How Autonomy Will Support The Growing Demand for Air Travel

Few emerging technologies embody the promise and wonder of artificial intelligence quite like autonomous vehicles, which have the potential to forever transform the way we move people, resources, and goods around the world. As more and more of humanity migrates to cities, autonomous vehicles could be key to realizing a brighter future in urban mobility. Indeed, these machines may one day help us build a world where efficient, automated deliveries and driverless flying taxis are used to minimize congestion and improve the quality of life in increasingly cramped urban landscapes.

Already today, one can find fully-functioning autonomous vehicles gliding through the streets of cities like San Francisco and Singapore. However, skeptics still question whether the technology will ultimately be as safe as researchers and AI experts claim. When it comes to aviation in particular, the idea of an autonomous urban air taxi has proven to be quite appealing, generating billions in research funding, but doubts still remain whether an automated system can match the training, experience, and natural intuition that a human pilot brings to the table.

Well, we’ve got bad news for the skeptics: autonomy isn’t just an accessory feature in the urban mobility of the future; it’s a necessity. Airlines are already facing a severe pilot shortage, and growing demand for air travel means that the industry will need to recruit thousands of pilots in the years ahead. Meanwhile, New York City alone required nearly 110,000 cab drivers to complete roughly 27 million trips in just the month of August. If even a tenth of that demand were shifted to air taxis, and extrapolated across all major cities in the country, the new industry would require of tens of thousands of additional certified pilots. That’s no small feat given the increasingly fierce competition they’ll face from major airlines and even the super rich aircraft owners.

Fortunately, self-piloted urban aircraft and single-piloted aircraft will bridge that gap.

How do we train a computer to perceive the environment and make decisions as competently as a professional pilot? That’s where Wayfinder comes in. Our core mission is to build a scalable, certifiable autonomy system capable of powering a range of self-piloted aircraft applications in single pilot operations, from small urban air vehicles to large commercial airplanes. This, however, raises the issue of another widely-discussed topic in the industry: automation vs. autonomy.

Today’s commercial aircraft already use a high level of automation, which at its core is simply a predetermined set of actions that the aircraft can be programmed to execute without human assistance. Autonomy is distinct from automation in that it refers to the aircraft’s ability to react to unforeseen events and make the same decisions that a pilot would under similar circumstances. In general, today’s commercial aircraft do not exhibit autonomous functionality in any meaningful form, and much of our efforts center on making the leap from automation to autonomy.

To accomplish this, the Wayfinder team uses machine learning, a form of statistical model that enables an AI system to learn abstract behavior from large data sets. At Wayfinder, we plan to observe the work that experienced pilots are doing every day, and then aggregate this data on a massive scale to train our machine learning models. As a rule, when a pilot retires, their experience is lost forever, but with our model, their contributions will endure. The historical data we gain from them will always be accessible to our AI systems, contributing to their continual learning and improvement. With this approach, we believe our AI system can eventually match the abilities of human pilots, bringing to life the business case of urban mobility and easing the strain put on pilots already in the field.

If you have questions as we approach an autonomy-driven future, please leave a comment. We’d love to discuss this topic with you. And as always, for those interested in helping build this future, please check out our open positions.

- Arne Stoschek, Project Executive, Wayfinder