|
Dec
16
2024
|
|
Posted 4 days ago ago by Admin
|
|
Once upon a time, AI (artificial intelligence) was just a buzzword for all that was new, cool, and impossible in technology — but no longer. “AI is having an impact on the drone and helicopter industries today,” said Clint Church, chief engineer with Aurora Flight Sciences, a Boeing subsidiary that specializes in special-purpose uncrewed aerial systems (UAS). “AI is enabling remote operation of uncrewed aircraft, such as small UAS and military air vehicles,” he told Rotor Pro. “It is also enabling more efficient data collection for use cases such as infrastructure inspection and intelligence, surveillance, and reconnaissance (ISR) missions. AI is also a significant area of investment in research and development. These investments are driving growth across our industry”
“AI is having an impact on the helicopter industry — not just our products, but many of our company processes,” echoed Mattia Cavanna, Leonardo Helicopters’s VP for technology and innovation. “So the short answer is: AI is not just a buzzword; it’s making a real difference.” The new question is, how much difference can AI actually make?
AI’s Impressive Impact
To prove his point about AI’s impact, Cavanna described the many ways that AI is now being used at Leonardo Helicopters. In engineering, for instance, Leonardo uses AI to test and verify the validity of its designs. The company also uses AI to improve its manufacturing processes, its management systems, and its training and simulation offerings.
“AI can help speed up the training process by recognizing the maneuvers that students are making in the simulators and giving them scores quickly,” Cavanna said. “It is also useful in preventive maintenance where AI can analyze the data being compiled by ongoing, sensor-based health monitoring of the aircraft and use it to project what maintenance needs to be done. Meanwhile, we are using generative AI to make sense of vast amounts of documents. AI is also important for autonomous flight, such as the autonomous uncrewed projects that Leonardo is doing with the U.K. Ministry of Defence and the U.S. Marines.”
Sikorsky Image = Sikorsky is focusing on AI for helicopter mission planning roles to support troops in contested battlespace. Photo by Sikorsky, a Lockheed Martin company.
Sikorsky, a Lockheed Martin company, is constantly evaluating the use of AI and “machine learning” on its helicopters and future VTOL products, both in the lab and in the air. The reason for this two-pronged approach? “Testing and qualifying AI (machine learning) for applications to direct aircraft control is difficult,” replied Igor Cherepinsky, director of Sikorsky Innovations. “That’s because of the inability to test and verify these algorithms accurately in the lab alone.”
Nevertheless, “Sikorsky can and does use AI in adjacent roles,” Cherepinsky noted. “For example, our MATRIX flight control system is capable of performing full mission planning from a handful of goals and constraints. Once the system comes up with several plans, we use reinforcement learning algorithms to pick a plan that is more desirable for the human crew. In this case, the AI algorithms are not performing a flight-critical function. So let’s say I’m in a Black Hawk helicopter performing a military cargo supply mission: AI would pick which routes one or more aircraft need to make on the battlefield to get from Point A to Point B, and with which helicopters. Another time, the algorithm might choose a different solution to get supplies to the troops. Either outcome is safe.”
Over at Aurora Flight Sciences, AI is having a big impact on how the company designs and builds special purpose drones. “In aircraft development, AI is advancing how engineers solve problems and deploy technical capability,” said Church. “Simulations, modeling, and digital twins have evolved to give a more complete analytical simulation. AI means we can feed in more constraints and simulate every option of every variable, generating a full cloud set of data points.”
AI is also making Aurora Flight Sciences’ drones more successful in fulfilling their missions. The reason: “In our flight operations, the strategic integration of AI-enabled features allows us to improve safety, reduce pilot workload, and increase data quality during flight testing,” Church said. “AI can allow the flight crew more capacity to focus on the system being tested. We also see quality improvements in that we can ensure that tests are repeatable, which means we are analyzing the technology rather than the variability in human operators.”
Of course, the use of AI does vary considerably from company to company. JumpAero.com states they are “bringing to market the fastest electric-vertical-takeoff-and-landing (eVTOL) aircraft for first responders.” According to company founder and CEO Carl Dietrich, “We do not use AI for anything that could be considered safety critical, which is most of what we do. However, we do have experience working under a USAF research contract with Caltech on an adaptive/ML flight control routine that demonstrated meaningful improvements in the response of the flight control system to failures. Importantly, however, the system is trained in a simulated environment. As such, the AI/ML component is static after training. This is important for certification and general confidence/reliability.”
Having said this, Dietrich acknowledged that, “Other companies that are in larger volume production use AI/ML as part of continued airworthiness and quality control/inspection process. Vision-based algorithms are useful in this context as well as in advanced autonomy routines.”
Must-Have Necessities and Unavoidable Limits
The degree to which rotorcraft companies are using AI underlines a key fact: For many of them, AI has become a necessity.
“I think AI has become a ‘must-have’ in the helicopter industry, because if you don’t have it, you risk losing ground to your competitors,” said Cavanna. “This is because AI lets you make more sense of your data. It helps you come up with new ideas that you might not tap into on your own.”
“Some elements of AI are must-haves for Aurora Flight Sciences’ processes today,” Church agreed. “For example, we design cutting-edge drone technology. AI helps us engineer the best products, test technologies in simulated environments, and maximize safety and data quality when testing in flight.”
At the same time, “AI/ML is only as good as the training data that is used,” explained Dietrich. “Just like any computational system, if the inputs are garbage, the output will be garbage too.”
“AI cannot yet perform in a reliable way in all scenarios, so humans must always be in the loop,” Church said. “It’s hard to say when AI will be reliable enough to operate truly autonomously, without being partnered with or supervised by a human.”
Vlcsnap = Aurora’s Centaur Optionally Piloted Aircraft can fly without an onboard pilot. Photo by Aurora Flight Sciences
This is why Mattia Cavanna recommends viewing AI-generated data with a grain of salt, and leaving final decisions to analytically minded humans. “You can’t afford to become too dependent on AI and let it do all the work for you — because such an approach would be hard to justify, especially to certifying bodies,” he observed. “This makes our industry, which is very prudent, a little bit slower in adopting AI for obvious reasons, because safety comes first.”
AI Takeover May Be Overstated
Even if AI should one day become reliable enough to be trusted with its own management — and that day may yet come — there is only so much that this technology is suited for. Despite the hype, AI cannot replace humans in all aspects of the rotorcraft business.
For instance, “I don't think AI will help mediate disputes between employees because people must respect a mediator, and people don't respect computers — they use computers as tools.” said Dietrich. “I also think the use of LLM (large language model) tools for anything like safety critical software is unlikely to happen anytime soon, even though the tech is capable of writing the code. This is more due to corporate culture around the importance of safety than a lack of capability of AI to generate code. The problem is that people don't trust it, and I don't blame them. I don't want human lives to depend on an LLM routine either.”
Church is similarly cautious in his assessment of AI’s abilities. “It’s difficult to say that there are areas of the business that AI will never be able to assist with,” he said. “But certainly, we don’t expect AI to ever replace the humanity of humans. Leading teams and managing people with compassion is an important part of every business and will continue to be done by humans. Meanwhile, AI will assist with an increasing amount of the mundane, dangerous, dirty, repetitive, and computational work.”
Are AI/Human Partnerships the Future?
In the years ahead, AI’s usefulness as a tool will expand as this technology is refined and improved, not just in the rotorcraft industry, but anywhere that AI is being currently employed. This means that AI will likely perform tasks tomorrow that it cannot do today, and do these tasks with more speed, depth, and accuracy than ever before.
At the same time, “the most challenging aspect of developing AI is ensuring that it acts in a trustworthy way under all conditions that may be encountered in the field,” observed Church. “It’s difficult, time-consuming, and expensive to predict every possible scenario and train AI accordingly. Granted, there are advances that will help. One is simply time. With more development time, effort and investment, AI will continue to improve as the number of unfamiliar scenarios declines. As well, advances in adaptive technology, shared learning, and the like will help AI adapt in real-time to unfamiliar scenarios, learn continuously, and share its learnings across a population to improve and accelerate the training of each AI agent in the group.”
The bottom line: Although AI is transforming the rotorcraft industry, humans appear destined to retain their roles in its management and operations.
For all these reasons, the likely future will be one of AI/human partnerships, rather than AI taking over on its own. “People tend to think that AI means the absence of a human operator,” said Church. “Rather, it often means trustworthy decision-making for and with humans. After all, a partnership between human and machine can create a better outcome compared to either acting alone. A human-machine team can accomplish more complex missions, increasing the number, breadth, or duration of tasks that can be completed. This kind of AI is something we are using effectively today, and it will continue to expand and improve year after year.”
READ MORE ROTOR PRO: https://justhelicopters.com/Magazine
WATCH ROTOR PRO YOUTUBE CHANNEL: https://buff.ly/3Md0T3y
You can also find us on
Instagram - https://www.instagram.com/rotorpro1
Facebook - https://www.facebook.com/rotorpro1
Twitter - https://twitter.com/justhelicopters
LinkedIn - https://www.linkedin.com/company/rotorpro1