As the years pass by, the technology around us is evolving day by day and even we have artificial intelligence on our smartphones or in our cars, aviation is lagging behind in this area. But what is AI?
Artificial intelligence (AI) is a wide-ranging branch of computer science concerned with building smart machines capable of performing tasks that typically require human intelligence. AI is an interdisciplinary science with multiple approaches, but advancements in machine learning and deep learning are creating a paradigm shift in virtually every sector of the tech industry.
In the early days of aviation, aircraft required the continuous attention of a pilot to fly safely. As aircraft range increased, allowing flights of many hours, the constant attention led to serious fatigue. An autopilot is designed to perform some of the tasks of the pilot. The first aircraft autopilot was developed by Sperry Corporation in 1912. The autopilot connected a gyroscopic heading indicator and attitude indicator to hydraulically operated elevators and rudder. It permitted the aircraft to fly straight and level on a compass course without a pilot’s attention, greatly reducing the pilot’s workload. Autopilot is not really artificial intelligence but is the first step towards computer-piloted aircraft.
Is the industry ready to implement AI airplanes? In some ways: yes! For example, Airbus is already using AI for observation tasks like computer vision, time series analysis, and natural language processing, predictions such as hybrid modeling, and decision making, Romaric Radeon, stated during the Global Symposium on the Implementation of Innovation in Aviation panel hosted by the ICAO on December 9, 2020.
Maybe a possible implementation of AI is what Diamond Aircraft proposes, cameras that will detect the runway and can land without the Instrument Landing System (ILS). Other applications could be autonomous taxing which could help for a better flow for ground operations.
Although it might take a while until we see AI implemented in aircraft because these systems may cause problems like the ones, we saw with the Boeing 737 MAX and its MCAS system. The major challenge of future AI systems in the cockpit is tackling these edge cases. These edge cases can be especially difficult to identify and understand due to the fact that they tend to be situations never before experienced. This can be a great challenge as AI models learn from data and are only as good as the data they get. The second challenge for AI autonomous aircraft is understanding and reviewing how automation affects pilot abilities. Until we achieve fully autonomous aircraft, humans and AI are going to share the cockpit. As seen in recent accidents, pilot abilities have been posited to have degraded dangerously low due to automation.
As the aviation industry and travel will grow in a post-pandemic world the demand for pilots will increase and AI can be a solution to the pilot shortage expected in the near future. Both Airbus and Boeing predict that about 500.000 new pilots would be needed by 2035. Airlines look at AI as a possible solution to this problem. UBS investment bank calculates that pilotless aircraft could save the airlines more than €30 billion and passengers could see a reduction of about 10% on fares. Airbus’s new A350 XWB has 50,000 sensors and collects daily about 2.5 terabytes of data. This huge amount of data has led manufacturers to believe in the possibility of introducing AI systems onboard. Also, NASA’s project Learn-To-Fly looks to develop software for real-time self-learning aircraft. The objective is for the aircraft to learn and develop its own aerodynamic model through data from its sensors rather than developing a fixed, predetermined one. Top universities around the globe are also conducting research to solve complex problems in aviation using AI, such as conflict avoidance, or even trying to learn by imitating a human pilot.
Other implementations of AI and Machine learning could be found in military aircraft that already have many sensors and systems onboard that helps the pilot to fly it at its maximum capability. Sixth generation fighters are planned to be introduced in the future and these aircraft can be game-changer because they can be only optional piloted and can be controlled by onboard-AI systems. Also, the drones that plenty of companies like Volocopter and Uber are talking about for some years now, will use AI to get us from one part of the city to another. Many applications of AI can be implemented in the airport terminal, for example in check-in and security areas.
Aviation always has been at the forefront of technological development but nowadays we can see that it’s not only hard but it can be dangerous to rush automated systems into new airplanes. AI will come on board firstly in military aircraft and drones but safety regulations and technology development for passenger aircraft will take a while. Until then, you will continue to enjoy when the pilot greets you onboard and communicates some reports about the weather at the destination as you fly at FL360.