personalized vehicle reposition technique with deep reinforcement learning (DRL). i-Rebalance estimates drivers' decisions on accepting reposition recommendations through an on-field user study involving 99 real drivers. To optimize supply-demand balance and enhance preference satisfaction simultaneously, i-Rebalance has a sequential reposition strategy with dual DRL agents: Grid Agent to determine the reposition order of idle vehicles, and Vehicle Agent to provide personalized recommendations to each vehicle in the pre-defined order. This sequential learning strategy facilitates more effective policy training within a smaller action space compared to traditional joint-action methods. Evaluation of real-world trajectory data shows that i-Rebalance improves driver acceptance rate by 38.07% and total driver income by 9.97%.

Using Reinforcement Learning to Iteratively Construct Road Networks from Satellite Images and GPS Data

Constructing road networks manually is a time consuming and labor-intensive process. This paper proposes a new method to iteratively construct road networks using reinforcement learning from a combined tensor-based representation of satellite image and GPS trajectory data.

Learn How to See: Collaborative Embodied Learning for Object Detection and Camera Adjusting

Passive object detectors, trained on large-scale static datasets, often overlook the feedback from object detection to image acquisition. Embodied vision and active detection mitigate this issue by interacting with the environment. Nevertheless, the materialization of activeness hinges on resource-intensive data collection and annotation. To tackle these challenges, we propose a collaborative student-teacher framework. Technically, a replay buffer is built based on the trajectory data to encapsulate the relationship of state, action, and reward. In addition, the student network diverges from reinforcement learning by redefining sequential decision pathways using a GPT structure enriched with causal self-attention. Moreover, the teacher network establishes a subtle state-reward mapping based on adjacent benefit differences, providing reliable rewards for student adaptively self-tuning with the vast unlabeled replay buffer data. Additionally, an innovative yet straightforward benefit reference value is proposed within the teacher network, adding to its effectiveness and simplicity. Leveraging a flexible replay buffer and embodied collaboration between teacher and student, the framework learns to see before detection with shallower features and shorter inference steps. Experiments highlight significant advantages of our algorithm over state-of-the-art detectors. The code is released at https://github.com/lydonShen/STF.

Intersection movements delay modelling based on crowd-sensed global positioning system trajectory data

Developing accurate large-scale transportation models, used to guide policy adoption and evaluate infrastructure alternatives or changes in sociodemographic conditions, is data and resource intensive. This research proposes a novel method for modeling intersection movement delay using crowd-sensed Global Positioning System (GPS) data. This is achieved by providing a general definition of turning movements and extracting travel times thought GPS trajectory data analysis. Additionally, a straightforward method is proposed to integrate the observed delays per movement type into volume-delay functions. The spatial definition provided for turning movements captured distinct speed profiles per turn type. The significant differences in mean speeds for different turn types highlights the importance of integrating turn penalty functions based on real observations and underscore the importance of crowd-sensed GPS data. A simple technique is also proposed to integrate the proposed method into the volume-delay functions used in large scale transport models.

Exploring the changes of individuals’ travel behavior in response to COVID-19 and their influencing factors based on mobile phone data

IntroductionThe COVID-19 pandemic has produced a profound impact on travel behavior. Yet, few studies explored how individuals resist such impact to maintain their daily life from the perspective of people's responses. A comprehensive theoretical framework to elucidate individual travel behavior changes and a quantitative analysis of the pivotal factors driving these changes was lacking. MethodsThis study constructed a framework for individuals' travel behavior in response to COVID-19 and utilized anonymized mobile phone trajectory data before and during COVID-19 in Guangzhou to explore the changes of individuals’ travel behavior on workdays. Gradient boosting decision trees was used to quantify the degree of the factors driving travel changes. ResultsDuring the pandemic workdays, non-essential trips experienced a reduction of 51.4%, while essential trips decreased by 30.94%; Subway trips decreased by 1.63%, whereas motorized trips increased by 8.75%. The most significant decrease was observed in travel duration (50.92%), followed by travel frequency (41.28%), and travel distance (39.19%). The three travel indices displayed significant social disparities and spatial disparities. However, the relative relationships among these three travel indices did not vary with groups and spaces. Risk perception and intervention measures, emerged as primary drivers of individuals’ travel changes, contributing to 27%–35% of the total impact, while individual socio-economic characteristics and built environment accounting for less than 10%. ImplicationsThe results indicated that individuals curtailed both their essential and non-essential trips and adjusted their travel mode in response to the epidemic. These changes in travel purpose and mode led to differing reduction rates in travel frequency, duration, and distance. These findings contribute to individual travel changes prediction and fine-grained epidemic modelling during other public health emergencies like COVID-19.

Accelerated failure time modeling of in-lane street hawkers’ lane entry and exit behaviors at signalized intersections

In-lane street hawking is the intermittent entry of signalized intersections by traders to sell groceries to drivers and passengers. Studies have shown that hawkers get exposed to traffic injuries but the lack of quantitative analysis of their lane entry and exit behaviors in signalized intersections makes it difficult to improve traffic safety. This study analyzes the significant predictors of in-lane street hawkers’ (1) lane entry within 30 s after the red signal illumination, (2) lane exit within 30 s after the green signal illumination, and (3) probability of getting injuries during the green signal time. Drone-based trajectory data were collected from a selected signalized intersection in Accra, Ghana. A Weibull accelerated failure time duration model incorporating Gamma frailty was used to evaluate hawkers’ behaviors. Overall, the majority of hawkers exhibited red-light running behaviors exposing them to traffic injuries. An increase in traffic speed, especially beyond 20 km/h, exposed hawkers to injury risks significantly. Notably, hawkers’ lane entry decreased significantly as the traffic speed increased. Their lane exit duration was significantly predicted by the queue lengths and traffic volumes. Accordingly, safety practitioners can enhance traffic regulation and control methods in addition to pro-poor social interventions to demotivate hawking at signalized intersections.

An Adaptive Multimodal Data Vessel Trajectory Prediction Model Based on a Satellite Automatic Identification System and Environmental Data

Ship trajectory prediction is essential for ensuring safe route planning and to have advanced warning of the dangers at sea. With the development of deep learning, most of the current research has explored advanced prediction methods based on historical spatio-temporal Automatic Identification System (AIS) data. However, environmental factors such as sea wind and visibility also affect ship navigation in real-world maritime shipping. Therefore, developing reliable models utilizing multimodal data, such as AIS and environmental data, is challenging. In this research, we design an adaptive multimodal vessel trajectory data prediction model (termed AMD) based on satellite AIS and environmental data. The AMD model mainly consists of an AIS-based extraction network, an environmental-based extraction network, and a fusion block. In particular, this work considers multimodal data such as historical spatio-temporal information and environmental factors. Time stamps and distances are correlated with AIS and environmental data, and a multilayer perceptron and gated recurrent unit networks are used to design multimodal feature extraction networks. Finally, the fusion block realizes the fusion output of multimodal features to improve the reliability of the AMD model. Several quantitative and qualitative experiments are conducted using real-world AIS and multimodal environmental datasets. Numerous experimental results prove that prediction performance using multimodal data can ensure satisfactory accuracy and reliability while exhibiting a positive impact on improving maritime transport services.

TAT-HUM: Trajectory analysis toolkit for human movements in Python.

Human movement trajectories can reveal useful insights regarding the underlying mechanisms of human behaviors. Extracting information from movement trajectories, however, can be challenging because of their complex and dynamic nature. The current paper presents a Python toolkit developed to help users analyze and extract meaningful information from the trajectories of discrete rapid aiming movements executed by humans. This toolkit uses various open-source Python libraries, such as NumPy and SciPy, and offers a collection of common functionalities to analyze movement trajectory data. To ensure flexibility and ease of use, the toolkit offers two approaches: an automated approach that processes raw data and generates relevant measures automatically, and a manual approach that allows users to selectively use different functions based on their specific needs. A behavioral experiment based on the spatial cueing paradigm was conducted to illustrate how one can use this toolkit in practice. Readers are encouraged to access the publicly available data and relevant analysis scripts as an opportunity to learn about kinematic analysis for human movements.

A Comprehensive Investigation of Lane-Changing Risk Recognition Framework of Multi-Vehicle Type Considering Key Features Based on Vehicles’ Trajectory Data

To comprehensively investigate the key features of lane-changing (LC) risk for different vehicle types during left and right LC, and to improve the accuracy of LC risk recognition, this paper proposes a key feature selection and risk recognition model based on vehicle trajectory data. Based on a HighD high-precision vehicle trajectory dataset, the trajectory data of LC vehicles and surrounding vehicles of each vehicle type are extracted. SDI (stop distance index) and CI (crash index) are selected as surrogate indicators to calculate the risk exposure level (REL) and risk severity level (RSL). The K-means algorithm is used to cluster the REL and RSL to obtain the LC risk level, which is divided into three levels. The combination of basic features and interaction features of LC vehicles and surrounding vehicles with LC risk levels is constructed as the LC risk feature dataset. Based on the LightGBM (light gradient boosting machine) algorithm, the importance of features is sorted. Finally, a CNN-BiLSTM-Attention model is established to recognize the LC risk of each vehicle type during left and right LC. The results indicate that significant differences exist among different vehicle types and LC directions. Compared with CNNs (convolutional neural networks), LSTM (long short-term memory), and BiLSTM (bi-directional long short-term memory), CNN-BiLSTM-Attention performs best in recognizing the risk of LC in all cases. Moreover, the key feature groups that have the optimal result of recognizing the risk of LC in different cases are obtained.

Designing outdoor emergency rescue stations based on the spatiotemporal behavior of outdoor adventure tourists using GPS trajectory data

While outdoor travel has become an increasingly popular phenomenon, its high accident rate remains a significant concern. It is important to reasonably design emergency rescue stations based on the behavioral characteristics of outdoor adventure tourists. However, previous studies have mainly relied on static population information, which cannot capture adventure tourists’ spatiotemporal behaviors. To overcome this disadvantage, we obtained the GPS trajectory data of adventure tourists in Shenzhen from the “2bulu” platform, covering three types of travel groups: hiking, cycling, and driving. The seasonal characteristics, intra-day activities, and trajectory distributions of outdoor adventure tourists were analyzed. On this basis, we used a genetic algorithm to determine the optimal locations of rescue stations, taking into account both socioeconomic and natural conditions. The results show that outdoor adventure tourists have seasonal preferences, with the majority traveling during the summer and being most active between 5 and 9 a.m. The travel trajectories of these tourists exhibited a linear distribution pattern with several hotspots. In addition, the optimal rescue stations are mainly distributed at the junctions of districts, which can cover most outdoor scenic spots in Shenzhen. These findings could provide decision support for ensuring the safety of outdoor adventures.

Car-Following-Response-Based Vehicle Classification via Deep Learning

The driving characteristics of individual vehicles in the flow have been shown to influence the aggregate traffic flow characteristics. This is true both for individual human drivers as well as vehicles with some level of automation, such as adaptive cruise control (ACC). Knowledge of the individual constituents of the traffic flow will allow for more advanced traffic control strategies that are tailored to the individual vehicles and their respective driving characteristics. Therefore, there is a need to rapidly assess the car-following dynamics of individual vehicles and identify their level of automation based on their car-following trajectory. This study proposed a time-series based deep learning classification method to classify and identify human-driven and driver-assist vehicles in real-time from driving data. Powered by the recent advances in deep learning, we are able to identify individual vehicles in the flow using only car-following trajectory data and identify both ACC vehicles and human drivers. This article represents the first step toward assessing vehicle characteristics in real time. Furthermore, the proposed method can classify vehicles within a couple of seconds with high accuracy. Comparison with existing state-of-the-art methods shows the superior performance of the proposed method.

Real-Time UAV Trajectory Prediction for UTM Surveillance Using Machine Learning

The Unmanned Aerial System (UAS) Traffic Management (UTM) surveillance plays an important role in monitoring the safety compliance of UAV flights within specific operational zones. However, the quality of data reception from UAVs depends on transmission signal quality, leading to variable data latency during flights. As a means of addressing this issue and improving UAV operational safety, trajectory prediction emerges as a promising solution. This study aims to implement real-time trajectory prediction through the integration of machine learning techniques within the UTM surveillance system using Broadcast Remote ID. To facilitate this, a homemade receiver for broadcast Remote ID is developed using the ESP32 microcontroller. Subsequently, two distinctive flight tests are executed using a DJI Phantom 4 UAV. In the first flight, UAV trajectory data are used to serve as training input for the machine learning algorithms. The second flight focuses on the implementation of real-time trajectory prediction. The trajectory prediction model uses inputs such as latitude, longitude, height, speed, direction, latency time, and the Received Signal Strength Indicator (RSSI). Through an analysis of the first flight’s offline data, the Gated Recurrent Unit (GRU) algorithm is preferred to the Long Short-Term Memory (LSTM) algorithm. The outcomes of the second flight test prove the feasibility of the GRU-based trajectory prediction. The GRU model successfully produces real-time predictions during UAV flight, showcasing accuracy levels similar to those derived from offline prediction analyses with short processing time. This real-time trajectory prediction could improve the safety of UAV operation by providing the estimated position when the latency time is higher than the threshold.

Research and application of the global positioning system (GPS) clustering algorithm based on multilevel functions

With the rapid development and widespread adoption of wearable technology, a new type of lifelog data is being collected and used in numerous studies. We refer to these data as informative lifelog which usually contain GPS, images, videos, text, etc. GPS trajectory data in lifelogs is typically categorized into continuous and discrete trajectories. Finding a point of interest (POI) from discrete trajectories is a challenging task to do and has caught little attention so far. This paper suggests an LP-DBSCAN model for mining personal trajectories from discrete GPS trajectory data. It makes use of the hierarchical structure information implied in GPS trajectory data and it is suggested a variable-levels, variable-parameters clustering method (LP-DBSCAN) based on the DBSCAN algorithm to increase the precision of finding POI information. Finally, the Liu lifelog dataset is subjected to a systematic evaluation. In terms of GPS data that are not evenly distributed geographically, the experimental results demonstrated that the proposed algorithm could more accurately identify POI information and address the adverse effects caused by the global parameters of the traditional DBSCAN algorithm.