A²I: The sky’s the limit ✈️
The digital revolution which is ready for take-off in the aviation industry with the help of smart intelligent systems!
Stuck in the middle of the traffic, I always wonder if there is be could any better mode of transport to commute. Won’t it be great if we could ditch the traffic and had an option to travel by aeroplane or heli-cabs at the affordable fare? If that is the case then in the near future, at countless airports around the world, tens of thousands of flights per day are taking off, landing, and crisscrossing the skies overhead.
Aviation is a cornerstone of contemporary civilization and touches every corner of our lives in ways we may not even realize. Take the example of the U.S. commercial aviation industry, in the next two decades, passenger count is expected to double. In 2016, the U.S. commercial aviation industry generated an operating revenue of $168.2 billion. This is an opportunity for exponential growth which needs to be handled well.
The aviation industry needs to move beyond its present ways of working and find better ways to optimize available resources, improve customer satisfaction and safety records, control costs and be more responsible environmentally.
AI take-off: Transformational change in the travel industry
As the quantity and velocity of aviation information grows and new technologies and skills in integrated Data Intelligence Platforms, Cloud Solutions, Advanced Analytics, Machine Learning make use of powerful computers to sort through vast amounts of data, learn patterns, and work smarter which help to evolve in accessing and make use of available the data, those airports and the airlines. Machine learning is combined with deep learning and neural networks to create powerful algorithms that attempt to “think” like a human.
AI can help in many innovative ways — from the optimization of manufacturing processes to smart maintenance, flight operations optimization, training or even virtual assistants for pilots and crew.
Here are a collection of scenarios in which AI seems the best option to take aviation to the next level :
Real-time Decision making in auto-piloting
So far, most of the AI innovation in aviation has focused on control of the aeroplane or its systems. Things get much more interesting when such technology is used for real decision-making tasks.
It began with Garmin’s Electronic Stability and Protection system, a major advance in autopilot technology that has received surprisingly little attention. This passive safety system continuously monitors the aeroplane’s attitude and uses the autopilot servos even when the autopilot is off to nudge the aeroplane back to safety. Garmin’s Telligence system uses voice commands to complete hundreds of common tasks in the cockpit.
Aurora’s approach involves a perception system in the cockpit that uses multiple cameras to read the gauges and monitor the switches and feeds the data into the real-time computer model of the aircraft’s state.
Researchers at University College London are taking it a step further by applying real AI to an autopilot. Instead of just programming it to fly certain pre-planned profiles, the team is using machine learning to make a more resilient autopilot that can adapt to changing conditions. By watching a human fly and storing hundreds of hours of detailed data from real flights, it builds a library of scenarios. Whereas a traditional autopilot might give up when an engine fails or the turbulence gets really rough, this new design leans on its experience to keep flying.
For example, a DARPA project called Aircrew Labor In-cockpit Automation System (ALIAS) aims to create a full replacement for a human copilot.
Air Traffic Management
Currently, aircraft are tracked by radar when over land and in coastal areas, and flight paths are negotiated by radio. Digital control towers and artificial intelligence are on the verge of transforming the world of Air Traffic Management(ATM), with enormous operational, safety and efficiency benefits for airports around the world and promise to boost the performance of ATM worldwide. These include the need to increase the predictability of traffic at different phases of flight, improve passenger flows at airports, and enable greater automation of the system.
Passenger Identification
The idea is to have machines perform end-to-end passenger identification and check-in at the airport. Delta Airlines has been testing this process and implementing creative initiatives such as ticketing kiosks and check-in via the Fly Delta mobile app.
Baggage Screening
In 2017, American Airlines conducted an app development competition “HackWars”, with the goal of having an app developed for making baggage screening easier for passengers. The winner of the competition “ Team Avatar”, developed an app that not only allows passengers to measure their baggage size before arriving at the airport but also provides an option to prepay any potential baggage-related expenses to the travellers.
Customer Assistance
United Airlines is using Amazon’s Alexa to have frequently asked common customer queries answered. All passengers need to do is to add the “United skill” feature to their Alexa app and then start asking questions. Alexa answers common queries correctly, such as the status of a flight by number, check-in requests and amenities like entertainment, WiFi and business-friendly perks. which helps the passengers to relax and focus on last-minute travel preparations, instead of worrying about their flight. There is a learning curve, and it is still a long way to go before AI can fully handle customer assistance.
Facial Recognition
Delta Airlines has teamed up with U.S. Customs and Border Protection (CBP) to test new biometric exit immigration procedures. The new technology known as Seamless Totem is part of a digital travel marketing scheme tested out in two airports. In New York’s JFK International Airport, the eGate would open for individual passengers to walk through after successful screening. At Hartsfield-Jackson Atlanta Airport, a self-contained unit would capture and verify a passenger’s identity before allowing him or her to continue boarding.
Challenges and Tasks
Since the aviation industry has only recently embarked on the AI journey, fully embracing AI is going to be a challenging task. Humongous volumes of data will be in use as the aviation industry embraces AI, and that will give rise to data confidentiality risks. However, the need to properly manage data is a new challenge to all the airlines. Tracking progress is an enormous challenge that airlines will face. The first thing they need to do is to develop analytics that will help them develop and process accurate data. However, that in itself is a challenge.
Ready to fly into the future?
Researchers at MIT use the phrase “extended intelligence” instead of artificial intelligence to signify how AI is used to augment human decision-making rather than replace it. At this point, we are mostly in the nascent stage, but there are some exciting possibilities to imagine. When used appropriately by the ever-increasing travel industry, it can improve the safety, utility and fun of flying. We can definitely say: AI is taking aviation to the next level where the realistic and exciting future awaits!
R&D at Arnekt
Arnekt helps in turning the vision into action. Arnekt envisions the development of AI-powered applications and web services using Cognitive Intelligence. Arnekt mainly focuses on building data-driven algorithms to improve logistics for businesses without compromising on the performance which helps in making a greater impact as a leader. This helps in giving a competitive edge and creating business value.
