Airspace Complexity Research Articles

Poster] Spatial modelling of midair collision risk using ADS-B data


 The airspace environment is a complex system that is only expected to continue increasing in complexity with the introduction of new types of air vehicles and operations, such as uncrewed aircraft, and the projected growth of air traffic volumes. This increase in complexity brings a need for investigating and developing new models of complex airspace environments to better understand their constituent parts. To address this need, this paper presents a methodology to create a geospatial model of complex airspace environments which can be used to study any geospatially distributed entity part of these environments. The methodology leverages Discrete Global Grid Systems (DGGS) for this purpose, a Geographic Information Systems framework previously utilized in geography and urban planning. The usefulness of the model is demonstrated on a case study geospatial entity which is the risk of midair collisions for many geospatially distributed points in an airspace region of interest. Since such a model needs to be able to work for any type of air vehicle and airspace region in a fully three-dimensional model that is capable of performing time varying analysis in a computationally efficient manner, a rudimentary midair collision risk model was also developed which satisfies these requirements. Air traffic data from the OpenSky Network was collected and integrated in the geospatial model and the midair collision risk model was used to calculate the risk of collisions for many geospatially distributed points in the airspace for four scenarios of ascending airspace complexity. The results from these four scenarios showed that the proposed methodology can be used to study the risk of midair collisions for different points in the airspace for any type of air vehicle and airspace region of interest in a fully three-dimensional model that is capable of performing time varying analysis in a computationally efficient manner.
 

A multi-objective memetic algorithm with adaptive local search for airspace complexity mitigation

Airspace complexity is a paramount safety metric to measure the difficulty and effort required to safely manage air traffic. The continuing growth in air traffic demand results in increasing airspace complexity and unprecedented safety concerns. Most existing methods treat the minimization of airspace complexity as the sole objective, ignoring the path deviation cost induced by the re-scheduled aircraft. In this paper, regarding reduction of airspace complexity and path deviation cost as two conflicting objectives, a multi-objective airspace complexity mitigation model is proposed to simultaneously ensure the safety and efficiency of air transport by optimizing flight trajectories. To effectively solve this multi-objective and non-linear optimization problem, a novel Memetic Algorithm with Adaptive Local Search (called MA-ALS) is developed. Specifically, we design a new crossover and three new local search operators under the flight trajectory representation. MA-ALS conducts exploration by crossover, and exploitation by a hill-climbing local search process. Moreover, we proposed an adaptive local search selection mechanism which facilitates the dynamic collaboration of different local search operators during evolution. A comprehensive comparison with the most recently developed algorithms on Chinese air traffic dataset is conducted. The Pareto front generated by the proposed algorithm dominates that of the compared baselines. Moreover, compared with a real flight schedule, the flight plan obtained by the proposed algorithm can significantly reduce the airspace complexity.

A quasi-dynamic air traffic assignment model for mitigating air traffic complexity and congestion for high-density UAM operations

In spite of the significant effects of COVID-19, UAM operations are still expected to grow smoothly and healthily in the near future. If such dense UAM traffic relies on tactical planning to resolve conflicts in a decentralized control scheme, urban airspace could soon be heavily congested and airspace complexity could be overwhelming. In this paper, we propose a Quasi-dynamic Air Traffic Assignment (QATA) model, which aims to allocate traffic flows among air routes in the planning horizon in order to organize UAM traffic flows and reduce air traffic congestion and complexity within a centralized strategic planning scheme while meeting the demand and respecting some criteria. Firstly, UAM traffics are modeled as flows that operate on a 3D two-way UAM route network. Next, the QATA problem is formulated as an optimization problem involving network dynamics to minimize the air traffic complexity evaluated by the linear dynamical system and congestion defined by traffic density and energy consumption. A simulation-based rolling horizon framework is introduced to decompose the QATA problem into several modified static air traffic assignment problems in each time interval. In order to overcome the limitations of conventional dynamic traffic assignment algorithms, a simulated annealing algorithm using parallel computing and a novel neighborhood generation strategy is proposed to efficiently optimize the problem. By applying the model to a pre-designed large-scale UAM route network in Singapore’s urban airspace, Experimental studies demonstrate the performance of the proposed framework and its applicability. Parallel computing can achieve up to three times faster than the original algorithm. The proposed algorithm significantly reduces the value of the objective function by (32.20±0.29)% in 143.47±3.74 seconds at the 95% confidence interval of 100 experiments, far better compared to the representative conventional dynamic traffic assignment algorithms. This study could be useful to assist air traffic control authorities and air navigation service providers in addressing various issues in unmanned traffic management.

Assuring Safe and Efficient Operation of UAV Using Explainable Machine Learning

The accurate estimation of airspace capacity in unmanned traffic management (UTM) operations is critical for a safe, efficient, and equitable allocation of airspace system resources. While conventional approaches for assessing airspace complexity certainly exist, these methods fail to capture true airspace capacity, since they fail to address several important variables (such as weather). Meanwhile, existing AI-based decision-support systems evince opacity and inexplicability, and this restricts their practical application. With these challenges in mind, the authors propose a tailored solution to the needs of demand and capacity management (DCM) services. This solution, by deploying a synthesized fuzzy rule-based model and deep learning will address the trade-off between explicability and performance. In doing so, it will generate an intelligent system that will be explicable and reasonably comprehensible. The results show that this advisory system will be able to indicate the most appropriate regions for unmanned aerial vehicle (UAVs) operation, and it will also increase UTM airspace availability by more than 23%. Moreover, the proposed system demonstrates a maximum capacity gain of 65% and a minimum safety gain of 35%, while possessing an explainability attribute of 70%. This will assist UTM authorities through more effective airspace capacity estimation and the formulation of new operational regulations and performance requirements.

A Spatiotemporal Hybrid Model for Airspace Complexity Prediction

Airspace complexity is a key indicator that reflects the safety of airspace operations in air traffic management systems. Furthermore, to achieve efficient air traffic control, it is necessary to accurately predict the airspace complexity. In this article, we propose a novel spatiotemporal hybrid deep learning model for airspace complexity prediction to efficiently capture spatial correlations as well as temporal dependencies pertaining to the airspace complexity data. Specifically, we apply convolutional networks to discover the short-term temporal patterns and skip long short-term memory networks to model the long-term temporal patterns of airspace complexity data. Furthermore, it is observed that the graph attention network in our proposed model, which emphasizes capturing the spatial correlations of the airspace sectors, can significantly improve the prediction accuracy. Extensive experiments are conducted on the real data of six airspace sectors in Southwest China. The experimental results show that our spatiotemporal deep learning approach is superior to state-of-the-art methods.

Conceptual Framework for Dynamic Optimal Airspace Configuration for Urban Air Mobility

In this work, a framework for optimizing the configuration of service areas in airspace into disparate partitions is demonstrated in the context of urban air mobility (UAM) operations. This framework is applied to a conceptual UAM airspace configuration, where a free-flight-based routing service and a corridor-based routing service are dynamically allocated to control different portions of the airspace over time, based on traffic demand. This allocation seeks to determine the least amount of structured coordination (in terms of active flight corridors) needed to safely meet traffic demand. This framework integrates several modeling components, including a novel spatiotemporal graph theoretic UAM traffic model capable of optimizing vehicle trajectories while maintaining multiple flight constraints. Airspace complexity and trajectory efficiency metrics are both implemented to quantify the overall safety and cumulative cost of routing a set of missions according to a given airspace configuration. Finally, spatial airspace partitions are managed using a support vector machine-based algorithm. Metrics are then applied to optimize the airspace configurations, according to desired objectives. Simulated results show that this framework can produce airspace configurations that ensure safety, while providing trajectory efficiency more effectively than purely uniform free-flight or corridor-based flight. This is demonstrated for both low- and high-density traffic scenarios.

Experimental validation of COMETA model of mental workload in air traffic control

The sustained increase in air traffic during the last decades represents a challenge to the air traffic management system in general. Thus, it is of utmost importance to develop strategies that can safely increase air traffic controller's handling capacity without increasing task related strain. This research proposes and validates a predictive model of air traffic controller's mental workload. Our model is based on COMETA, a model that considers the effect of the most relevant air traffic events in the cognitive complexity of the task. In the version of COMETA used in this study we include the online effects of the controllers' actions on the state of the airspace. To validate the model, a laboratory experiment was conducted using a simulator to precisely control the task workload factors. We used traffic density and airspace complexity as experimental factors because they are the most commonly acknowledged sources of mental workload in air traffic control literature. The measured dependent variables were selected because they have been found to correlate with mental workload in ATC tasks, namely, ISA and NASA indexes, electrodermal activity, heart rate, and different performance measures. The results demonstrate that our model can successfully predict air traffic controllers' mental workload across a wide range of task workload conditions. In addition, our results provide a clear portrait of the complex interactions between the different sources of task workload and their effects on mental workload. In the conclusion we consider the limitations and opportunities for the application of this model to improve policies.

Determination of Air Traffic Complexity Most Influential Parameters Based on Machine Learning Models

Today, aircraft demand is exceeding the capacity of the Air Traffic Control (ATC) system. As a result, airspace is becoming a very complex environment to control. The complexity of airspace is thus closely related to the workload of controllers and is a topic of great interest. The major concern is that variables that are related to complexity are currently recognised, but there is still a debate about how to define complexity. This paper attempts to define which variables determine airspace complexity. To do so, a novel methodology based on the use of machine learning models is used. In this way, it tries to overcome one of the main disadvantages of the current complexity models: the subjectivity of the models based on expert opinion. This study has determined that the main indicator that defines complexity is the number of aircraft in the sector, together with the occupancy of the traffic flows and the vertical distribution of aircraft. This research can help numerous studies on both air traffic complexity assessment and Air Traffic Controller (ATCO) workload studies. This model can also help to study the behaviour of air traffic and to verify that there is symmetry in structure and the origin of the complexity in the different ATC sectors. This would have a great benefit on ATM, as it would allow progress to be made in solving the existing capacity problem.

A Deep Unsupervised Learning Approach for Airspace Complexity Evaluation

Airspace complexity is a critical metric in current Air Traffic Management systems for indicating the security degree of airspace operations. Airspace complexity can be affected by many coupling factors in a complicated and nonlinear way, making it extremely difficult to be evaluated. In recent years, machine learning has been proved as a promising approach and achieved significant results in evaluating airspace complexity. However, existing machine learning based approaches require a large number of airspace operational data labeled by experts. Due to the high cost in labeling the operational data and the dynamical nature of the airspace operating environment, such data are often limited and may not be suitable for the changing airspace situation. In light of these, we propose a novel unsupervised learning approach for airspace complexity evaluation based on a deep neural network trained by unlabeled samples. We introduce a new loss function to better address the characteristics pertaining to airspace complexity data, including dimension coupling, category imbalance, and overlapped boundaries. Due to these characteristics, the generalization ability of existing unsupervised models is adversely impacted. The proposed approach is validated through extensive experiments based on the real-world data of six sectors in Southwestern China airspace. Experimental results show that our deep unsupervised model outperforms the state-of-the-art methods in terms of airspace complexity evaluation accuracy.

Toward Conflict Resolution with Deep Multi-Agent Reinforcement Learning

Safety in air traffic management at the tactical level is ensured by human controllers. Automatic detection and resolution tools are one way to assist controllers in their tasks. However, the majority of existing methods do not account for factors that can affect the quality and efficiency of resolutions. Furthermore, future challenges such as sustainability and the environmental impact of aviation must be tackled. In this work, we propose an innovative approach to pairwise conflict resolution, by modeling it as a multi-agent reinforcement learning to improve the quality of resolutions based on a combination of several factors. We use multi-agent deep deterministic policy gradient to generate resolution maneuvers. We propose a reward function that besides solving the conflicts attempts to optimize the resolutions in terms of time, fuel consumption, and airspace complexity. The models are evaluated on real traffic, with a data augmentation technique utilized to increase the variance of conflict geometries. We achieve promising results with a resolution rate of 93%, without the agents having any previous knowledge of the dynamics of the environment. Furthermore, the agents seem to be able to learn some desirable behaviors such as preferring small heading changes to solve conflicts in one time step. Nevertheless, the nonstationarity of the environment makes the learning procedure nontrivial. We argue ways that tangible qualities such as resolution rate and intangible qualities such as resolution acceptability and explainability can be improved.

Bayesian Spatio-Temporal grAph tRansformer network (B-STAR) for multi-aircraft trajectory prediction

Multi-Agent Trajectory Prediction is a critical and challenging component across different safety–critical engineering applications, e.g., autonomous driving and flight systems. Trajectory prediction tools are required for the next-generation air transportation system (NextGen). In practice, the prediction of aircraft trajectories needs to consider the impact of various sources, such as environmental conditions, pilot/controller behaviors, and potential conflicts with nearby aircraft. Huge uncertainties associated with these factors lead to the untrustworthiness of a deterministic trajectory prediction model. Moreover, the safety assurance in the near-terminal area is of specific interest due to the increased airspace complexity, where the instrument/visual flight rules are applied. In this work, we propose the Bayesian Spatio-Temporal grAph tRansformer (B-STAR) architecture to model the spatial and temporal relationship of multiple agents under uncertainties. It is shown that the proposed B-STAR achieves state-of-the-art performance on the ETH/UCY pedestrian dataset with UQ competence. Then, multi-aircraft near-terminal interactive trajectory prediction model is trained and validated with real-world flight recording data. The sensitivity study on the prediction/observation horizon and the graph neighboring distance threshold are performed. The code is available at https://github.com/ymlasu/para-atm-collection/tree/master/air-traffic-prediction/MultiAircraftTP.

Pilots’ willingness to operate in urban air mobility integrated airspace: a moderated mediation analysis

Interest in advanced air mobility (AAM) and urban air mobility (UAM) operations for on-demand passenger and cargo transport continues to grow. There is ongoing research on market demand and forecast, community acceptance, privacy, and security. There is also ongoing research by National Aeronautics and Space Administration , Federal Aviation Administration, academia, and industry on airspace integration, regulatory, process, and procedural challenges. Safe integration of UAM and AAM will also require different stakeholder perspectives such as air traffic controllers, manned aircraft pilots, remote pilots, UAM operators, and the community. This research aimed to assess the willingness of manned aircraft pilots to operate in UAM integrated airspace based on airspace complexity and UAM automation level. In addition, a moderated mediation analysis was conducted using trust and perceived risk as mediators and operator type as a moderating variable. The results indicated that automation level influenced pilots’ willingness to operate an aircraft in integrated airspace. A moderating effect of operation type on automation level and willingness to pilot an aircraft was also observed: professional pilots were more amenable to UAM operations with a pilot on board compared with remotely piloted operations. Results from the study are expected to inform airspace integration challenges, processes, and procedures for UAM integrated operations.

The evaluation of Istanbul airspace design from the perspective of complexity and safety

The approach, descent, and climb phases of flights in terminal maneuvering areas (TMAs) are some of the critical parts of a flight in which more than half of accidents happen. For an ANSP (Air Navigation Service Provider), to fulfill the responsibility with a high-quality service degree while maintaining safety, these difficult areas should be designed carefully and equipped with the most efficient procedures. Point merge system (PMS), which is defined as a systemized method for sequencing arrival flows, is launched in Istanbul's new TMA (LTFM TMA) being designed by DHMI (Devlet Hava Meydanları Isletmesi) to improve safety and efficiency. In this paper, the airspace complexity is based on adjusted density and structural index, and safety indicators. To investigate the effects of the radical changes made in re-organized LTFM TMA on the safety issue in comparison with the previous terminal maneuvering area, LTBA TMA, six months' data consisting of 75215 arrival and departure flights are used. Results reflect that the LTFM TMA, one of the world's busiest terminal airspaces, has statistically significantly lower scores in terms of conflict numbers per aircraft, complexity metrics, adjusted density, the hour of interactions, and flight hours than LTBA TMA. Lastly, there exists no longer a significant relationship between conflict types and complexity after launching the new design and structure.

Aircraft sequencing and scheduling in TMAs under wind direction uncertainties

ABSTRACTAircraft sequencing and scheduling within terminal airspaces has become more complicated due to increased air traffic demand and airspace complexity. A stochastic mixed-integer linear programming model is proposed to handle aircraft sequencing and scheduling problems using the simulated annealing algorithm. The proposed model allows for proper aircraft sequencing considering wind direction uncertainties, which are critical in the decision-making process. The proposed model aims to minimise total aircraft delay for a runway airport serving mixed operations. To test the stochastic model, an appropriate number of scenarios were generated for different air traffic demand rates. The results indicate that the stochastic model reduces the total aircraft delay considerably when compared with the deterministic approach.

Workload assessment of air traffic controllers

Air traffic controllers (ATCOs) are exposed to high workload even during routine operations. Their job carries a lot of responsibility and consists of complex tasks. In order to enhance high safety standards, a systematic evaluation of workload levels is required. This study explores an objective measurement of workload. Heart activity of ATCOs was monitored in order to indicate psychological status of ATCOs while being exposed to different levels of workload - in terms of changing traffic loads and airspace complexity. A standard method was used for the evaluation of heart activity. This method includes the frequency analysis in context of heart rate variability; time intervals of consecutive R waves in the heart activity record are assessed. The evaluation of the ratio of power in the low-frequency and high-frequency bands (indicator of sympathovagal balance) as well as parameters derived from fluctuation analysis were used. The results indicated that parameters of heart rate variability based on spectral analysis were significant in case of workload evaluation.

South East Common Sky Initiative Free Route Airspace - implementation aftermath

In a short period since South-East Axis Free Route Airspace (SEAFRA) and Slovenian Austrian Cross-Border Free Route Airspace (SAXFRA) were established, during 2018 these two Free Route Airspace (FRA) areas operationally merged into South East Common Sky Initiative Free Route Airspace (SECSI FRA). Nowadays, SECSI FRA represents a joint venture with the aim of sustainable future development of European Air Traffic Management (ATM). It’s a good example of regional cooperation since it includes stakeholders from six adjacent states and four Air Navigation Service Providers (ANSPs). Also, successful deployment of SECSI FRA have led to the creation of one of the largest areas with applicable FRA concept. Therefore, that represent a major step towards achieving a 2022 plan - implementation of FRA concept across whole Europe. This research aims to assess deployment effects of SEAFRA, SAXFRA and SECSI FRA and based on quantitative research it provides information on hypothetical question how did implementation of South East Common Sky Initiative Free Route Airspace (SECSI FRA), and its earlier versions - SEAFRA and SAXFRA, reflected on the performances at South East Axis in terms of airspace complexity. In addition, this research is based on the computation of real data obtained from Performance Review Unit (PRU) and it covers period from 2014 till end of 2018. Lastly, deployment impacts have been analysed and compared in relation to other European ATM network’s performances and presented throughout this research paper.

Relationship between air traffic demand, safety and complexity in high density airspace in Europe

Air traffic performance of the European air traffic system depends not only on traffic demand but also on airspace structure and its traffic distribution. These structural (airspace structure) and flow characteristics (factors such as traffic volume, climbing/descending traffic, mix of aircraft type, military area activity) influence airspace complexity, which can affect controller workload and influence the probability of safety occurrence. In other words, all these dynamic and static complexity components can potentially have an impact upon the safety of the air traffic management (ATM) system. Having in mind fluctuation in traffic on daily, seasonal or annual level in certain airspace, a few questions arise: How changes in traffic demand influence complexity and conflict risk? Is there any correlation between traffic demand, conflict risk and complexity? Are there any differences between seasons? For that purpose, an investigation is performed on FAB Europe Central (FABEC) airspace, based on two weeks of operated traffic during the summer and winter of 2017. Air traffic complexity is estimated using the EUROCONTROL complexity metrics, while conflict risk is assessed using the conflict risk assessment simulation tool. Results show that certain positive relationship exists between traffic demand, conflict risk and complexity.

Integer Programming–Based Airspace Sectorization for Terminal Maneuvering Areas with Convex Sectors

In this paper an airspace sectorization framework for terminal maneuvering areas based on mixed integer programming is presented. It incorporates an airspace complexity representation, as well as various constraints on the sectors’ geometry, for example, the requirement that points demanding increased attention from air traffic controllers should lie in the sector’s interior to allow for enough time to resolve possible conflicts. The method can enforce convex sectors. In contrast to earlier integer/constraint programming approaches, which used synthesis methods with variables per elementary airspace piece that were glued together to form sectors, the integer programming formulation uses a variable per potential edge on the sector boundary. It is also the first step toward an integrated design of routes, the resulting complexity, and a sectorization. This paper presents results for Stockholm Arlanda airport and compares the integer programming results to convex sectorizations obtained by enumerating all possible topologies for a given number of sectors. This yields a proof-of-concept for the application of this highly flexible approach to terminal maneuvering areas.

Sensitivity analysis of potential capacity and safety of flow corridor to self-separation parameters

ABSTRACTA flow corridor is a new class of trajectory-based airspace that encloses groups of flights which fly along the same path in one direction and accept responsibility for separation from each other. A well-designed corridor could reduce the airspace complexity, decrease the workload of air traffic controllers and increase the airspace capacity. This paper analyses the impact of different self-separation parameters on capacity and conflicts of the flow corridor. Both the quantitative impact and interaction effects of pairs of parameters are evaluated using the combined discrete-continuous model and Monte Carlo simulation method. The simulation results show that although the initial separation is the dominating factor, the interactions between initial separation and separation buffer, minimum separation, extra switch buffer, extra threshold buffer and velocity difference threshold also have some significant impacts on the capacity and conflicts for the flow corridor.

Assessment of the North European free route airspace deployment

Free Route Airspace is an operational concept for the modernization of the airspace, addressed to improving the efficiency of the flights. It also aims at the environmental friendly performance area by reducing the emissions from fuel burnt. But these benefits should not derive in a loss of safety. Several areas are introducing free route as part of the Single European Sky Airspace Research programme (SESAR). This paper assesses the Northern Europe Free Route Airspace deployment, where two SESAR solutions are combined: the Free Route Airspace and the Functional Airspace Blocks. This assessment is produced using fast-time simulations and presented from a safety perspective using two indicator sets: the aircraft loss of separation and the airspace complexity. The number of potential separation losses, together with complexity metrics, such as adjusted density, potential horizontal, vertical and/or speed interactions, are presented for different free route deployment status. Results reflect that from the safety perspective the free route deployment in North Europe did not present notable changes in terms of the selected indicators, despite of the increase of traffic of last years.