Tag: RAeS AEROSPACE

RAeS Article: AI, Autonomy, and Human-Machine Teaming Become Rising Forces of Change in Aviation

By Shawn Weil, Chief Growth Officer, Aptima, and Member, AIAA SciTech Forum Guiding Coalition; and Scott Fouse, Aerospace R&D Domain Lead and AIAA SciTech Forum Executive Producer, AIAA

Originally published in the November issue of RAeS AEROSPACE

Aviation is where artificial intelligence (AI) and human-machine teaming with autonomy has become mainstream, beginning initially as assistance for fighter jets in terrain avoidance in the 1980s. Today we see it in commercial jet operations with automatic co-pilots.

Now it’s time to expand AI-powered machine-learning autonomy systems in aviation. There’s an opportunity to focus on applications training to help guide the human-machine teaming for improving aircraft performance and reducing pilot risk.

Engineers are tweaking the relationship between pilot and AI to address concerns about autonomy in a more complex aviation system. The early models of autonomy in aviation have given way to a much more nuanced and complex view of autonomy, where tradeoffs can be made in different ways for different circumstances.

While that autonomy work is still in its infancy, the development of vehicles with autonomous system operations actually dates back to the 1940s in the automobile industry. A blind automotive engineer invented cruise control, an autonomous system that began the process of a broader, more adaptive autonomous system for automobiles. Today, fully autonomous taxi cabs are roaming the streets of San Francisco, aggregating data and updating machine learning capabilities as they transport fares across the city.

Aviation engineers are taking a cue from the automotive industry and exploring the lessons learned about the process of AI-powered autonomy. How should it be implemented in a plane? How should a pilot interface with it? How can a pilot know and anticipate what the autonomy is actually in control of and what the pilot is responsible for?

To address those questions, engineers have honed their systems interfaces, re-designed workflow, and created other externalized cognition tools built on data collection and aggregation. Ultimately what engineers want to create is an autonomous system where they have both high levels of automation and high levels of control. They want to make autonomy a full-fledged member of the flight team that is in some sense omniscient because it’s receiving information from more sensors than the human partner could.

AI won’t replace people in the cockpit. But it may, in fact, amplify their efforts.

Meanwhile, aviation engineers are trying out new ways of using autonomy. One example the U.S. Air Force (USAF) is exploring is the concept of the automated wingman. Here, a piloted aircraft might be flying with two or three autonomous aircraft around it, anticipating the pilot’s next move. These drones are not just reacting to the pilot’s commands, but they’re reacting to the pilot’s intent. They can anticipate the pilot’s actions. The USAF is currently ramping up plans for using 1,000 autonomous drones to assist jetfighters, calling them collaborative combat aircraft.

Aviation engineers are beginning to understand that perhaps the whole science of human autonomy interaction from a cognitive systems point of view has to be rethought. Training should be created to help the pilots know more than just how to fly the aircraft, but also how to manage, understand, and anticipate the autonomous system.

Now the real work in AI-powered machine-learning autonomy for aviation begins. Learn more during the 2024 AIAA SciTech Forum, 8–12 January, Orlando, Florida. A number of panel discussions and technical papers presented throughout the forum will help the aviation industry move the autonomy and human-machine teaming work forward.

RAeS Article: Engineers Weigh in on the Design Freedom of GenAI in Aerospace

Rocket propulsion and other next-gen aerospace systems increasingly depend on GenAI models—a force for democratizing design.

By Greg Zacharias, Aerospace R&D Domain Lead and Executive Producer, AIAA SciTech Forum.

Originally published in the November issue of RAeS AEROSPACE.

From nuclear-thermal rockets to hypersonic aircraft, today’s aerospace systems are increasingly complex, relying on lighter-weight 3D-printed materials, as well as advanced structures, which can include a mix of different materials and thermal-management technologies. The control over form offered by 3D printing means that these components are exceptionally complex, requiring aerospace engineers to develop innovative design approaches. Not surprisingly, some of the most promising approaches tap into generative artificial intelligence, or GenAI, which will be featured at the upcoming 2025 AIAA SciTech Forum in January in Orlando, Florida.

“GenAI is more than just ChatGPT; it has applications in engineering design and it’s going to be used in critical engineering components in the not-so-distant future,” says Zachary Cordero, the Esther and Harold E. Edgerton Associate Professor in MIT’s Department of Aeronautics and Astronautics, who will present in two sessions at the forum. GenAI systems leverage vast datasets to autonomously generate novel solutions and designs, enhancing innovation and applications in diverse fields.

“GenAI is extremely powerful if you have a lot of data,” notes Faez Ahmed, Assistant Professor of Mechanical Engineering, who leads the MIT Design Computation & Digital Engineering (DeCoDE) Lab in the MIT Center for Computational Science and Engineering (CCSE), an interdisciplinary research and education center focused on innovative methods and applications of computation.

The lack of data for learning models – the oxygen that fuels GenAI training – is the biggest bottleneck, Ahmed adds. “Whenever someone says GenAI doesn’t work, a lot of times it’s not the model; it’s the lack of data.”

The DeCoDE Lab bridges this gap by creating design datasets, often by performing a lot of high-fidelity engineering simulations, including recent work for the automobile industry. The Lab created one of the largest and most comprehensive multimodal datasets for aerodynamic car design named DrivAerNet++, which comprises 8,000 diverse car designs modelled with high-fidelity computational fluid dynamics simulations.

Ahmed emphasises that his MIT team doesn’t always use data from good designs but also develops methods to leverage negative data, since bad designs “are cheap and much easier to get.”

Cordero’s Aerospace Materials and Structures Lab at MIT is pushing the boundaries of additive manufacturing for spaceflight through developing new processes and materials. Cordero is collaborating with Ahmed and MIT Research Scientist Cyril Picard on a US Department of Defense-funded research project on the design of next-generation reusable rocket engines.

According to Picard, the team is using GenAI to assess mechanical and thermal properties of materials to inform the design of 3D-printed multi-material parts, with the “long-term goal of making the engines more high-performing, efficient and lighter.”

Looking across the aerospace sector, GenAI offers many benefits, from optimising materials to reducing costly late-stage design changes when scaling production to enabling rapid validation and qualification, say the researchers.

To Ahmed, the biggest benefit of GenAI goes beyond making better products faster: it affords the time for people to explore new designs while also opening up design to innovators outside of traditional aerospace fields.

“I’m personally really excited about this idea of democratisation of design. Historically, design has been limited to the headquarters of major industries. But with tools, like GenAI, we can tap into the creative potential of people with good ideas, but who aren’t necessarily experts.”

Join MIT and dozens of other worldleading aerospace companies and research institutions at the 2025 AIAA SciTech Forum, 6–10 January 2025, Orlando, Florida. AIAA SciTech Forum is the premier aerospace R&D event of the year that explores the science, technologies and capabilities that are transforming aerospace.

Aviation Week Article: Agility Matters: Accelerating Aerospace Autonomy

Cross-Industry Collaboration Needed to Advance Autonomous Systems in Air & Space

By Greg Zacharias, Aerospace R&D Domain Lead and Executive Producer, AIAA SciTech Forum.

Originally published in the October issue of Aviation Week.

Agility matters when designing new capabilities like autonomous aircraft. So does thinking and partnering non-traditionally—it can lead to breakthroughs.

Who would have thought that the Secretary of the U.S. Air Force would fly on a X-62 VISTA fully controlled by a neural network? By working outside the box, the Air Force Research Laboratory (AFRL) and DARPA partnered together and pulled it off in only five years, not decades.

For the latest flight test in May, U.S. Air Force Secretary Frank Kendall flew on the aircraft, configured to behave like an F-16, where the modified fighter jet performed dogfighting maneuvers autonomously on par with an experienced F-16 pilot.

The feat left an impression on Dr. Kerianne “Yoda” Hobbs. “It changed how I view technical development. It’s non-traditional partnerships and integrated teams that are most effective,” says Hobbs, who serves as the Safe Autonomy Lead at AFRL.

Hobbs is part of AFRL’s Autonomy Capability Team (ACT 3), in which government researchers work directly with large and small businesses and university researchers to change the paradigm of how the Air Force innovates when it comes to autonomous air and space vehicles. They’re using a technique called reinforcement learning to train a neural network to control physical and digital systems.

Hobbs hopes to bring this same spirit of collaboration in aerospace autonomy to a new cross-industry task force.

New Roadmap for Aerospace Autonomy

The American Institute of Aeronautics and Astronautics (AIAA) Autonomy Task Force brings together all sectors of the industry—large and small commercial companies, government agencies, and academia—to drive faster and better collaboration in autonomy innovation across the air and space domains. Its initial focus includes three key functions of autonomous systems: sensing and perception; reasoning and acting, such as verifying that an autonomous entity performed within its delegated and bounded authority; and collaboration and interaction. In this last functional area, multiple autonomous agents such as a constellation of space vehicles may work together to navigate around each other.

The timing couldn’t have been better with the rise in advanced air mobility, a growing commercial presence in space, and rapid developments in defense systems.

Defining Autonomy in Aerospace

What is meant by aerospace autonomy? There isn’t an agreed-upon definition across the industry. The task force’s working definition is “a robotic air or space system set to achieve goals with delegated and bounded authority while operating independently or with limited external control.” Autonomous aerospace systems are categorized as either safety critical or mission critical, with the former applying when humans are involved and the latter more applicable to a robotic mission. Unlike traditional robotics that perform a single task, today’s autonomous vehicles need to be adaptive to a broken tread or a flash of sunlight on a sensor, but not so independent that the system would deviate and compromise the mission. The emphasis is on setting a boundary around what the autonomous system is allowed to do and how it’s allowed to operate. Technologies such as run time assurance are useful tools to enforce boundaries on autonomous system behavior. Trust plays a role as well, especially in human-autonomous interactions.

Speed and Lessons from Aerospace

A key research gap that the task force hopes to address is in the area of verification and validation (V&V) systems and processes that are cost-effective to implement. While the space domain has a long history of conducting extensive V&V of semiautonomous systems, the air domain is gaining ground in part because of the test opportunities, where getting a quadcopter or a small UAV or even an F-16 is significantly cheaper than procuring a space vehicle for an autonomy test. “Your opportunities to test are few and far between,” says Hobbs of the space environment. The current pace of autonomous system development remains a major concern for Hobbs. Even witnessing the AI-enabled F-16 test flight, which occurred on the AFRL’s VISTA test platform, pinpointed the limitations of current testing. “I realized everything I knew about traditional V&V wasn’t going to help us use this technology fast,” she recalls. Hobbs is challenging her team to ask themselves, “What is the path forward to do this quickly and competitively without compromising safety or mission? What is the right-size approach?”

Lessons from Computing

Aerospace autonomy builders also should embrace the computing industry’s market approaches that focus on the idea of a “minimal viable product,” says Hobbs. Instead of ensuring that all requirements are correct in the beginning of a program, teams can make a small investment as fast as possible to get from the requirements and development phases to ground and flight simulations more quickly. In this way, groups can learn quickly and iterate better autonomous system designs.

High Stakes for Getting Autonomy Right

Much is riding on getting aerospace autonomy right. “We need a strategy to fully harness these technologies. Without it, we risk other countries moving ahead,” warns Hobbs, noting that unequal access to autonomy breakthroughs within the commercial sector could also harm U.S. competitiveness. “The goal is for aerospace to continue to evolve. It’s going to take a tight-knit community across big industry, small industry, government, and academia working together to speed up the development process to catch up to other industries,” she concludes.

Join worldleading aerospace companies and research institutions at the 2025 AIAA SciTech Forum, 6–10 January 2025, Orlando, Florida. AIAA SciTech Forum is the premier aerospace R&D event of the year that explores the science, technologies and capabilities that are transforming aerospace.

Op-Ed: Human-Machine Teaming Key to Aerospace Engineering’s Digital-Driven Future

By Scott Fouse
AIAA Domain Lead for Aerospace R&D; Lockheed Martin Space Systems (Retired); Fouse Consulting Services

Originally published in the November issue of RAeS’ AEROSPACE

Machines that can surpass human intelligence? Today’s artificial intelligence (AI) systems promise to outmatch certain aspects of human brainpower by developing thinking skills of their own. From digital twins to digital threads, aerospace systems are increasingly complex and AI-dependent. How do we find systems engineers (SEs) equipped to manage this complexity – while ensuring our growing reliance on AI doesn’t replace us? Tapping into the full potential of the data revolution for aerospace systems requires us to leverage the best of machine learning models and human ingenuity by harnessing the strengths of each to achieve what neither can do alone.

The world has changed dramatically since I began working in AI and human decision support in 1984. The computational horsepower and the world’s access to data have been game changers – and will no doubt lead to revolutionary breakthroughs in the next 5 to 10 years. While some elements of machine perception have exceeded human performance, one area where machines lag is recognizing and managing context – an area in which humans excel.

Great SEs have been exposed to multiple kinds of systems and bring all that experience to bear when tackling a new problem. How do we tap into SEs who have the right blend of experience in today’s fast-evolving AI environment? To achieve this needed expertise in future aerospace systems will require human-machine teaming (HMT). The new AIAA Transformative System Engineering Task Force is looking at how we accelerate the skillsets of this new breed of engineers. This will be the topic of many sessions during the 2023 AIAA SciTech Forum in National Harbor, Maryland, 23-27 January 2023.

Successful collaboration between humans and intelligent machines depends largely on trust. But as you apply human trust to machines, you begin to anthropomorphize them, asserting other human-like capabilities that aren’t there. It’s better to view AI not as a human, but rather as a different kind of contributor with unique characteristics.

Additionally, as the aerospace community embraces AI, we must ensure we don’t lose the art of design. Instead, we must leverage AI to amplify our ability to do design. Back in 1998, I worked with a car manufacturer that had embraced digital design. They had become reliant on their automated design tools after 10 years and they had lost the art of design, meaning they could only produce designs that the tools allowed them to do. This carmaker’s experience serves as a wake-up call for the aerospace community to avoid similar mistakes on its own AI journey.

The future of HMT is both about changing the way we engineer the system, and the way we operate the system. And AI in the cockpit is one of the factors that makes the systems engineering process so complex. Making AI systems more transparent, perhaps through explanation, will allow SEs to train alongside these intelligent systems. In the case of aircraft (or spacecraft) pilots, they’ll develop instincts about how to work more effectively with this kind of intelligent support.

As we get more effective at developing digital system models, we’ll become better at modeling and characterizing risk. We already are seeing promising potential with digital twins and digital threads, which allow us to recognize potential design issues earlier in the process.

People are now looking at designing a digital twin of a human-machine team. Instead of only monitoring sensors on an aircraft, for instance, the digital twin also would model a pilot’s workload and performance. If the digital twin sees that the pilot is experiencing overload, some tasks could be taken off the pilot’s plate, with the AI acting as an intelligent co-pilot.

In 20 years, this will be the future of aerospace operations: leveraging human-machine teaming to accelerate design and engineering processes from conception to operational capability, resulting in lower costs for ever-more complex systems.

To learn more, attend the 2023 AIAA SciTech Forum, 23–27 January 2023, in National Harbor, Maryland, and online. Digital Day on 26 January will feature a keynote address from the Acubed team on their work in digital twins and digital engineering followed by multiple panels tackling topics such as complex adaptive systems engineering and human-machine teaming.

About the Author
As AIAA’s Aerospace R&D Domain lead, Scott Fouse helps ensure that the U.S. aerospace community focuses on key technologies that will affect future generations of aerospace platforms. His four decades in the aerospace industry have predominantly focused on how Artificial Intelligence (AI) applies to military decision making. Fouse has led three R&D organizations, including directing both the Advanced Technology Labs and Advanced Technology Center for Lockheed Martin. Today, he serves as principal of Fouse Consulting Services, focused on helping companies identify and create technology-enabled futures.