Artificial Intelligence in Aviation and Human-Machine Interfaces

NB: We do not resell your papers. Upon ordering, we do an original paper exclusively for you.

NB: All your data is kept safe from the public.

Abstract

The intensive introduction of new and emerging technologies characterizes the current trend in the development of society. The following study analyzes the research results to determine the impact of artificial intelligence (AI) on aviation. As computerized capabilities continue to improve and become more widely available worldwide, their introduction into aviation is inevitable, highlighting the relevance of the work. The article also discusses ways to use AI in the aviation environment, for example, applications in aviation. Qualitative and quantitative analyzes allow a detailed study of the relationship between technological development and changes in aviation.

Proposal Summary

In the last decade, an urgent problem has been the question of the rational use of the achievements of scientific and technological progress in the field of complex systems based on artificial intelligence (AI). It is a field of science and engineering that deals with creating machines and computer programs that solve intellectual problems by modeling intelligent behavior. Solving problems of intelligent control in technical systems is an actively developing interdisciplinary research area. The relevance of intelligent systems lies in the need to reduce the human factors influence on the control object while maintaining a high level of safety and reliability during its technical operation (Asatiani et al., 2021). This problem is considered in the general context of the impact of new technologies on the aviation field: how is the implementation going, and what are the consequences of this?

The new world of air travel undoubtedly requires an innovative approach. Artificial intelligence technologies have changed the way people think about opportunities, and many companies are starting to prepare for an even more modern future today. Some US companies are already using artificial intelligence technologies in training future pilots. It launched a program called Pilot Training in the Future to find new ways to train pilots and use modern biometric systems, artificial intelligence technology, and virtual reality systems in their simulators (Svens, 2019). Such simulators can give an idea of the passage of real tests to provide the students with the correct concept of erroneous actions and teach them how to correct them (Cheung et al., 2022). By implementing artificial intelligence technologies, US companies have created a fast and efficient way for pilots to learn and practice, allowing them to train many pilots each year.

The appearance of the cockpit of modern aircraft has changed significantly. There has been a transition from disparate indicators of physical parameters to integrated multifunctional systems that inform the pilot about various states of the aircraft and the environment (Daniels et al., 2019). At the same time, not only 2D and 3D visual information is used, but also spatial sound and tactile interfaces that are new in aviation, allowing the design and implementation of new adaptive human-machine interface (HMI) concepts (Lim et al., 2018). Adaptive HMIs should increase pilot comfort levels and situational awareness, which should reduce crew members up to and including their total removal without adversely affecting flight safety.

Artificial intelligence (AI) is rapidly penetrating industrial automation, particularly as part of recommender systems and intelligent decision-making systems that advise human operators on managing complex technological systems. That qualitatively enhances human-machine control systems but also creates new challenges for ensuring the safety of workers and production assets (Piller & Nitsch, 2022). At the center of it is the problem of trust/distrust of the human operator in AI-based algorithms.

Incorporating artificial intelligence and autonomy into aviation may not be new, but it has a profound impact. Thus, it is necessary to analyze the problem, assuming previous studies. The work will use qualitative and quantitative research methods to achieve the goals. It is essential to carry out a meaningful interpretation of the results obtained and their discussion. The structure of the proposal will take into account each of the points presented.

Literature Review

In the development of onboard equipment, several stages were observed, each corresponding to the appearance of onboard complexes, determined by the technical capabilities and technological base characteristic of that time. The creation of cybernetic systems capable of performing creative functions traditionally considered mans prerogative has significantly increased productivity in many industries. Aviation is no exception: air travel has not yet become fully automated, but leading airlines and aircraft manufacturers are already investing in artificial intelligence. For example, a deep neural network is currently being developed for an airborne collision avoidance system that will replace its networks (DNNs) without the explicit rule foundation used to implement ACAS Xa (Katz et al., 2021). Instead, it offers a 40% improvement over the most recent iteration of Traffic collision avoidance systems (TCAS) and learns from millions of situations and 180,000 possible conflicts in everyday life (Pavel et al., 2022). Thus, introducing artificial intelligence into aviation will make it even safer.

Human Machine Interfaces

Artificial intelligence applications in aviation and human-machine interfaces include autonomy in air traffic control. Given the current low level of automation in ATM methods, it is unreasonable to assume that performance will be matched by a high degree of automation and increasing autonomy (Sabatini et al., 2020). The National Aeronautics and Astronomy Administration (NASA) asked the National Research Council (NRC) to study freedom of flight in 2013 (Chapman, 2020). Part of the study was establishing operating principles for compatibility between ground stations and aircraft with various automated vehicles. It was supposed to be implemented in addition to predicting the impact of AI systems and aircraft in regulated airspace at the network level.

Applications in Aviation

The Internet of Things is gaining momentum across all industries, but its impact on aviation could be revolutionary. IoT technology has many benefits, from ease of use to fast data collection. There are several exciting applications for IoT technology, from design to baggage claim. In aviation, satellite navigation has long been a complementary means of positioning (Dovis et al., 2020). The development of GNSS has provided an additional positioning service for many phases of flight, both for recreational and commercial air transport (Grote et al., 2022). Improvements and enhancements to satellite navigation through augmentation systems will help pilots through all stages of flight. It will include from taxiing to takeoff, en-route, and landing in all weather conditions, achieving the level of safety needed to handle the continuous flight increase (Zheng et al., 2019). When planning aircraft routes and landing schedules at busy airports, it is important to ensure that aircraft are always at a safe distance from each other. GNSS will provide a guaranteed service with sufficient accuracy so that airlines and pilots can know their location reliably and accurately enough to realize significant efficiency savings.

Implementation of AI in Aviation

A more difficult task is to solve aircraft control issues based on solid intelligence. Scientists and developers are sure that by 2030 a computer will be able to do this, and it will do it better than a person (Schlüter et al., 2022). Experts believe that equipping artificial intelligence with pre-formed rules will ensure the proper safety of passengers and crew of aircraft as well.

It should be noted that the crews presence determines a wide range of features and restrictions imposed on the process of liner control. A person is characterized by a low speed of perception, processing of information, reactions, insufficient reliability when performing monotonous functions, and more. At the same time, when solving flight problems, the crew interacts with onboard equipment in a complex, constantly changing tactical environment (Lim et al., 2018). It should be taken into account when using AI in air traffic participant management systems.

The main problem that hinders the introduction of AI in aviation, especially in civil aviation, is a large number of emergencies that cannot be foreseen and described in the algorithm. The transfer of a person to the status of an operator is dangerous because it is difficult to determine when to intervene (Golan et al., 2019). If artificial intelligence can do routine operations better than a person, then when faced with an emergency, a creative component is needed, which AI is deprived of (Golan et al., 2019). It is necessary to increase the number of sensors of information about the operation of systems in the air and on the ground to give artificial intelligence detailed data for making the right decision. It leads to additional high costs and, as a result, will significantly increase the price of infrastructure (Wamba-Taguimdje et al., 2020). In addition, the question of determining legal liability when a pilot (controller) is replaced by artificial intelligence remains open.

Thus, traditional methods can no longer guarantee an increase in the quality of control of complex objects since they do not consider all the uncertainties in which solutions must be sought. Therefore, the design of new aviation technology requires creating and implementing onboard software using knowledge processing methods using modern intelligent technologies.

Although many factors slow the introduction of AI into the process of controlling an airliner, among them a high degree of uncertainty in control processes, increased demands on flight safety, and economic feasibility, artificial intelligence has enormous potential in the aviation industry. Although introducing artificial intelligence is now at an early stage, some progress has already been made. Due to the high safety requirements in this area, it is necessary to carry out extensive tests and certifications. Many experts say that AI cannot be used on passenger aircraft until neural networks can make informed decisions and learn how to explain and justify their actions (Bird et al., 2020). Thus, one of the main reasons for the slow adoption of AI in aviation is time.

Objectives and Outcomes of the Study

This work aims to explore and thoroughly evaluate AI systems to determine the role of human and machine understanding in flight and its possible ramifications. The paper discusses how aviation safety can be improved through the development and use of technology. It is necessary to analyze AIs early recognizable proof and error detection and its components, including the Internet of Things and aviation applications. Thus, the goals of the paper are:

to analyze technological development in the field of aviation;
to assess the degree of implementation of artificial intelligence and its forms in the aviation environment;
to consider existing AI in aviation, including applications in aviation;
to study the impact of technological progress on aviation and human-machine interfaces;
to establish a link between the implementation of artificial intelligence and flight safety.

As a result of the study, the degree of AI implementation in aviation will be analyzed, taking into account the history of its development. Through a quantitative analysis, the level of current use of AI in aviation and how this affects aviation human-machine interfaces will be examined. In addition, the study will determine how safe the use of AI in the air is and whether it is possible to completely abandon human resources.

Interest of the Study and Research Questions

Todays technological environment is characterized by rapid and continuous development. Nanotechnologies, biometrics, computing power and speed, and learning technologies are becoming more popular, accessible, and constantly improving. Based on it, there is interest in conducting this study, which aims to examine the current state of AI in aviation. The commercial sector relies more on automation and technology to increase efficiency, security, and information transfer speed. New technologies open opportunities that require significantly less pilot or controller input. From here, the studys central questions are formed:

How does the development of technologies in the field of aviation happen?
Is it possible to completely abandon human participation in aircraft with AI?

Research Methods

The study was organized through a qualitative online survey, during which personal data, opinions, and the level of use of artificial intelligence technologies were determined. The author applied the judgment/target sampling method to obtain participants who can provide important data. In addition, various studies have been conducted to understand this studys implications. The Literature Review section of this dissertation explores the impact that the aviation industry could face if AI expands its capabilities. It also examines the extent to which artificial intelligence applications are applied in various sectors, such as manufacturing or the actual flight process.

The existing trends in the implementation of AI in aviation will be analyzed and compared. Based on a quantitative research approach, an empirical online experiment was conducted to study the impact of the introduction of AI on people, both employees, and passengers in civil aviation. The effect on the public of aviation security measures and their impact on flight intent, customer satisfaction, value for money, and perceived health risks were studied. The study found that airline safety measures are likely to impact expected customer satisfaction positively. At the same time, the direct impact of the safety measures by airlines does not reduce their perceived health risk but also increases their value for money.

The following paragraphs describe the methodology implemented to achieve the goals mentioned above and whose steps are related to the documents structure through successive sections. First, the paper analyzes airline organizational trends, challenges, and AI tools. A comprehensive review of the literature is underway, focusing on these topics, particularly those studies, including developing qualitative and quantitative (not only related to AI) models used for strategic decision-making and related financial objectives. In the case of describing airline trends concerning AI, a general introductory overview of the topic is first presented. It is followed by a deep dive highlighting the most critical aspects of each issue.

The air transport sector, having undergone significant changes in the use of technology, demonstrates both threats and opportunities for airlines. The study includes references to the effect caused by AI, both at the initial stages of implementation and later steps in the near future after establishing the new era. Bibliography and references are selected primarily based on a systematic search of the Google Scholar database, airline websites, and regulatory reports. Specific keywords were used for each topic, and the results were filtered by limiting papers to those within the field of air transport research.

Gantt Chart for a Study

Tasks	Date (since 2023)	January	February	March	April	May	June
Research proposal	January
Literature review	January-March
Data collection	January-February
Data analysis	February-March
First draft	April-May
Finale draft	June
Dissertation due	June

Reference List

Asatiani, A. et al. (2021) Sociotechnical envelopment of Artificial Intelligence: An approach to the organizational deployment of Inscrutable Artificial Intelligence Systems, Journal of the Association for Information Systems, 22(2), pp. 325352.

Bird, E. et al. (2020) The ethics of Artificial Intelligence: Issues and initiatives, European Parliament. Web.

Chapman, B. (2020) Congressional committee resources on space policy during the 115th congress (20172018): Providing context and insight into US government space policy, Space Policy, 51, p. 101359.

Cheung, J. et al. (2022) Using artificial intelligence to clear pilots for take-off, NATS. Web.

Daniels, T.S. et al. (2019) Regarding pilot usage of display technologies for improving awareness of aircraft system states, 2019 IEEE Aerospace Conference [Preprint].

Dovis, F. et al. (2020) Recent advancement on the use of Global Navigation Satellite System-based positioning for intelligent transport systems [guest editorial], IEEE Intelligent Transportation Systems Magazine, 12(3), pp. 69.

Golan, M., Cohen, Y. and Singer, G. (2019) A framework for the operator workstation interaction in industry 4.0, International Journal of Production Research, 58(8), pp. 24212432.

Grote, M. et al. (2022) Sharing airspace with Uncrewed Aerial Vehicles (UAVS): Views of the general aviation (GA) community, Journal of Air Transport Management, 102, p. 102218.

Katz, G. et al. (2021) Reluplex: A calculus for reasoning about Deep Neural Networks, Formal Methods in System Design [Preprint].

Lim, Y. et al. (2018) Avionics human-machine interfaces and interactions for manned and Unmanned Aircraft, Progress in Aerospace Sciences, 102, pp. 146.

Pavel, M.I., Tan, S.Y. and Abdullah, A. (2022) Vision-based autonomous vehicle systems based on Deep Learning: A Systematic Literature Review, Applied Sciences, 12(14), p. 6831.

Piller, F.T. and Nitsch, V. (2022) How Digital Shadows, new forms of human-machine collaboration, and data-driven business models are driving the future of industry 4.0: A Delphi study, Contributions to Management Science, pp. 131.

Sabatini, R. et al. (2020) Avionics Systems Panel Research and Innovation Perspectives, IEEE Aerospace and Electronic Systems Magazine, 35(12), pp. 5872.

Schlüter, U. et al. (2022) Exposure modelling in Europe: How to pave the road for the future as part of the European Exposure Science Strategy 20202030, Journal of Exposure Science & Environmental Epidemiology, 32(4), pp. 499512.

Svens, E. (2019) OSM Aviation Academy project funded by the European GNSS Agencys aviation grant program, OSM Aviation Academy. Web.

Wamba-Taguimdje, S.-L. et al. (2020) Influence of Artificial Intelligence (AI) on firm performance: The Business Value of AI-based transformation projects, Business Process Management Journal, 26(7), pp. 18931924.

Zheng, Y., Yang, Y. and Chen, W. (2019) New Imaging Algorithm for range resolution improvement in Passive Global Navigation Satellite systembased synthetic aperture radar, IET Radar, Sonar & Navigation, 13(12), pp. 21662173.

Click Here To Order Now!