The introduction of machines to replace humans is growing steadily ever since the industrial revolution. The use of data-driven approach has led to the development of artificial intelligence and machine learning.
Popping out from computer science and data science as the third matryoshka doll is artificial intelligence. Artificial intelligence, or AI, encompasses the ability of machines to perform intelligent and cognitive tasks. Comparable to the way the Industrial Revolution gave birth to an era of machines that could simulate physical tasks, AI is driving the development of machines capable of simulating cognitive abilities.
Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it learn for themselves.
According to theBritish Broadcasting Company’s (BBC) interactive online resource. Will a robot take my job?, professions such as bar worker (77%), waiter (90%), chartered accountant (95%), receptionist (96%), and taxi driver (57%) each have a high chance of becoming automated by the year 2035.
Machine learning as a pilot support system
Humans are a part of the error chain. With the increased complexities of the air traffic, fatigue, automation, behavior etc., there is a need for a safe guard which can assist the pilots. With increased automation, the pilots arousal levels decrease. Its takes a while before the pilot catches up-to speed with the environment in the case of a situation requiring conflict resolution.
Pilot Support System utilizes big data analytics to provide improvements in a number of areas. For example, the data may be used to improve training, flight deck design, and help reduce the pilot’s cognitive workload.
The system identifies patterns during the various phases of flight (e.g., take-off, climb, cruise, descend, and landing). It will identify impairment, distraction, fatigue, or other pilot inhibiting events as well as pilot enabling events. If the system identifies significant events, it will trigger an advisory alert to the pilot. If the situation becomes more urgent, the advisory will be elevated to a caution and then a warning. These advisories, cautions, and warnings will help the pilot take proper actions. If the system determines both pilots are impaired or incapable, a warning will be sent to the air traffic controllers so they can take appropriate.
The pilot support system will collect and analyze large amounts of data, such as:
- Own-ship data
- Flight path information ATC communication
- Weather/environmental data surrounding the aircraft
- Terrain information
- Pilot feedback through controls
- GPS Pilots Data (e.g., age, gender, experience, education, levels of training, eye vision degradation levels, cultural background, etc.)
- Pilot interactions with flight deck systems
Other sensors may be used, such as gaze trackers and bio sensors, to collect data and maintain a safe flight environment. Additionally, the Pilot Support System utilizes big data analytics to provide improvements in a number of other areas. For example, the data may be used to improve training, flight deck design, and help reduce the pilot’s cognitive workload
Machines are learning how humans think, behave and take decisions. The reactions of the machines are filtered for the negative behavioural aspects of humans. Machines continue to learn and neural networks are being developed to replicate the human brain functions. The technology may not replace the human but will surely reduce the dependence of systems and processes on human beings.