Simulated Air Traffic Control Research Articles

Operator selection for human-automation teaming: The role of manual task skill in predicting automation failure intervention

Humans working in modern work systems are increasingly required to supervise task automation. We examined whether manual aircraft conflict detection skill predicted participants’ ability to respond to conflict detection automation failures in simulated air traffic control. In a conflict discrimination task (to assess manual skill), participants determined whether pairs of aircraft were in conflict or not by judging their relative-arrival time at common intersection points. Then in a simulated air traffic control task, participants supervised automation which either partially or fully detected and resolved conflicts on their behalf. Automation supervision required participants to detect when automation may have failed and effectively intervene. When automation failed, participants who had better manual conflict detection skill were faster and more accurate to intervene. However, a substantial proportion of variance in failure intervention was not explained by manual conflict detection skill, potentially reflecting that future research should consider other cognitive skills underlying automation supervision.

A reinforcement learning approach to vehicle coordination for structured advanced air mobility

Advanced Air Mobility (AAM) has emerged as a pioneering concept designed to optimize the efficacy and ecological sustainability of air transportation. Its core objective is to provide highly automated air transportation services for passengers or cargo, operating at low altitudes within urban, suburban, and rural regions. AAM seeks to enhance the efficiency and environmental viability of the aviation sector by revolutionizing the way air travel is conducted. In a complex aviation environment, traffic management and control are essential technologies for safe and effective AAM operations. One of the most difficult obstacles in the envisioned AAM systems is vehicle coordination at merging points and intersections. The escalating demand for air mobility services, particularly within urban areas, poses significant complexities to the execution of such missions. In this study, we propose a novel multi-agent reinforcement learning (MARL) approach to efficiently manage high-density AAM operations in structured airspace. Our approach provides effective guidance to AAM vehicles, ensuring conflict avoidance, mitigating traffic congestion, reducing travel time, and maintaining safe separation. Specifically, intelligent learning-based algorithms are developed to provide speed guidance for each AAM vehicle, ensuring secure merging into air corridors and safe passage through intersections. To validate the effectiveness of our proposed model, we conduct training and evaluation using BlueSky, an open-source air traffic control simulation environment. Through the simulation of thousands of aircraft and the integration of real-world data, our study demonstrates the promising potential of MARL in enabling safe and efficient AAM operations. The simulation results validate the efficacy of our approach and its ability to achieve the desired outcomes.

Research on automatic pilot repetition generation method based on deep reinforcement learning.

Using computers to replace pilot seats in air traffic control (ATC) simulators is an effective way to improve controller training efficiency and reduce training costs. To achieve this, we propose a deep reinforcement learning model, RoBERTa-RL (RoBERTa with Reinforcement Learning), for generating pilot repetitions. RoBERTa-RL is based on the pre-trained language model RoBERTa and is optimized through transfer learning and reinforcement learning. Transfer learning is used to address the issue of scarce data in the ATC domain, while reinforcement learning algorithms are employed to optimize the RoBERTa model and overcome the limitations in model generalization caused by transfer learning. We selected a real-world area control dataset as the target task training and testing dataset, and a tower control dataset generated based on civil aviation radio land-air communication rules as the test dataset for evaluating model generalization. In terms of the ROUGE evaluation metrics, RoBERTa-RL achieved significant results on the area control dataset with ROUGE-1, ROUGE-2, and ROUGE-L scores of 0.9962, 0.992, and 0.996, respectively. On the tower control dataset, the scores were 0.982, 0.954, and 0.982, respectively. To overcome the limitations of ROUGE in this field, we conducted a detailed evaluation of the proposed model architecture using keyword-based evaluation criteria for the generated repetition instructions. This evaluation criterion calculates various keyword-based metrics based on the segmented results of the repetition instruction text. In the keyword-based evaluation criteria, the constructed model achieved an overall accuracy of 98.8% on the area control dataset and 81.8% on the tower control dataset. In terms of generalization, RoBERTa-RL improved accuracy by 56% compared to the model before improvement and achieved a 47.5% improvement compared to various comparative models. These results indicate that employing reinforcement learning strategies to enhance deep learning algorithms can effectively mitigate the issue of poor generalization in text generation tasks, and this approach holds promise for future application in other related domains.

Developing Air Traffic Control Simulator for Laboratory

The widely-used ATC simulator laboratory in air traffic control education lacks research on its development. This study aims to develop a computer-based aerodrome control tower simulator for ATC using the research and development method. The simulator offers a realistic training environment, covering simulation, technicalities, facilities, configuration, equipment, specifications, software, operations, and development. It is a crucial facility in ATC courses at Indonesian aviation universities. Findings demonstrate its effectiveness in enhancing student proficiency and reducing reliance on external suppliers. The resulting design concept, developed through research and development, can be utilized by local experts to promote advanced technology mastery and cost efficiency in ATC training systems. It provides opportunities for local experts and serves as a model for other countries, advancing ATC education.

Reducing the Costs of Automation Failure by Providing Voluntary Automation Checking Tools.

We investigated the extent to which a voluntary-use range and bearing line (RBL) tool improves return-to-manual performance when supervising high-degree conflict detection automation in simulated air traffic control. High-degree automation typically benefits routine performance and reduces workload, but can degrade return-to-manual performance if automation fails. We reasoned that providing a voluntary checking tool (RBL) would support automation failure detection, but also that automation induced complacency could extend to nonoptimal use of such tools. Participants were assigned to one of three conditions, where conflict detection was either performed: manually, with RBLs available to use (Manual + RBL), automatically with RBLs (Auto + RBL), or automatically without RBLs (Auto). Voluntary-use RBLs allowed participants to reliably check aircraft conflict status. Automation failed once. RBLs improved automation failure detection - with participants intervening faster and making fewer false alarms when provided RBLs compared to not (Auto + RBL vs Auto). However, a cost of high-degree automation remained, with participants slower to intervene to the automation failure than to an identical manual conflict event (Auto + RBL vs Manual + RBL). There was no difference in RBL engagement time between Auto + RBL and Manual + RBL conditions, suggesting participants noticed the conflict event at the same time. The cost of automation may have arisen from participants' reconciling which information to trust: the automation (which indicated no conflict and had been perfectly reliable prior to failing) or the RBL (which indicated a conflict). Providing a mechanism for checking the validity of high-degree automation may facilitate human supervision of automation.

Is it possible to evaluate the event-based taskload of an air traffic controller using an air traffic control simulator?

Air Traffic Controllers (ATCOs) perform safety-critical tasks and face a wide variety of demands to manage aircraft safely and efficiently. In order for these demands to not result in a degradation of their performance, they need to be within certain upper and lower limits. In the field of human factors in aviation, one option to establish these limits is to study neurophysiological variables related to human performance. The problem is that the study of these variables can only be done on the basis of an adequate taskload baseline, which allows to accurately define the situation of the scenario during the course of the experiment. Taskload is a measure that quantifies the difficulty a person encounters in completing a task. CRITERIA project (atC event-dRiven capacITy modEls foR aIr nAvigation) aims to establish capacity models and study neurophysiological variables against taskload distribution profiles based on ATC events that appear in real-time simulations. This study presents the methodology defined in CRITERIA to evaluate the taskload of ATCOs based on ATC events, as well as the analysis of the first results obtained from a set of real-time simulations of four exercises with six participants using SkySim simulator.

Return-to-Manual Performance can be Predicted Before Automation Fails.

This study aimed to examine operator state variables (workload, fatigue, and trust in automation) that may predict return-to-manual (RTM) performance when automation fails in simulated air traffic control. Prior research has largely focused on triggering adaptive automation based on reactive indicators of performance degradation or operator strain. A more direct and effective approach may be to proactively engage/disengage automation based on predicted operator RTM performance (conflict detection accuracy and response time), which requires analyses of within-person effects. Participants accepted and handed-off aircraft from their sector and were assisted by imperfect conflict detection/resolution automation. To avoid aircraft conflicts, participants were required to intervene when automation failed to detect a conflict. Participants periodically rated their workload, fatigue and trust in automation. For participants with the same or higher average trust than the sample average, an increase in their trust (relative to their own average) slowed their subsequent RTM response time. For participants with lower average fatigue than the sample average, an increase in their fatigue (relative to own average) improved their subsequent RTM response time. There was no effect of workload on RTM performance. RTM performance degraded as trust in automation increased relative to participants' own average, but only for individuals with average or high levels of trust. Study outcomes indicate a potential for future adaptive automation systems to detect vulnerable operator states in order to predict subsequent RTM performance decrements.

Recognising situation awareness associated with different workloads using EEG and eye-tracking features in air traffic control tasks

The rate of human errors would increase as air traffic control officers (ATCOs) lose situation awareness (SA), which could also be affected by their perceived workloads. Recognising ATCOs SA inadequacy is crucial for ensuring traffic safety. This paper aims to propose a two-phase analytical methodology for revealing SA-related neuro-physiological patterns and hierarchically recognising ATCOs SA loss with workload concerns using EEG and eye-tracking data. A simulated air traffic control (ATC) radar-monitoring experiment involving different task loads with SA-probe tests was first conducted to collect behavioural and physiological (EEG and eye-tracking) data simultaneously, and the NASA Task Load Index (NASA-TLX) scale was used to measure participants’ perceived workloads. In our two-phase methodology, behavioural data representing the task performance was analysed in Phase I using the Gaussian Mixture Model to determine sample’s SA, and the perceived workloads on samples were labelled using NASA-TLX scores. Subsequently, in order to achieve our purposes, the physiological data were annotated based on results from Phase I, the physiological feature base was extracted using a fast Fourier transformation and Hilbert transform in Phase II, and the linear discriminant analysis was then used to extract the core features as inputs to train multiple classifiers. Results showed that the neuro-physiological behaviours of SA loss during normal workloads differed from those in high workload situations. A leave-one-subject-out cross-validation was also performed, and the results demonstrated that the optimal performance was 76.1% for classifying high/low SA (1-Level classification) and 82.7% for recognising low SA associated with high workload (2-Level classification).

연속강하운용을 이용한 궤적 기반의 항공기 도착 관리 효과 분석 연구

In this study, we propose trajectory-based arrival management using CDO (Continuos Descent Operations). The operational procedures with TBO (Trajectory-Based Operations) concept were established to allow aircraft and ground system to share the trajectories with each other in real time. The proposed operational concept was validated in the air traffic control simulation environment, which consists of controller working position, pseudo pilot system, air traffic generation system, and controllers’ decision support system for arrival management using CDO. Simulation results compared with actual flight data indicate that proposed concept could improve the efficiency of traffic flow management in terms of total descending time and fuel consumption. And it was confirmed that if there is a system that can share and utilize the synchronized trajectory, it can be helpful to control arrival aircraft and apply CDO concept.

Plithogenic multi‐criteria decision making approach on airspace planning scheme evaluation based on ATC‐flight real‐time simulation

Airspace planning scheme evaluation based on ATC-Flight real-time simulation which incorporates air traffic control simulator and flight simulator has become increasingly important. It has irreplaceable advantages of truly simulating and in-depth evaluating airspace operation, especially for analyzing human factors. As a multi-criteria decision making (MCDM) problem, it poses challenges which this study aims to overcome from three aspects. Firstly, the complexity of airspace and the characteristics of ATC-Flight real-time simulation are analyzed to build a multi-criteria evaluation system. The criteria include air traffic flow, airspace operational performance, flight procedure quality, cost, controller workload and pilot workload. Secondly, a novel weighting method based on plithogenic set is presented to derive robust subjective criteria weights from a group of human decision makers. The subjective weights are then combined with objective weights using game theory to determine cumulative criteria weights. Thirdly, technique for order preference by similarity to ideal solution (TOPSIS) and grey correlation analysis are integrated to perform comprehensive evaluation and ranking. The first series of ATC-Flight real-time simulations in China are conducted to illustrate a case study. The results demonstrated that the proposed MCDM approach could improve the accuracy and discriminability of evaluation results, and outperformed other existing well-known MCDM algorithms.

The effect of multi‐tasking training on performance, situation awareness, and workload in simulated air traffic control

AbstractIncreasingly higher demands are being made on the capacity‐limited cognitive capabilities of human operators as they strive to maintain situation awareness (i.e., understanding “what is going on”) and performance in complex tasks. In the current study we asked whether: (a) training administered via a mobile phone‐based app could improve multitasking and (b) improved multitasking in the app would generalize to improved performance and situation awareness in a simulated air traffic control task (ATC). Participants completed the ATC task before and after multiple sessions of app‐based multitasking training or control training. Multitasking on the app improved across training sessions. However, this did not lead to improved performance or situation awareness, or workload reduction, relative to control training on the ATC task. These outcomes indicate that app‐based multitasking training based on repetition of a single training task will not necessarily yield generalizable benefits to human performance in other complex dynamic tasks.

The effect of linguistic intelligence and memory on air traffic control performance of field aviation polytechnic

Some research has been conducted to understand how general knowledge and short-term memory affect academic achievement. However, research that links these two predictors with air traffic control performance in a laboratory has not been found. Twenty-four ATC cadets participated in this research. This is associative research with multiple correlation analysis that aims to find the correlation between linguistic intelligence and short-term memory toward cadets’ air traffic control performance in Aerodrome Control Tower (TWR) Laboratory. The research instruments used are oral proficiency interview, Intelligence Structure Test (IST), and air traffic control simulation. Data obtained, then, are analyzed by using the product-moment method of correlation. The results show that there is a positive correlation among the three variables with the level of closeness that falls in the high category that can be seen from the correlation coefficient value. In fact, linguistic intelligence and short-term memory both contribute to air traffic control performance during simulations. These findings offer several implications for the training program to promote success in learning air traffic control, especially in the laboratory.

Exploring Effects of Ecological Visual Analytics Interfaces on Experts' and Novices' Decision‐Making Processes: A Case Study in Air Traffic Control

AbstractOperational demands in safety‐critical systems impose a risk of failure to the operators especially during urgent situations. Operators of safety‐critical systems learn to make decisions effectively throughout extensive training programs and many years of experience. In the domain of air traffic control, expensive training with high dropout rates calls for research to enhance novices' ability to detect and resolve conflicts in the airspace. While previous researchers have mostly focused on redesigning training instructions and programs, the current paper explores possible benefits of novel visual representations to improve novices' understanding of the situations as well as their decision‐making process. We conduct an experimental evaluation study testing two ecological visual analytics interfaces, developed in a previous study, as support systems to facilitate novice decision‐making. The main contribution of this paper is threefold. First, we describe the application of an ecological interface design approach to the development of two visual analytics interfaces. Second, we perform a human‐in‐the‐loop experiment with forty‐five novices within a simplified air traffic control simulation environment. Third, by performing an expert‐novice comparison we investigate the extent to which effects of the proposed interfaces can be attributed to the subjects' expertise. The results show that the proposed ecological visual analytics interfaces improved novices' understanding of the information about conflicts as well as their problem‐solving performance. Further, the results show that the beneficial effects of the proposed interfaces were more attributable to the visual representations than the users' expertise.

NeuroTracker Multiple Object Tracking Ability Predicts Novice Performance on a Simulated Air Traffic Control Task

ABSTRACT Objective To explore the utility of multiple object tracking (MOT) ability, measured using NeuroTracker, as a predictor of air traffic control (ATC) task performance. Background The perceptual-cognitive abilities required for MOT are also important for ATC performance. The current study provides a novel examination of NeuroTracker’s utility to predict novice performance on a simulated ATC task, relative to two discrete measures of working memory (WM). Method Forty-six participants completed computer-based assessments of MOT ability (NeuroTracker) and WM (Corsi Block Tapping, Automated Operation Span) followed by the simulated ATC task. Regression analyses were performed to determine the associations between ATC task performance and the MOT and WM measures. Results After controlling for age and video game playing, MOT ability significantly predicted more correct detections of conflicts between aircraft, fewer false alarm responses to conflicts, and faster aircraft acceptance and hand-off. When WM measures were included in regressions, MOT was a stronger predictor of performance than WM on those outcomes, and remained a statistically significant predictor of better conflict detection, false alarm response, and hand-off performance. Conclusion The findings demonstrate the relevance of MOT ability to ATC task performance and support the potential utility of NeuroTracker for controller applicant screening and selection. Research is required to validate the findings in larger and more representative samples under more realistic conditions.

Cognitive control strategies and adaptive performance in a complex work task.

Adapting to task changes in work settings frequently calls not only for shifting one's thoughts and behaviors to the new demands, but also for dealing with outdated knowledge and skills. This article focuses on the role of control strategies in task adaptation and reports two experimental studies using an air traffic control simulation task. In both studies (N = 66 and 105 with k = 1,320 and 1,680 observations, respectively), all participants first learned and performed an initial version of the task then received instruction about control strategies, performed an altered version of the task with new execution rules, and finally worked on a memory test. Participants were instructed to either deliberately forget the old rules, remember the old rules, or simply learn the new task (Study 2 only). Results from discontinuous growth curve modeling revealed that the directed forgetting in both studies and the control group in Study 2 showed higher performance in the simulation after the change relative to their performance before the change (transition adaptation). There were no relearning differences between the groups suggesting that these differences persisted throughout the task. However, the memory test at the end of the study revealed that the directed forgetting groups and the learning control group remembered less outdated task execution rules in the memory test after the simulation than the remembering group. The findings suggest that different types of cognitive strategies have costs and benefits. Conceptual and practical implications of these findings are discussed. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Lightweight Simulation of Air Traffic Control Using Simple Temporal Networks

Flight simulators are becoming more sophisticated and realistic, and the requirements of those using them are becoming more demanding. Air traffic control simulation for such simulators is now approaching the real problem of air traffic control, where several aircraft need to be scheduled for safe approach and landing or for safe passage through the air space that an air traffic controller is responsible for. Also, the computational resources available to dedicate to air traffic control simulation are sparse, given that most simulations focus on a realistic graphical user interface and aircraft physics modeling. We provide a formulation of the air traffic control problem and a solver for this problem that makes use of temporal constraint networks and simple geometric reasoning. We provide results showing that this approach is practical for realistic simulated problems.

Detecting a Single Automation Failure: The Impact of Expected (But Not Experienced) Automation Reliability.

Examine the impact of expected automation reliability on trust, workload, task disengagement, nonautomated task performance, and the detection of a single automation failure in simulated air traffic control. Prior research has focused on the impact of experienced automation reliability. However, many operational settings feature automation that is reliable to the extent that operators will seldom experience automation failures. Despite this, operators must remain aware of when automation is at greater risk of failing. Participants performed the task with or without conflict detection/resolution automation. Automation failed to detect/resolve one conflict (i.e., an automation miss). Expected reliability was manipulated via instructions such that the expected level of reliability was (a) constant or variable, and (b) the single automation failure occurred when expected reliability was high or low. Trust in automation increased with time on task prior to the automation failure. Trust was higher when expecting high relative to low reliability. Automation failure detection was improved when the failure occurred under low compared with high expected reliability. Subjective workload decreased with automation, but there was no improvement to nonautomated task performance. Automation increased perceived task disengagement. Both automation reliability expectations and task experience played a role in determining trust. Automation failure detection was improved when the failure occurred at a time it was expected to be more likely. Participants did not effectively allocate any spared capacity to nonautomated tasks. The outcomes are applicable because operators in field settings likely form contextual expectations regarding the reliability of automation.

Power law model for subjective mental workload and validation through air traffic control human-in-the-loop simulation

We provide evidence for a power law relationship between the subjective one-dimensional Instantaneous Self Assessment workload measure (five-level ISA-WL scale) and the radio communication of air traffic controllers (ATCOs) as an objective task load variable. It corresponds to Stevens’ classical psychophysics relationship between physical stimulus and subjective response, with characteristic power law exponent γ of the order of 1. The theoretical model was validated in a human-in-the loop air traffic control simulation experiment with traffic flow as environmental stimulus that correlates positively with ATCOs frequency and duration of radio calls (task load, RC-TL) and their reported ISA-WL. The theoretical predictions together with nonlinear regression-based model parameter estimates expand previously published results that quantified the formal logistic relationship between the subjective ISA measure and simulated air traffic flow (Fürstenau et al. in Theor Issues Ergon Sci 21(6): 684–708, 2020). The present analysis refers to a psychophysics approach to mental workload suggested by (Gopher and Braune in Hum Factors 26(5): 519–532, 1984) that was recently used by (Bachelder and Godfroy-Cooper in Pilot workload esimation: synthesis of spectral requirements analysis and Weber's law, SCL Tech, San Diego, 2019) for pilot workload estimation, with a corresponding power law exponent in the typical range of Stevens’ exponents. Based on the hypothesis of cognitive resource limitation, we derived the power law by combination of the two logistic models for ISA-WL and communication TL characteristics, respectively. Despite large inter-individual variance, the theoretically predicted logistic and power law parameter values exhibit surprisingly close agreement with the regression-based estimates (for averages across participants). Significant differences between logistic ISA-WL and RC-TL scaling parameters and the corresponding Stevens exponents as ratio of these parameters quantify the TL/WL dissociation with regard to traffic flow. The sensitivity with regard to work conditions of the logistic WL-scaling parameter as well as the power law exponent was revealed by traffic scenarios with a non-nominal event: WL sensitivity increased significantly for traffic flow larger than a critical value. Initial analysis of a simultaneously measured new neurophysiological (EEG) load index (dual frequency head maps, DFHM, (Radüntz in Front Physiol 8: 1–15, 2017)) provided evidence for the power law to be applicable to the DFHM load measure as well.

Development Of Air Traffic Control Simulator System Applied In Education And Training

Air traffic control simulation system has become familiar in developed countries. Moreover, in Vietnam, the demand for air traffic control systems is increasing due to the boom of the civil aviation industry. However, there is any research or development on this system. The Northern and Southern Flight Management Companies all import control simulation systems at a very high cost. Many other flight management companies also have a high demand for this system, including military units. This demand prompted the research team to find a solution to build an air traffic control simulation system in accordance with domestic training needs. Based on individual open source simulation software with some basic features, the team has successfully built an aerodrome control simulation system that recreates the visually appealing 3D visualization used in training of air traffic controllers.

Comparison of SAGAT and SPAM for Seeking Effective Way to Evaluate Situation Awareness and Workload During Air Traffic Control Task

Evaluation of air traffic controller’s situation awareness (SA) is becoming important for air traffic management with the growth of air traffic. This study compared two SA evaluation methods: Situation Awareness Global Assessment Technique (SAGAT) and Situation Present Assessment Method (SPAM) to understand how these techniques affect controllers’ predictability in different traffic density settings. Twenty students undertook simple air traffic control simulations by using both techniques. We investigated how these techniques affect their workload with Subjective Workload Assessment Technique (SWAT) and NASA-TLX. SWAT scores showed that high traffic density increased participants’ workload, and extra workload was posed right after answering SA queries. NASA-TLX scores were larger when SAGAT was used than when SPAM was used throughout the simulation. We found that the workload with SAGAT interferes with main tasks more than that of SPAM. The results of query scores suggested that SPAM is more predictive to the assessment of the controller’s SA.