The show is often a place where new technology is unveiled that will eventually — due to the strict regulatory and airworthiness requirements — make its way to the world of aerospace and commercial air travel.
CES this year did not disappoint, with many automakers, traditional electronics firms and aerospace companies discussing applications of artificial intelligence (AI), connected car technology and envisioning mobility systems within a ‘smart city’ context.
Samsung’s Digital Cockpit 2020, the third evolution of collaboration with HARMAN International, utilizes 5G connectivity to link cars to a driver’s other devices as well as other cars on the road. By aggregating and processing location data shared between devices, Samsung hopes to generate a more accurate picture of future traffic and transit times, improve collision avoidance and improve passenger entertainment options through higher-speed connectivity.
Using Internet of Things (IoT) sensors, big data and machine learning, LG partnered with Element AI to apply artificial intelligence to home appliances, offering personalized, proactive maintenance and improved functionality — similar to health and usage monitoring (HUMS) systems for aircraft.
The most prescient theme of the event’s mobility presentations seemed to be reclaiming one’s time spent in traffic, with many automakers debuting ideas for vehicles that allow passengers to make better use of the hours spent in transit — or reclaiming that time by taking to the skies. CES included multiple attention-grabbing presentations by air taxi developers, who showcased their progress on electric takeoff and landing (eVTOL) aircraft and demoed AI-powered connected fleet technology that will enable safety, efficiency and high throughput in low-altitude city skies.
Japanese automaker Hyundai announced its entrance into the air taxi space in September 2019, hiring just-retired NASA aeronautics director Jaiwon Shin to lead its newly created Urban Air Mobility (UAM) division. Just a few months later, Hyundai revealed a full-scale model of its eVTOL design, the S-A1, and announced it would join Uber Elevate, the mobility company’s ecosystem targeting commercial operations of aerial ridesharing in 2023.
Hyundai’s S-AI isn’t expected to be ready until 2028, but it was the first vehicle partner to join Uber with a history of successful manufacturing on a mass scale — something new to aerospace but necessary to achieve the scale air taxi developers intend to provide.
“There are currently about 25,000 commercial airplanes flying around the world,” Shin said at CES. “We believe the [UAM sector] will well exceed this number once it matures fully. At Hyundai, we know how to mass produce high-quality vehicles with cost efficiency and reliability, which is a key enabler for reducing overall operating costs.”
An all-electric aircraft, the S-A1 combines four stationary rotors with four tilting rotors for wing-borne lift in cruise, according to Hyundai. The aircraft is intended to reach speeds up to 180 miles per hour, carrying a pilot, four passengers and their luggage up to 60 miles on a single charge at altitudes of 1,000-2,000 feet.
Just a week later, secretive startup Joby Aviation — also an Uber partner — announced a $394 million investment and manufacturing partnership from Toyota. Automakers, believing that peak auto sales are in the past due to ridesharing as well as advances in connectivity and autonomous technology, are getting serious about taking to the skies.
Hyundai and Toyota both discussed their visions for more human-centric mobility in urban areas; Hyundai focused on “purpose-built vehicles” that can double as stores or doctor’s offices and allow people to make better use of their transit time. Toyota plans to build a 175-acre, fully connected “Woven City” near the base of Mt. Fuji, powered by hydrogen fuel cells and filled with autonomous cars. The city will also make extensive use of sensor-based AI “to do things automatically, like restocking your fridge, or taking out your trash — or even taking care of how healthy you are,” said Danish designer Bjarke Ingels.
But the most compelling demonstration of applying artificial intelligence, predictive algorithms and connected systems to mobility during CES 2020 came from Bell, which displayed a “smart city” with miniature versions of its Bell Nexus air taxi and Autonomous Pod Transport (APT) cargo drones flying from rooftop to rooftop, fulfilling missions requested by audience members on the floor.
Bell’s smart city ran off an early version of AerOS, the company’s “operating system” it plans to offer to cities as a full-stack digital infrastructure mobility solution. The AerOS software platform is intended to manage both the customer interface as well as fleet management tools, using machine learning and predictive algorithms to optimize for demand, vehicle charging and maintenance. The software also incorporated aircraft scheduling and de-confliction, ensuring the mini-Bell Nexus and APT drones safely arrived at their destinations — though the company intends to partner with an unmanned traffic provider soon.
“We’re talking about the demand signal coming in has to flawlessly interchange with the AI master scheduling engine,” said Matthew Holvey, intelligent systems lead for Bell’s innovation team. “That’s deciding what these 100 aircraft are going to do, where they’re going to go. If you’ve got battery management that dictates that these batteries are healthiest, when you discharge to this percentage, then your deeper discharges need to be spread out across your fleet, which means you need to be tracking which aircraft and which batteries are seeing those deeper discharges … you need to spread that fatigue across different aircraft.”
“If you have all of that data accessible and are using current technology — artificial intelligence, optimization algorithms — then you can accomplish that today,” Holvey added. “Drive down your costs, drive up safety, and make this truly approachable.”
Bell also took its Nexus air taxi design in a new direction, announcing the Nexus 4EX: four rotors instead of six, and fully electric instead of hybrid, though the company stressed it will be designed propulsion-agnostic. The new aircraft is a result of changing demand signals, according to Bell — initially, potential air taxi customers stressed a need for range, resulting in the hybrid approach revealed at CES in (2017/2018). Now, with demand growing for inner-city aerial transit, the Nexus 4EX is redesigned for maximum efficiency in forward flight (with a longer back wing), to move 4-5 passengers and their luggage 60 miles per charge — a very similar target to Hyundai’s S-A1.
Though AerOS will be available as a modular product, allowing cities to use individual pieces of the Bell’s connected fleet operating system, the company hopes to provide as many pieces of the ecosystem as it can, including its Nexus 4EX aircraft as well as potentially the pilots and maintenance system. But the key to ensuring the simultaneous safe operation of a hundred eVTOLs above city skies — whether Bell Hyundai, or Joby-made aircraft —will be the connected real-time data sharing, predictive maintenance and machine learning behind a fleet management tool like AerOS.
Delta Air Lines CEO Ed Bastian used his keynote speech at CES to discuss a new 2020s operational structure for the international carrier that will be driven by the use of a new AI machine learning tool.
Under development at Delta’s operations and customer center, Bastian did not provide a specific product name for the technology, but instead called it a proprietary tool focused on helping passengers and flight crews overcome weather occurrences that impact the routes they fly on a daily basis. The keynote speech is a familiar strategy across all of the divisions of Delta, including their maintenance team whose predictive maintenance leadership gave a speech on how the airline is shifting towards the adoption of AI at the 2019 AEEC/AMC annual conference.
“We’ve cancelled cancellations, but we still have to deal with weather variables like hurricanes or a nasty Nor’easter, and that’s why the team in our operations and customer center is developing the industry’s first machine learning platform to help ensure a smooth operation even in extreme conditions,” Bastian said. “The system uses operational data to run scenarios and project future outcomes while simulating all the variables of running a global airline with more than 1,000 planes in the sky.”
Initial implementation of Delta’s new tool is scheduled for the spring, with the airline describing it as being capable of creating hypothetical outcomes for decision-making that occurs in anticipation of large-scale disruptions, due to weather or other environmental factors beyond their control. A key aspect of the tool is its ability to use machine learning to ‘learn’ from the impact of weather disruption so that airline personnel can make better decisions when the same situation occurs in the future.
Delta’s pilots have also developed a flight weather viewer tablet application that gives them a three-dimensional view of their flight path with a prediction of where turbulence will occur. Initial use of turbulence avoidance first emerged for Delta in 2016, when their fiscal year annual report noted pilots were beta testing the use of algorithms developed by the National Center for Atmospheric Research.
Bastian said the airline is still improving its use of turbulence avoidance and that it will be a major focus of their overall AI and machine learning driven operational structure moving forward.
“Another focus we have is turbulence, we’re seeing more and more instances of it, and it has a very real impact on our customers and on our employees,” Bastian said. “We have been able to reduce the impact of turbulence with a flight weather viewer, which is an app developed by our very own Delta pilots. It visualizes turbulence and other weather hazards along the flight path. Using it, pilots can adjust their course more precisely. It also helps our pilots give real time updates to travelers while they’re in the air in advance of encountering turbulence and can also let them know how long we expect it to last.”