Artificial Intelligence in Aviation

Over the last few years a number of aircraft accidents have been caused by pilot fatigue. Automation failure has played a role in this, combined with pilots lack of hand-flying skills and tiredness; causing a fatal crash.

The  forecasted pilot shortage with huge numbers predicted by Boeing and Airbus mentions the need for as many as 617,000 new pilots by 2035 – have been shared far and wide.

Pilots are more and more fatigued and the future requires more pilots…

Could integrating the cockpit with Artificial Intelligence (AI), be the solution to these two growing problems?

I have covered this subject in previous blogs but new developments prompted me to give you an update.

Haitham Baomar and his colleague Peter Bentley, both  Artificial-Intelligence (AI) experts at University College London (UCL); inspired by these accidents, are developing a special kind of autopilot: one that uses a “machine learning” system to cope when the going gets tough, rather than the crew manual flying.

Today’s autopilots cannot be trained, because they are “hard coded” programs in which a limited number of situations activate well-defined, pre-written coping strategies—for example, to maintain a certain speed or altitude. A list of bullet points (which is what such programs amount to) does not handle unfamiliar situations well: throw one of these scenarios at the computer that its programmers have did not consider, and it has no option but require humans to take over control.

The UCL team are working on the creation of a machine-learning algorithm could learn from how human pilots and cope with unfamiliar situations, such as serious emergencies like sudden turbulence, engine failures, or loss of critical flight data. This way the autopilot will not have to cede control as often back to the pilots,  reducing pilot workload and fatigue.

Machine learning is a hot topic in AI research. It is already used for different tasks like decoding human speech, image recognition or deciding which adverts to show web users. The programs work by using artificial neural networks (ANNs), which are inspired by biological brains, to process huge quantities of data, looking for patterns and extracting rules that make them more efficient at whatever task they have been programmed to do. This way the computers teach themselves.

UCL has lots of experience in this area. The UCL team has written an Intelligent Autopilot System that uses ten separate ANNs. Each is tasked with learning the best settings for different controls (the throttle, ailerons, elevators and so on) in a variety of different conditions. Hundreds of ANNs would probably be needed to cope with a real aircraft, but ten is enough to check whether the idea is fundamentally a sound one.

To train the autopilot, its ten ANNs observe real pilots using a flight simulator. As the plane is flown—taking off, cruising, landing and coping with severe weather and aircraft emergencies that can strike at any point—the networks teach themselves how each specific element of powered flight relates to all the others. When the system is given a simulated aircraft of its own, it will thus know how to alter the plane’s controls to keep it flying as straight and level as possible, come what may.

In a demonstration at a UCL lab, the system recovered with very efficiently from all sorts of in-flight emergencies, from losing engine power to extreme turbulence or hail storms . If it were to lose speed, the machine would keep the nose low enough to prevent a stall. The newest version will seek speed data from other sources, like the global positioning system (GPS).

To the team’s surprise, the system could also fly aircraft it had not been trained on. Despite learning on a (simulated) Cirrus light aircraft, the machine proved capable with  both airliners and fighter jets, also available in the database. That is a good example of a machine-learning phenomenon called “generalisation”, in which neural networks can handle scenarios that are conceptually similar, but different in the specifics, to the ones they are trained on.

A team at aircraft manufacturer, Airbus, are working on investigating neural networks, too. Airbus reckon such systems are unlikely to be flying passenger jets just yet. One of the downsides of having a computer train itself is that the result is a black box. Neural networks learn by modifying the strength of the connections between their simulated neurons. The exact strengths they end up with are not programmed by engineers, and it may not be clear to outside observers what function a specific neuron is serving. That prevents ANNs from being validated by aviation authorities, says Peter Ladkin, a safety expert at Bielefeld University in Germany.

The new autopilot will probably find its first uses in drones. The system’s versatility has already impressed delegates at the 2016 International Conference on Unmanned Aircraft Systems in Virginia. The system’s ability to keep control in challenging weather might see it used in scientific investigations of things like hurricanes and tornadoes, says Dr Ladkin.

Garmin’s Telligence product is sort of a Siri for the cockpit. This predictive AI will probably involve voice alerts and speech recognition, too. The interface of the future may resemble a conversation more than a computer to be programmed. Garmin’s Telligence system uses voice commands to complete hundreds of common tasks in the cockpit. This is certified and available to install today, and it most certainly isn’t the last voice command product we’ll see.

Aviation will get a big boost from the drone market when it comes to developing practical, airborne AI. After all, on a quadcopter that’s inspecting a pipeline there is no pilot to make decisions, so the AI is essential. Billions of dollars are being spent to develop drone technology that avoids terrain, obstacles, traffic, and weather, or self-diagnoses a mechanical problem and returns to base.  A lot of these scenarios and technology will be taken for a test drive on drones before coming to your passenger aircraft.

As always, regulation will move far slower than technology. What’s possible and what’s certified are not the same, and we can expect the various aviation regulators around the world to be cautious in approving this type of AI technology in aircraft. Not all of that caution is unjustified, and the good news is that aviation is actually ahead of cars in many ways – we’ve been regulating and training on automation for decades.

Researchers at MIT use the phrase “extended intelligence” to signify how AI is used to augment human decision-making rather than replace it. This is actually a crucial distinction. Extended intelligence, just like a glass panel or a deice system, is simply a tool. When used properly by pilots, it can improve the safety, utility and fun of flying. That’s a realistic – and exciting – future.

What many people do not know is that new technology in aviation is first introduced into military aircraft, it then gets into the private jets and a few years later is fitted into airliners. One thing technology has done in the past and will do even more in the future, is improve flight safety. You just need to compare the avionics in an Embraer Phenom 300 to a Boeing B737NG and you can clearly see the biz jet quite a few generations ahead.

In the following video you can see the new Cirrus Vision Jet, single-engine private jet. It is fully loaded with new technology and out to be certified in next few weeks.

Fabrizio Poli is Managing Partner of Aircraft Trading Company Tyrus Wings. He is also an accomplished Airline Transport Pilot having flown both private Jets and for the airlines. Fabrizio is also a bestselling author and inspirational speaker & has been featured on Russia Today (RT), Social Media Examiner,Bloomberg, Channel 5, Chicago Tribune, Daily Telegraph, City Wealth Magazine, Billionaire.com, Wealth X, Financial Times, El Financiero and many other Media offering insight on the aviation world. Fabrizio is also regularly featured as an Aviation Analyst on Russia Today (RT). Fabrizio is also aviation special correspondent for luxury magazine, Most Fabullous Magazine. Fabrizio is also considered one of the world's top 30 experts in using Linkedin for business. You can tune in weekly to Fabrizio's business Podcast Living Outside the Cube available both in video & audio. You can also follow Fabrizio's aviation videos on Tyrus Wings TV.

You can contact Fabrizio on:

[email protected]

OR Mobile: +44 7722 350 017