Artificial Intelligence in Aviation Beyond Autonomous Flight

It’s more than just flying cars and drones

Mikhail Klassen
Dec 19, 2020 · 7 min read
The Liberty flying car, by Dutch company PAL-V. Photo via Wikimedia Commons, CC BY-SA 4.0. Author: Eslivb

AI is eating the world

It’s quickly becoming a cliché to say that AI is disrupting every industry on the planet. It’s been almost a year now since Marc Andreessen’s famous essay in the Wall Street Journal about why software is eating the world.

Software is eating the world. — Marc Andreessen

That was true in 2011, and it’s still true today. Everywhere we look, software is being embedded into the things that we use every day. Even toaster ovens are being outfitted with touchscreen displays.

The myth of Talos describes a giant automaton made of bronze to protect Europa in Crete from invaders. This represents some of the earliest recorded ideas about a machine intelligence. Still image from Jason and the Argonauts (1963, Columbia Pictures)

Some examples

  • Take X audio, and predict Y words as text (speech-to-text engine)
  • Take X text, and predict Y synthesized audio (text-to-speech engine)
  • Take X text, and predict the next word in the sentence (GPT-3)
  • Take X image, and predict Y contents (computer vision, image segmentation)
  • Take X time series, and predict Y future values (forecasting)
  • Take X user reviews (👍,👎), and predict Y preferred song/show/product (recommendation engine)
  • Take X user query, and predict Y table of results (search engine)

With fully autonomous cars expected within years, it’s tempting to assume fully autonomous passenger aircraft are next. That’s mistaken.

Expecting the unexpected

Quite apart from the fact that Level 5 autonomy in cars is turning out to be much harder than we thought, given the current state of deep learning research, human brains seem to be uniquely qualified at dealing with the unexpected.

Dealing with the unexpected is at the core of much pilot training today.

In the best case, this increased automation reduces the pilots’ cognitive burden of managing an aircraft. However, in the worst cases, pilots become too dependent on automation and lose their manual flying skills. This dependency has contributed to a number of high-profile accidents over the years.

A flight data recorder (left) and cockpit voice recorder (right) mounted in the rear fuselage of an aircraft. Photo by YSSYguy, via Wikimedia Commons. CC BY-SA 3.0.

AI is coming for aviation

Machine learning thrives wherever there is lots of data. And aviation is one of the most data-intensive industries on the planet. “Black box” data recorders were an early innovation that tracked a handful of parameters that were essential in accident investigations. The more modern Quick Access Recorder (QAR) tracks 2000 or more different parameters, and at much higher sampling rates. A multitude of other sensors are collecting data for predictive maintenance and future performance improvements.

Photo by Artur Tumasjan on Unsplash

What about pilot training?

The holy grail of “evidence-based training” would be if you could take all of your airline operations data, and have some very intelligent software design a perfectly tailored recurrent training curriculum for you. This program would perfectly target any weaknesses and not waste any time on redundant training.

  • Rote execution of a task from memory does not, by itself, guarantee competency.

Implementing competency-based training, if done manually, comes with many upfront costs and increased instructor burden. Hence the need for automation.

Programs like the Multi-crew Pilot License (MPL) are already designed around competency-based training. These programs can help address the pilot shortage. But competency-based training is hard to implement. There’s an upfront cost to overhauling curricula. Instructors need to be retrained, because now they’re tasked with assessing pilots across even more dimensions.

Pilot selection

Another example where AI can benefit aviation is in pilot selection. To become a pilot it takes the “right stuff” — certain aptitudes, personality traits, and psychomotor skills.

Avoiding bias

A machine learning algorithm isn’t objective by definition. It just learns from patterns, and if we’re not careful, our own biases get “baked” into the algorithms.

Pilot training in 2020/2021

In the middle of a pandemic, when thousands of pilots are furloughed, it can seem like the wrong time to change pilot training.

In the near term, we can focus on data infrastructure and the digitization of assessment.

Adding capacity for data-driven training will allow training organizations to return to regular operations faster by re-certifying more pilots in less time, reducing remedial training, and collecting the necessary evidence for regulators to grant reductions in the frequency of recurrent training.

Conclusion

I believe it likely that commercial aircraft will eventually be fully autonomous. The technological and economic forces driving this are powerful. This is distinct from automation, which modern aircraft use in abundance. To account for the unexpected, industry experts believe pilots will remain an essential component of safe travel for a long time yet.

Paladin AI

At Paladin AI, we’re building the tools and the platform that airlines and ATOs need to implement CBT, using their existing hardware and training media.

Paladin AI

The official blog of Paladin AI where we write about…