The goal of the new partnership, first and foremost is to make sense of the burgeoning amount of data in the aerospace industry. By applying principles of machine learning, it might be possible to optimize many aspects of Boeing’s operations — including those related to design, construction and operation – and turn ordinary data into real-world insights.
According to Jaime Carbonell, the Carnegie Mellon professor and Director of the Language Technologies Institute, who will head up the new Aerospace Data Analytics Lab, ”The mass of data generated daily by the aerospace industry overwhelms human understanding, but recent advances in language technologies and machine learning give us every reason to expect that we can gain useful insights from that data.“
One example of how machine learning can be used to gain useful insights is the whole issue of airline maintenance. Think of airline maintenance the same way you think of maintenance for our car – you can follow the generally suggested guidelines for your vehicle (e.g. an oil change every 3,000 miles) – or you can use real-time data to see which planes needs fixing, when. By fixing planes before – not after – they need maintenance, an airline flying Boeing planes could gain a real competitive advantage over its peers.
“A Boeing aircraft such as the 787 Dreamliner combines thousands of on-board sensors, text from pilots and mechanics, structured engineering data bases, across the entire fleet collected from each of the client airlines,” Carbonell told me. “This provides a golden opportunity, merging CMU’s capabilities and Boeing data to address problems such as predictive analysis for preventive maintenance — rather than after-the-plane-is-grounded maintenance.”
In short, Carnegie Mellon and Boeing might be able to determine when planes actually need maintenance instead of just following historical maintenance schedules. And that might avoid the airline equivalent of the “check engine” light that comes on without warning in automobiles. That obviously makes flying planes safer for passengers – and could reduce the time lost on the tarmac accounting for last-minute mechanical failures in planes.
At the launch of the new lab, Ted Colbert, Boeing chief information officer, commented on the importance of the new initiative for the aerospace giant: “We’re aiming to push the technology envelope. We have the best and the brightest faculty at a leading institution focused on how we can innovate and solve business challenges for today and into the future.”
The Aerospace Data Analytics Lab, Andrew Moore, Carnegie Mellon’s computer science dean, told me in a conversation before the announcement of the Boeing partnership, is just part of an expanding number of initiatives at Carnegie Mellon that are attempting to tap into the exciting future potential of AI. He referenced a number of “moonshot” initiatives underway — including robots that take over the cleanup of hazardous environments and robotic arms that can pick up a cup of coffee without spilling.
And keep in mind, Carnegie Mellon is also the home of the self-driving car, perhaps one of the most talked-about advances in the AI field in recent years. Carnegie Mellon has already created more than 140 technologies related to autonomous vehicles.
So are self-driving airplanes on the horizon anytime soon?
That’s not really the goal, Carbonell told me, especially given the three-year time horizon of the Boeing lab project. “We already have semi-self-driving airplanes. We call the devices autopilots, which have been in use for a long time. These will keep improving and gradually yield a higher degree of automation.”
Instead, said Carbonell, the goal is airplanes that can fix themselves: “The audacious plan is closer to self-healing airplanes: evidence-based predictions of what may not be working right tomorrow, to enable preventive inspection or replacement before a failure, and hence to lower costs of coping with real unscheduled failures and to increase safety.”
At the official launch of the lab, Boeing suggested that its involvement could grow over time, presumably based on the success of the aerospace giant being able to realize a return from its AI investment. For now, the lab will launch with more than half a dozen Boeing-directed projects and will involve over 20 researchers pulled from the ranks of Carnegie Mellon’s faculty and graduate students.
The big idea is that visible success by an American corporate giant in a data-intensive industry could encourage other companies to explore AI initiatives. As AI continues to move up the software stack, Moore told me, AI could become the layer on top that provides helpful advice to humans, enabling them to build better models of the world based on new machine learning algorithms.
At first, AI will change our day-to-day lives in ways that may not be visible at first — or in ways that we don’t think of as traditional AI. But as big corporations embrace AI that could change, making it more of a strategic decision for the CEO than a technological decision for the CIO. That means that the next time you look up in the sky, that plane flying overhead might just be a Boeing jetliner that’s been optimized with the help of intelligent machines.