Why AI Won't Replace Air Traffic Controllers

Spread the love

After hours of normal operations, the air traffic controller receives a radio call from a small plane whose cockpit indicators cannot confirm that the plane's landing gear is extended for landing. The controller arranges for the pilot to fly down through the tower so the controller can visually inspect the aircraft's landing gear. Everything looks good. “Looks like your gear is down,” the controller told the pilot.

The controller calls the airport fire trucks to be ready and the plane lands safely again. Such scenarios happen regularly. In an air traffic control system, everything must meet the highest level of safety, but not everything goes according to plan.

Contrast this with the still science-fiction vision of future artificial intelligence “pilots” flying autonomous aircraft, complete with autonomous air traffic control systems that handle aircraft as easily as routers shuttling data packets over the Internet.

I am an aerospace engineer who led a Congressionally mandated National Academies study of air traffic controller personnel recruitment. Researchers are constantly working on new technologies that automate elements of the air traffic control system, but the technology can only perform the functions planned at the time of its design and cannot modify standard procedures. As illustrated in the above scenario, humans are likely to remain a necessary central factor in air traffic control for a long time to come.

What do air traffic controllers do?

The Federal Aviation Administration's basic guidance for the responsibility of air traffic controllers states: “The primary purpose of the air traffic control system is to prevent a collision involving an aircraft.” Air traffic controllers are charged with providing “safe, orderly and expeditious air traffic” and other services that support safety, including helping pilots avoid mountains and other hazardous terrain and hazardous weather.

The jobs of air traffic controllers vary. Tower controllers provide local control that clears planes to take off and land, ensuring they are safely separated. They also provide ground control, taxi planes and brief pilots on flight plans and potential safety issues on the day before the flight. Tower controllers are assisted by some displays but mostly look out from the towers and talk to the pilots by radio. At large airports operated by FAA controllers, surface surveillance displays show controllers aircraft and other vehicles on the ground at the airfield.

Approach and route controllers, on the other hand, sit in front of large displays in dark and quiet rooms. They communicate with the pilots by radio. Their displays show aircraft positions in map view with airspace boundaries and route highlights.

The 21 air traffic control centers in the US handle traffic between and above airports and thus typically fly at high speeds and altitudes.

Controllers at approach control facilities divert departing aircraft from local control into airspace after takeoff and en route. They similarly take incoming aircraft from the airspace, line them up with the landing approach and hand them over to the tower controllers.

A controller at each display manages all traffic in the sector. Sectors can vary in size from a few cubic miles, focusing on sequencing aircraft landing at a busy airport, to route sectors over 30,000 cubic miles (125,045 cubic km) in area and when fewer aircraft are flying. If a sector is busy, a second and third controller may assist, or the sector may be split in two, with another display and controller team manning the second.

How technology can help

Air traffic controllers have a stressful job and are subject to fatigue and information overload. Public concern about the growing number of close calls has focused on aging technology and staff shortages that have led to mandatory overtime for air traffic controllers. New technologies can help alleviate those problems.

Air traffic control system is incorporating new technologies in many ways. The FAA's NextGen Air Transportation System initiative is providing controllers with more and more accurate information.

The controllers' displays actually only showed radar tracking. They can now tap all the data they know about each aircraft into an automation modernization system along the way. The system integrates automatic position reports from aircraft via radar, automatic dependent surveillance-broadcast, weather reports, flight plans and flight histories.

The systems help to alert controllers of potential conflicts between aircraft or aircraft that are too close to elevated ground or structures, and provide instructions to controllers to maneuver aircraft into smooth traffic flows. Speaking to the US Senate on November 9, 2023 about airport security, FAA Chief Operating Officer Timothy Arrell said the administration is developing or improving several air traffic control systems.

Researchers use machine learning to analyze and predict aspects of air traffic and air traffic control, including air traffic flow between cities and air traffic controller behavior.

How technology complicates things

New technology will also bring about drastic changes in air traffic control in the form of new types of aircraft. For example, current regulations limit mostly unmanned aircraft to less than 400 feet (122 meters) above the ground and away from airports. These are drones used by first responders, news organizations, surveyors, delivery services and hobbyists.

However, some emerging unmanned aircraft companies are proposing to fly in controlled airspace. Some plan to have their aircraft fly normal flight paths and communicate normally with air traffic controllers via voice radio. These include Reliable Robotics and Xwing, which are separately working to automate the Cessna Caravan, a small cargo airplane.

Others are targeting new business models such as modern air mobility, small, highly automated electric aircraft – electric air taxis. These require dramatically different ways and procedures to manage air traffic.

Expect the unexpected

An air traffic controller's routine is interrupted by an aircraft requiring special handling. This can range from an emergency situation to medical flights or priority management of Air Force One. Controllers are given the responsibility and flexibility to adapt how their airspace is managed.

The front line needs of air traffic control are not well matched to AI capabilities. People expect air traffic to continue to be a complex, high-technology system that is safe. It achieves this standard by adhering to procedures when practical, something AI can do, and by adopting and exercising good judgment when something unplanned occurs or a new operation is implemented – a notable weakness of today's AI.

Indeed, when conditions are dire – when controllers figure out how to manage flights with serious problems due to safety issues or infrastructure failures, airport crises or extensive airspace closures – controllers' contribution to safety is greatest.

Also, controllers don't fly the plane. They communicate and interact with others to guide the flight, so their responsibility is primarily to work as part of a team – another significant weakness of AI.

As an engineer and designer, I'm excited about AI's ability to analyze big data records of past air traffic operations, for example, to follow more efficient flight paths. However, as a pilot, I am happy to hear the calm voice of the controller on the radio to land quickly and safely if I have a problem.

One more thing! We are now on WhatsApp channels! Follow us there so that you never miss any updates from the world of technology. To follow HT Tech channel on WhatsApp, click Here Join now!

Source link

Leave a Comment