Traffic Trajectory Research Articles

MPE: a mobility pattern embedding model for predicting next locations

The wide spread use of positioning and photographing devices gives rise to a deluge of traffic trajectory data (e.g., vehicle passage records and taxi trajectory data), with each record having at least three attributes: object ID, location ID, and time-stamp. In this paper, we propose a novel mobility pattern embedding model called MPE to shed the light on people's mobility patterns in traffic trajectory data from multiple aspects, including sequential, personal, and temporal factors. MPE has two salient features: (1) it is capable of casting various types of information (object, location and time) to an integrated low-dimensional latent space; (2) it considers the effect of ``phantom transitions'' arising from road networks in traffic trajectory data. This embedding model opens the door to a wide range of applications such as next location prediction and visualization. Experimental results on two real-world datasets show that MPE is effective and outperforms the state-of-the-art methods significantly in a variety of tasks.

GRAPH MODEL OF VEHICLE CONFLICT INTERACTION AT VARIOUS CROSSROADS

The paper introduces a new notion that is a graph of crossroad transport flows. It has been shown that the given graph serves as a unification of conflict graphs. The paper provides numerical characteristics of graphs on conflict interaction of transport flows in the process of their merging and intersection at crossroads of various configuration. The following construction of the graph has been carried out: merging graphs where their nodes correspond to conflicting flows and their edges indicate what flows enter into a merging conflict between themselves; intersection graphs where graph nodes correspond to conflicting flows and their edges indicate what flows enter into an intersection conflict between themselves. Taking into account the conflict interaction between traffic and pedestrian flows, traffic conditions and traffic trajectories before possible physical interaction the traffic flow graph takes such form which contains complete information about existing conflicts for the required intersection. As a result of the construction in accordance with theoretical aspects of a graph theory and actual interaction of transport and pedestrian flows at intersections, some regularities have been revealed that allow to estimate a danger of any particular intersection within the urban street-road network. The proposals can be identified as hazard markers of an object and that is especially topical with due account of available actual data on driving regimes, traffic light regulation, flow intensity and driving speed (especially single vehicles exceeding permissible driving speed for urban traffic or taking into account local restrictions on certain sections of street-road network) which form a vehicle or pedestrian graph. The proposed approaches can be used to assess quality of road traffic in conflict areas of the street-road network in cities and settlements and public roads as well.

Visual analysis of traffic data based on topic modeling (ChinaVis 2017)

The spatio-temporal urban movement patterns can be extracted from the massive trajectory data recorded by GPS devices. Effectively analyzing the massive and complex traffic data and then finding useful information hidden in such data constitute challenging yet meaningful research. By providing the interactive visual analysis of the underlying traffic patterns of the city, the results can guide the users in choosing ideal locations for setting up shops for business operations. We construct the topic model to analyze the GPS taxi trajectory data. The topic information is combined with the traffic volume information to choose the representative candidate areas. Then, traffic flow graphs are generated between candidate areas to show the distribution of such areas and the taxi running rules. We study the distribution and semantics of the topics from three aspects: time, space, and POIs (points of interest). Thus, we can enhance the user’s understanding of area characters by semantics. In addition, inspired by the wheels of vehicles, we design a metaphor-based glyph to summarize the multi-dimensional attributes of each candidate area. Users can explore the prospective areas’ multiple attributes over time through varied interactions to learn the details of the area from multiple perspectives. Finally, we design and implement a visual analysis prototype system of traffic trajectory data as well as verify the feasibility and validity of the system in the case study.

Exploring Human Mobility Patterns in Urban Scenarios: A Trajectory Data Perspective

Smart cities have been recognized as a promising research focus around the world. To realize smart cities, computation and utilization of big data are key factors. More specifically, exploring the patterns of human mobility based on large amounts of multi-source data plays an important role in analyzing the formation of social-economic phenomena in smart cities. However, our acquired knowledge is still very limited for smart cities. In this article, we propose an integrated computing method to rescale heterogeneous traffic trajectory data, which leverages MLE and BIC. Our analysis is based on two real datasets generated by subway smart card transactions and taxi GPS trajectories from Shanghai, China, which contain more than 451 million trading records by 14 subway lines and 34 billion GPS records by 13,695 taxis. Specifically, we quantitatively explore the patterns of human mobility on weekends and weekdays. Through logarithmic binning and data fitness, we calculate the Bayesian weights to select the best fitting distributions. In addition, we leverage three metrics to analyze the patterns of human mobility in two datasets: trip displacement, trip duration, and trip interval. We obtain several important human mobility patterns and discover quite a few interesting phenomena, which lay a solid foundation for future research.

Virtual traffic simulation with neural network learned mobility model

Virtual traffic simulation plays an important role in easing traffic congestion and reducing traffic pollution. As the transportation network expands, the former rule-based mobility models showed several limitations in producing convincing virtual vehicles. A more realistic model with example-based method is in demand. In this paper, a neural network is employed with carefully selected traffic trajectory data. The virtual vehicle production is driven by the proposed mobility model and organized by a specified structure. Then, the virtual traffic simulation could be given for an indicated scenario.

Advanced Trajectory Modeling: Stakeholder Needs and Expectations

Advanced air traffic control techniques require accurate predictions of aircraft trajectories. Such predictions rely on complex aircraft parameters which typically are unknown and must be estimated. These estimates can be improved with aircraft-to-ground data exchange methods. The Advanced Trajectory Modeling project is exploring such methods, and how they can improve the aircraft data available to the air traffic control trajectory models used by controller and traffic management decision support tools. The project has identified aircraft data, including current state and intent, which could be downlinked to ground automation systems. The project is exploring emerging technologies onboard the aircraft—such as Internet Protocol Data Link, Aircraft Interface Devices, and Electronic Flight Bags—that could be used to extract and downlink these data to ground automation systems. The project is evaluating advanced trajectory models to enable future synchronization of various ground automation trajectory models with aircraft-generated models to support Trajectory Based Operations, an effort that affects a wide range of stakeholders. Here we use a two-phase stakeholder engagement approach to insure the feasibility of the proposed concept.

Human Control of Air Traffic Trajectory Optimizer

Supervisory constraints are developed for a trajectory optimizer for air traffic. By choosing to apply combinations of these constraints, a human controller can exercise intuitive influence over how conflicts between aircraft are resolved. This offers a compromise between the flexibility of an automated optimizer and the insight of a human controller. Requirements, such as the sense of resolution,— i.e., which aircraft goes first or over—are encoded as constraints on a mixed-integer linear program. Examples verify that the constraints work as expected and that the computation times required are reasonable.

The design of a cloud-based tracker platform based on system-of-systems service architecture

Devices embedded with position tracking facilities are now widely available, such as smartphones, smartwatches, vehicle location trackers, etc. However, data mining and advanced analytics are rarely bundled with these devices that limits their utility. In this paper, we present the design of a generic, programmable position tracking platform, namely CQtracker. In particular, this platform is incorporated with a cloud-based engine of advanced analytics. CQtracker is constructed based on a concept of system-of-systems service architecture to deliver data-system-as-a-service. It is designed for the consumption by a variety of spatio-temporal applications. Spatio-temporal data exhibit strong heterogeneous patterns, data sparseness and distribution skewness. Hence, they are difficult to analyze. CQtracker reveals relationships and structures from these data by self-regularized time-varying dynamic Bayesian networks. In addition, a Bayesian parameter estimation approach is applied to an epidemic model for outbreak predictions. Sample applications are presented in this paper, in which CQtracker successfully reveals the evolution of time-varying structures from traffic trajectories.

Analysis and Modeling of Vehicle Following Behavior in Mixed Traffic Conditions

Abstract Car following models replicate the behaviour of a car following another car. In mixed traffic conditions, leader-follower vehicle types are not only car-car cases but also there are different combinations of vehicles (e.g., car-two wheeler and heavy vehicle-auto-rickshaw). Due to weak lane discipline, the follower is unable to strictly follow the lead vehicle. The other types of following behaviour like staggered following, following between vehicles, etc. are also observed under mixed traffic conditions. Depending on speed and position of vehicles in front, the subject vehicle may follow a leading vehicle with varying levels of lateral separation or stagger. The nature, extent and impact of such interactions need to be investigated for characterizing following behaviour under mixed traffic conditions. Hence, the present study focuses on analysis and modelling of vehicle following behaviour under mixed traffic conditions. The current study uses an open access mixed traffic trajectory data collected on an urban arterial road in Chennai city, India. The collected dataset includes 3005 vehicle trajectories with a total of 111,629 observations. To identify the different types of following behaviour, the extent of overlap (%) between leader-follower pair was used. The vehicle following behaviour was classified into three types: 1) Car Following 2) Staggered following and 3) Following between two vehicles. The vehicle following behaviour were analysed for different categories of vehicles and also, for different types of follower-leader pair. When the follower is a smaller size vehicle compared to a leader, it generally follows the leader. It was observed that when the vehicle size increases, staggered following behaviour of vehicle also increases. Subject vehicle chooses a following behaviour based on size of follower and leader, speeds of follower and leader, longitudinal gap between follower and leader, types of follower and leader. Multinomial Logistic Regression model was used to model the choices of vehicle following behaviour. This study has interesting implications in identifying vehicle-specific and vehicle following parameters for car following models to be adopted under mixed traffic and non-lane discipline traffic conditions.

Router Group selection using BAT Algorithm with Bayesian Filter (BABF): An Efficient Trajectory Error Detection

The most common factors of traffic trajectory monitoring in operational networks are Error prediction, computational time and communication overhead. These factors are most applicable to the Wide Area Network (WAN) such as MANETs (Mobile Ad-hoc Networks) including 3G, 4G and 5G networks. This larger network size affects the traffic trajectory monitoring factors, i.e., Larger the network size, Error prediction; computational time and communication overhead will be lesser. BAT Algorithm is a new meta-heuristic Swarm Intelligence based optimization algorithm, which has been developed rapidly and has been applied in different optimization issues in recent years. In this paper, heuristic BAT algorithm is deployed with Bayesian filter (BABF) based on Naive Bayes Algorithm. To prove that our proposal is a promising approximation method, router group selection is applied with techniques such as Trajectory Sampling, PSAMP, and Fatih for the performance analysis and results are obtained. The proposed methodology is compared with the default Heuristic Router Group Selection Algorithm to analyze the efficiency of the new approach. The analysis is implemented in the working platform of MATLAB.

Parsimonious shooting heuristic for trajectory design of connected automated traffic part II: Computational issues and optimization

Advanced connected and automated vehicle technologies enable us to modify driving behavior and control vehicle trajectories, which have been greatly constrained by human limits in existing manually-driven highway traffic. In order to maximize benefits from these technologies on highway traffic management, vehicle trajectories need to be not only controlled at the individual level but also coordinated collectively for a stream of traffic. As one of the pioneering attempts to highway traffic trajectory control, Part I of this study (Zhou et al., 2016) proposed a parsimonious shooting heuristic (SH) algorithm for constructing feasible trajectories for a stream of vehicles considering realistic constraints including vehicle kinematic limits, traffic arrival patterns, car-following safety, and signal operations. Based on the algorithmic and theoretical developments in the preceding paper, this paper proposes a holistic optimization framework for identifying a stream of vehicle trajectories that yield the optimum traffic performance measures on mobility, environment and safety. The computational complexity and mobility optimality of SH is theoretically analyzed, and verifies superior computational performance and high solution quality of SH. A numerical sub-gradient-based algorithm with SH as a subroutine (NG-SH) is proposed to simultaneously optimize travel time, a surrogate safety measure, and fuel consumption for a stream of vehicles on a signalized highway section. Numerical examples are conducted to illustrate computational and theoretical findings. They show that vehicle trajectories generated from NG-SH significantly outperform the benchmark case with all human drivers at all measures for all experimental scenarios. This study reveals a great potential of transformative trajectory optimization approaches in transportation engineering applications. It lays a solid foundation for developing holistic cooperative control strategies on a general transportation network with emerging technologies.

An agent-based model for queue formation of powered two-wheelers in heterogeneous traffic

This paper presents an agent-based model (ABM) for simulating the queue formation of powered two-wheelers (PTWs) in heterogeneous traffic at a signalized intersection. The main novelty is that the proposed interaction rule describing the position choice behavior of PTWs when queuing in heterogeneous traffic can capture the stochastic nature of the decision making process. The interaction rule is formulated as a multinomial logit model, which is calibrated by using a microscopic traffic trajectory dataset obtained from video footage. The ABM is validated against the survey data for the vehicular trajectory patterns, queuing patterns, queue lengths, and discharge rates. The results demonstrate that the proposed model is capable of replicating the observed queue formation process for heterogeneous traffic.

Estimating online vacancies in real-time road traffic monitoring with traffic sensor data stream

Real-time road traffic monitoring is widely considered to be a promising traffic management approach in urban environments. In the smart cities scenario, traffic trajectory sensor data streams are constantly produced in real time from probe vehicles, which include taxis and buses. By exploiting the mass sensor data streams, we can effectively predict and prevent traffic jams in a timely manner. However, there are two urgent challenges to processing the massive amounts of continuously generated trajectory sensor data: (1) the inhomogeneous sparseness in both spatial and temporal dimensions that is introduced by probe vehicles moving at their own will, and (2) processing stream data in real time manner with low latency. In this study, we aim to ameliorate the aforementioned two issues. We propose an online approach to addresses the major defect of inhomogeneous sparseness, which focuses on employing only real-time data rather than mining historical data. Furthermore, we set up a real-time system to process trajectory data with low latency. Our tests are performed using field test data sets derived from taxis in an urban environment; the results show that our proposed method lends validity and efficiency advantages for tackling the sparseness, and our real-time system is viable for low latency applications such as trafficmonitoring.

Prediction of traffic convective instability with spectral analysis of the Aw–Rascle–Zhang model

This article starts from the classical Aw–Rascle–Zhang (ARZ) model for freeway traffic and develops a spectral analysis of its linearized version. A counterpart to the Froude number in hydrodynamics is defined that enables a classification of the nature of vehicle traffic flow using the explicit solution resulting from the analysis. We prove that our linearization about an equilibrium is stable for congested regimes and unstable otherwise. NGSIM data for congested traffic trajectories is used so as to confront the linearized model's predictions to actual macroscopic behavior of traffic. The model is shown to achieve good accuracy for speed and flow. In particular, it accounts for the advection of oscillations on boundaries into the interior domain where the PDE under study is solved.

A Spatio-Temporal Simulation Model for Incremental Clustering in Massive Moving Objects Data Set

The real-world data process of large spatio-temporal data collection presents a very difficult technical problem. Firstly, the given process is very expensive, requiring a lot of various high-technology software instruments and modern hardware infrastructure (sensors, servers, GPS infrastructure etc.) installations; secondly, this process sometimes cannot show special traffic patterns, which we may characterize as patterned traffic trajectories. The Arena simulation framework introduced in this paper uses our suggested random linear interpolation algorithm and spatio-temporal prediction algorithm, which are applicable to visualize, handle and predict movement data with various time resolutions.

Visual Exploration of Sparse Traffic Trajectory Data.

In this paper, we present a visual analysis system to explore sparse traffic trajectory data recorded by transportation cells. Such data contains the movements of nearly all moving vehicles on the major roads of a city. Therefore it is very suitable for macro-traffic analysis. However, the vehicle movements are recorded only when they pass through the cells. The exact tracks between two consecutive cells are unknown. To deal with such uncertainties, we first design a local animation, showing the vehicle movements only in the vicinity of cells. Besides, we ignore the micro-behaviors of individual vehicles, and focus on the macro-traffic patterns. We apply existing trajectory aggregation techniques to the dataset, studying cell status pattern and inter-cell flow pattern. Beyond that, we propose to study the correlation between these two patterns with dynamic graph visualization techniques. It allows us to check how traffic congestion on one cell is correlated with traffic flows on neighbouring links, and with route selection in its neighbourhood. Case studies show the effectiveness of our system.

Sense and Avoid

This study explored the ability of operators to provide separation between three unmanned aircraft using basic cockpit traffic displays. Four groups of three general aviation, instrument-rated pilots flew cross-country flights controlling simulated twin-engine unmanned aircraft systems (UAS). They were required to maintain 2 nautical miles (nmi) horizontal and 500 ft vertical separation from all other aircraft. To examine the effect of two important safety factors, the flights were conducted with and without communication among the operators and with and without variable accuracy in the displayed traffic location due to degraded sensor quality. Twenty four different three-dimensional traffic conflict trajectories with three UASs, were repeated randomly for each of the four experimental conditions for each group. Of the 1152 aircraft encounters 12.8% were in violation of separation minimums. Eighteen of these were closer than 400 ft vertically or 1.6 nmi horizontally. The minimum separation of all aircraft pairs was 293 ft and 0.13 nmi. No difference in minimum separations was found due to the presence of communications, the variable accuracy of traffic position, or the participant group. The type and time of evasive maneuvers showed no effect when displayed horizontal position accuracy was variable. When operators were able to communicate and coordinate their maneuvers, the time to resolve the conflict was reduced. Participant groups varied significantly in: time of conflict resolution, frequency and type of maneuvers, control activity, reported amount of threat, confidence, satisfaction, and appraisal of the efficacy of their communications. The findings of this study serve as a benchmark for the development of sense and avoid procedures and minimum equipage standards for operating UASs in the airspace over the United States.

Assessing NextGen Operational Improvements: A Case of Airspace Complexity and Aircraft Arrival Management System

The Next Generation Air Transportation System (NextGen) supports multiple operational and technological improvements that enable efficiencies for users and service providers. One of the potential components of the NextGen - the Aircraft Arrival Management System (AAMS) is a tool that jointly optimizes timing of arriving traffic to streamline flight arrivals at congested airports. This study utilizes experimental settings to examine the AAMS effect on the terminal area airspace complexity. During the experiment, the air traffic trajectory data before and after the AAMS implementation were collected at two terminal areas: Charlotte Douglas International Airport (CLT) and Minneapolis-St. Paul International Airport (MSP). Then, the trajectory data were used to estimate the Reciprocal Square Metrics (RSM) airspace complexity measures that were compared between the baseline and active AAMS periods. The results of the study suggest that potential implementation of AAMS concepts could reduce terminal area complexity at congested airports.

Router group monitoring: making traffic trajectory error detection more efficient

Detecting errors in traffic trajectories (i.e., packet forwarding paths) is important to operational networks. Several different traffic monitoring algorithms such as Trajectory Sampling, PSAMP, and Fatih can be used for traffic trajectory error detection. However, a straight-forward application of these algorithms will incur the overhead of simultaneously monitoring all network interfaces in a network for the packets of interest. In this paper, we propose a novel technique called router group monitoring to improve the efficiency of trajectory error detection by only monitoring the periphery interfaces of a set of selected router groups. We analyze a large number of real network topologies and show that effective router groups with high trajectory error detection rates exist in all cases. However, for router group monitoring to be practical, those effective router groups must be identified efficiently. To this end, we develop an analytical model for quickly and accurately estimating the detection rates of different router groups. Based on this model, we propose an algorithm to select a set of router groups that can achieve complete error detection and low monitoring overhead. Finally, we show that the router group monitoring technique can significantly improve the efficiency of trajectory error detection based on Trajectory Sampling or Fatih.

Aviation emission inventory development and analysis

An up to date and accurate aviation emission inventory is a prerequisite for any detailed analysis of aviation emission impact on greenhouse gases and local air quality around airports. In this paper we present an aviation emission inventory using real time air traffic trajectory data. The reported inventory is in the form of a 4D database which provides resolution of 1° × 1° × 1000 ft for temporal and spatial emission analysis. The inventory is for an ongoing period of six months starting from October 2008 for Australian Airspace. In this study we show 6 months of data, with 492,936 flights (inbound, outbound and over flying). These flights used about 2515.83 kt of fuel and emitted 114.59 kt of HC, 200.95 kt of CO, 45.92 kt of NO x , 7929.89 kt of CO 2, and 2.11 kt of SO x . From the spatial analysis of emissions data, we found that the CO 2 concentration in some parts of Australia is much higher than other parts, especially in some major cities. The emission results also show that NO x emission of aviation may have a significant impact on the ozone layer in the upper troposphere, but not in the stratosphere. It is expected that with the availability of this real time aviation emission database, environmental analysts and aviation experts will have an indispensable source of information for making timely decisions regarding expansion of runways, building new airports, applying route charges based on environmentally congested airways, and restructuring air traffic flow to achieve sustainable air traffic growth.