Last week, Kendall got in the cockpit of a self-flying fighter plane during a historic flight at Edwards Air Force Base (KEDW) in California. The aircraft—called the X-62A Variable In-flight Simulator Test Aircraft, or VISTA for short—is a modified F-16 testbed and represents the Air Force’s first foray into aircraft flown entirely by machine learning AI models.

As Kendall and a safety pilot observed, the X-62A completed “a variety of tactical maneuvers utilizing live agents” during a series of test runs. Incredibly, the aircraft was able to simulate aerial dogfighting in real time, without Kendall or the safety pilot ever touching the controls. According to the Associated Press, VISTA flew at more than 550 mph and within 1,000 feet of its opponent—a crewed F-16—during the hourlong simulated battle.

“Before the flight, there was no shortage of questions from teammates and family about flying in this aircraft,” Kendall said. “For me, there was no apprehension, even as the X-62 began to maneuver aggressively against the hostile fighter aircraft.”

It wasn’t VISTA’s first rodeo. In September, the Air Force for the first time flew the uncrewed aircraft in a simulated dogfight versus a piloted F-16 at the Air Force Test Pilot School at Edwards. The department said autonomous demonstrations are continuing at the base through 2024. But Kendall’s decision to get into the cockpit himself represents a new vote of confidence from Air Force leadership.

“The potential for autonomous air-to-air combat has been imaginable for decades, but the reality has remained a distant dream up until now,” said Kendall. “In 2023, the X-62A broke one of the most significant barriers in combat aviation. This is a transformational moment, all made possible by breakthrough accomplishments of the ACE team.”

ACE stands for Air Combat Evolution, a Defense Advanced Research Projects Agency (DARPA) program that seeks to team human pilots with AI and machine-learning systems. The Air Force, an ACE participant, believes the technology could complement or supplement pilots even in complex and potentially dangerous scenarios—such as close-quarters dogfighting.

“AI is really taking the most capable technology you have, putting it together, and using it on problems that previously had to be solved through human decision-making,” said Kendall. “It’s automation of those decisions and it’s very specific.”

ACE developed VISTA in 2020, imbuing it with the unique ability to simulate another aircraft’s flying characteristics. The aircraft received an upgrade in 2022, turning it into a test vehicle for the Air Force’s AI experiments. 

VISTA uses machine learning-based AI agents to test maneuvers and capabilities in real time. These contrast with the heuristic or rules-based AI systems seen on many commercial and military aircraft, which are designed to be predictable and repeatable. Machine learning AI systems, despite being less predictable, are more adept at analyzing complex scenarios on the fly.

“Think of a simulator laboratory that you would have at a research facility,” said Bill Gray, chief test pilot at the Test Pilot School, which leads program management for VISTA. “We have taken that entire simulator laboratory and crammed it into an F-16, and that is VISTA.”

Using machine learning, VISTA picks up on maneuvers in a simulator before applying them to the real world, repeating the process to train itself. DARPA called the aircraft’s first human-AI dogfight in September “a fundamental paradigm shift,” likening it to the inception of AI computers that can defeat human opponents in a game of chess.

Since that maiden voyage, VISTA has completed a few dozen similar demonstrations, advancing to the point that it can actually defeat human pilots in air combat. The technology is not quite ready for actual battle. But the Air Force-led Collaborative Combat Aircraft (CCA) and Next Generation Air Dominance programs are developing thousands of uncrewed aircraft for that purpose, the first of which may be operational by 2028.

The goal of these initiatives is to reduce costs and take humans out of situations where AI could perform equally as well. Some aircraft may even be commanded by crewed fighter jets. The self-flying systems could serve hundreds of different purposes, according to Kendall.

Even within ACE, dogfighting is viewed as only one use case. The idea is that if AI can successfully operate in one of the most dangerous settings in combat, human pilots could trust it to handle other, less dangerous maneuvers. Related U.S. military projects, such as the recently announced Replicator initiative, are exploring AI applications in other aircraft, like drones.

However, autonomous weapons, such as AI-controlled combat aircraft, have raised concerns from various nations, scientists, and humanitarian groups. Even the U.S. Army itself acknowledged the risks of the technology in a 2017 report published in the Army University Press.

“Autonomous weapons systems will find it very hard to determine who is a civilian and who is a combatant, which is difficult even for humans,” researchers wrote. “Allowing AI to make decisions about targeting will most likely result in civilian casualties and unacceptable collateral damage.”

The report further raised concerns about accountability for AI-determined strikes, pointing out that it would be difficult for observers to assign blame to a single human.

The Air Force has countered that AI-controlled aircraft will always have at least some level of human oversight. It also argues that developing the technology is necessary to keep pace with rival militaries designing similar systems, which could be devastating to U.S. airmen.

Notably, China too is developing AI-controlled fighter jets. In March 2023, Chinese military researchers reportedly conducted their own human-AI dogfight, but the human-controlled aircraft was piloted remotely from the ground.

Leading U.S. defense officials in recent years have sounded the alarm on China’s People’s Liberation Army’s growing capabilities, characterizing it as the U.S. military’s biggest “pacing challenge.” The country’s AI flight capabilities are thought to be behind those of the U.S. But fears persist that it may soon catch up.

“In the not too distant future, there will be two types of Air Forces—those who incorporate this technology into their aircraft and those who do not and fall victim to those who do,” said Kendall. “We are in a race—we must keep running, and I am confident we will do so.”

Like this story? We think you’ll also like the Future of FLYING newsletter sent every Thursday afternoon. Sign up now.

The post Air Force Secretary Gets in Cockpit of Self-Flying Fighter Plane appeared first on FLYING Magazine.

I logged in to OpenAI.com and asked to speak to ChatGPT. It presented me with a box where I could insert a question. I began with the most basic of all aeronautical questions: How does a wing produce lift?

“An airplane wing produces lift due to the principles of aerodynamics,” my interlocutor rather tautologically began. It then said that lift is a pressure difference between the upper and lower surfaces of the wing. That was better.

“The shape of the wing, known as an airfoil,” it recklessly continued, “is designed to create this pressure difference. The top surface of the wing is curved, while the bottom surface is relatively flat. This causes the air moving over the top of the wing to travel faster than the air moving below it, according to Bernoulli’s principle.”

Oops. Sorry, Daniel. And the part about the airfoil shape is at best only half true. Symmetrical airfoils produce lift too, and airplanes with cambered airfoils can fly upside-down. The curved-top-flat-bottom error is a common one, and nine out of ten explanations of lift that you find in textbooks and ground school classes parrot it.

Sensing that the chatbot might be a sucker for common misconceptions, I tried a harder question: Is there any danger for an airplane in turning from upwind to downwind?

The bot got off to a flying start, noting that all pattern flying involves such turns. It went on to caution that turning downwind can “increase the airplane’s ground speed beyond safe limits if not managed properly.” This was an odd idea; there are, as far as I know, no “safe limits” when it comes to ground speed. I think we all agree that the more ground speed, the better.

Having stumbled, the chatbot proceeded to a full face plant: “Turning downwind can result in a loss of lift if the angle of attack of the wing is not adjusted to com- pensate for the change in wind direction.” It had fallen into the elementary confusion of airspeed and ground speed that afflicts every novice pilot. I expected better of an omniscient bot.

I wondered how the chatbot would do with a purely technical question. What conditions must be fulfilled, I asked, for an airplane to be longitudinally stable?

Again, the chatbot got off to a good start. “The center of gravity must be forward of the center of lift.” Close enough. Then, however, it went completely off the rails. Seizing upon the widespread but false belief that the horizontal stabilizer always produces a downward force, it pronounced, “The downforce produced by the tail must be sufficient to counteract the nose-up moment generated by the wings at high angles of attack.” This statement is not only false but also self-contradictory, since a downward force on the tail would obviously reinforce, not counteract, any nose-up moment.

Deciding to try a softball question. I asked it what it thought was the most beautiful airplane ever designed. Now, the AI’s creators have taken the precaution of informing it that it is not a person, and so it begins by demurely explaining, “As an AI language model, I don’t have personal opinions or feelings.” (Fat chance! This same bot fell in love with a New York Times reporter last February and tried to browbeat him into leaving his wife.) In its bland, uncontroversial way, however, it did acknowledge that the looks of many airplanes have been admired, and it offered the Connie, Concorde, the 747, and the Spitfire as examples. In this test, at least, it did no worse than a rather prosaic human. Still, I can’t forgive it for snubbing the F-106.

Succumbing to a desire to know how I was perceived in the bot world, I asked it who Peter Garrison is. After correctly reporting that this person had written extensively about aviation safety in FLYING Magazine, it attributed to him more hours than I have in fact logged, several hon- ors that I have not received, and a “significant impact on the aviation industry” of which I am unaware. I wondered whether it knew that I had designed and built an airplane and flown it from the U.S. to Japan and back. I consider this the crowning achievement of my life, apart from once solving the problem of a garage ceiling leak, which was dripping on my work table, by making a hole in the table. Alas, it did not.

I asked it what it thought about the adage that there are old pilots and bold pilots, but no old bold pilots.

“In my opinion,” it began, sounding as if it might have opinions after all, “there is some truth to this saying, although it is not necessarily true in all cases. Flying requires a high level of skill, experience, and judgment, and pilots who take unnecessary risks or fail to manage risks effectively are more likely to experience accidents or other incidents that could shorten their careers or even endanger their lives. On the other hand, pilots who prioritize safety and manage risks effectively are more likely to have long and successful careers in aviation.”

Well, well. The analysis is accurate, the language grammatical, and correctly punctuated. Here, at last, is the bot that is poised to replace me.

Artificial intelligence is evolving incredibly rap- idly. Its milestones pass in weeks, not years or decades. Some of its conversations are creepily human-like. Yet it seems unable to avoid rookie mistakes because the information it gives out does not come from what we humans call “knowledge.” We acquire information, as it does, from myriad sources, but we subject it to criti- cal scrutiny. The greater our previous knowledge, the deeper our experience with and understanding of the subject, the less likely we are to be misled. The bot, possessing neither experience nor previous knowledge, merely trawls its neural net through a sea of written discourse and presents us with whatever gets caught.

I asked ChatGPT whether it judges the reliability of its sources, ranking scientific papers over magazine articles, for instance. It replied that it does, but, even- handed to a fault, it remarked that a good magazine article may be more accurate than a bad scientific paper. It did not explain how it would tell the sheep from the goats, since it has no knowledge of its own; that is for its creators and minders to figure out.

I think my job is secure—for another week, at least.

The post An Aviation Chat with a Bot appeared first on FLYING Magazine.

On Wednesday, San Francisco-based Xwing partnered with Swiss firm Daedalean in a bid to accelerate both companies’ path to market. The intelligent systems developers agreed to share data, knowledge, and processes around artificial intelligence and machine learning as a way to harmonize their approaches to certification.

Xwing makes modular systems designed to integrate with a wide variety of aircraft serving use cases from logistics to aerial firefighting. The firm works with aircraft operators, manufacturers, and government and defense customers to enable ground-supervised flights without a pilot onboard. In April, the company’s Superpilot unmanned aircraft system (UAS) became the first standard category large UAS to receive official FAA project designation.

“At Xwing, we balance our commitment to a strong safety culture with our push for technical innovation,” said Maxime Gariel, president and chief technology officer of Xwing. “Our collaboration with Daedalean underscores this philosophy and the importance we place on sharing data, knowledge, and processes to inform a credible path forward toward certification for the industry as a whole as we work closely with regulators.”

Daedalean , similarly, offers machine learning-based avionics systems for civil aircraft. Through a collaboration with Avidyne, it’s working to certify and bring to market the first such system for general aviation: Pilot Eye, a solution that visually detects non-cooperative traffic. It too has a relationship with the FAA, having published a joint report with the regulator in 2022.

“In this emerging industry, it’s as crucial to collaborate with fellow pioneers as it is to partner with regulators around the world,” said Luuk van Dijk, co-founder and CEO of Daedalean. “With this shared undertaking, we will be able to demonstrate that increasing safety is driving innovation and that a collaborative approach to harmonize regulations and standards ensures that best practices are universally adopted.”

Both companies are “working closely” with the FAA and European Union Aviation Safety Agency (EASA) to certify their machine learning-based safety-critical systems, a category of tech which so far has not appeared on any civil aircraft. The move to autonomy will require a shift in the way regulators certify hardware and software for the cockpit. 

Accordingly, Xwing and Daedalean agreed that creating consensus on their design assurance approaches—via information sharing—is the best way to speed the development of certification guidelines. The partners also believe their collaboration will deliver safer standards than if they worked separately.

Each company has released blueprints of their approach to certification, which they hope will guide regulators as they work to establish an acceptable means of compliance.

Xwing’s Formal and Practical Elements for the Certification of Machine Learning Systems, for example, attempts to outline a model-agnostic, tool-independent framework that could apply to any use case.

Similarly, Daedalean’s Concepts of Design Assurance for Neural Networks, published jointly with EASA, looks to set industry-wide guidance on developing machine learning systems. Already, EASA has used its findings to draft the first usable guidance for Level 1 machine learning applications.

Although those two frameworks were developed independently, Xwing and Daedalean concurred that sharing their expertise will lead to higher levels of safety, and quicker.

In addition to its relationship with the FAA, Xwing owns a contract from AFWERX, the innovation arm of the U.S. Air Force, to trial its Superpilot system aboard a crewed Cessna 208 Caravan. Pilots will offer feedback on its usability. The company was also contracted by NASA to build an autonomous flight safety management system.

Simultaneously, Daedalian is working to ensure its Pilot Eye technology complies with Aerospace Recommended Practice, DO-178C, and field-programmable gate array standards. Partner Avidyne, meanwhile, has applied for a supplemental type certificate for Pilot Eye with the FAA, with concurrent validation from EASA.

Like this story? We think you’ll also like the Future of FLYING newsletter sent every Thursday afternoon. Sign up now.

The post Autonomous Flight Leaders Join Forces in Bid to Speed Certification appeared first on FLYING Magazine.

Rather, the organization is exploring a new way for counter-uncrewed aircraft systems (C-UAS) to talk to each other. Open-source intelligence company Janes reported NATO will adopt the U.K. Ministry of Defense’s (MOD) Sensing for Asset Protection with Integrated Electronic Networked Technology protocol, or SAPIENT, as a “C-UAS standard.”

Essentially, SAPIENT will lay out new guidelines for manufacturers of C-UAS sensors and other technology. The framework emphasizes plug-and-play components, artificial intelligence-based decision making, and a lower burden to acquisition and integration.

In 2024, NATO will begin a yearlong ratification process to adopt SAPIENT as a Standardization Agreement, Cristian Coman, chief scientist for the Joint Intelligence, Surveillance, and Reconnaissance (ISR) division of NATO’s Communications and Information (NCI) Agency, told Janes. It will require the approval of 14 member countries.

Prior to the announcement, the NCI Agency organized a 10-day series of C-UAS exercises in Vredepeel, Netherlands, for NATO’s C-UAS Technical Interoperability Exercise (TIE23), hosted by the organization’s C-UAS Joint Nucleus within the Dutch Ministry of Defense. 

The demonstrations ran from September 12 to 22 and looked at how SAPIENT interacted with some 70 C-UAS systems—including newfangled concepts such as jet-powered drones and net-tossing UAS.

What Is SAPIENT?

Written and sponsored by the U.K. Defense Science and Technology Laboratory (Dstl) and funded by the MOD, SAPIENT was designed as an open architecture that can integrate autonomous sensor information into a single picture. The MOD adopted it as the country’s C-UAS standard in 2019.

“In the SAPIENT system, the individual sensors are advanced, using [AI] to make detections and classifications locally, sending only the information, not the raw data, to the command and control [C2] system,” a summary on the U.K. government’s official website reads.

“They also make operating decisions autonomously, such as which direction to look or whether to zoom in, in order to fulfill higher-level objectives,” it continues. “These higher-level objectives are managed by a decision-making module which controls the overall system and makes some of the decisions normally made by the operators. This reduces the operator’s need to constantly monitor the output of the sensors.”

More specifically, SAPIENT calls for AI algorithms that reside both in the decision-making modules and the onboard sensors themselves. It encourages an architecture in which different sensors use a shared interface to talk to each other, which could reduce integration time and create a competitive market for suppliers.

The system also enables “multisensor fusion,” meaning several different nodes jointly handle tasks such as correlation, association, tracking, and decision-making. In addition to lowering the cognitive burden on operators, it’s expected to reduce the bandwidth requirements for network traffic and the cost of acquiring new tech.

The key export of the program so far has been the interface control document (ICD) standards that tell suppliers how to develop compliant components. But researchers have also developed variants of SAPIENT technologies to demonstrate the concept and weigh its benefits for users.

Most recently, SAPIENT was published by the British Standards Institute as BSI Flex 335, which provides U.K. manufacturers with the first iteration of requirements for producing interfaces between sensor edge, effector, and fusion nodes. BSI Flex, which develops guidelines for markets with rapidly evolving needs, accelerated the standard’s development.

BSI Flex 335 makes a few changes to the most recent version of the ICD, most notably a 60 percent reduction in the communications bandwidth needed to run SAPIENT. The living document is expected to be updated later this year.

SAPIENT was initially evaluated as the interoperability standard for NATO C-UAS systems at TIE21, where it made more than 70 connections between C-UAS sensor systems and C2 modules. The organization revisited it during TIE22, where it connected another 31 autonomous sensor nodes from a who’s who of vendors to 13 decision-making nodes.

The program’s standards, decision-making nodes, and sensors were also deployed in the Contested Urban Environment 2021 (CUE2021) exercise, a multinational experiment that tested it with over 60 technologies. AI technology in the decision-making nodes managed the sensors and provided the multisensor fusion the U.K. MOD covets.

In the future, the ministry will look to stack multiple SAPIENT systems in a hierarchy, which could improve scalability and open more real-life scenarios for deployment. The Dstl has also tasked a cross-industry working group—the SAPIENT Interface Management Panel, or SIMP—with creating a “configuration control framework” around the interface and its tools. The panel is open to all and operates on a nonfunded, voluntary basis.

The Implications of SAPIENT

Mario Behn, principal scientist of the NCI Agency’s Joint ISR, told Janes the purpose of the TIE23 trial was to enhance the interoperability of C-UAS technology through SAPIENT. The exercises involved more than 300 participants from 15 NATO-allied and three partner nations, the European Union, and 57 private sector companies. But could these systems one day show up in Ukraine?

Military, scientific, and industry specialists live-tested around 70 systems and technologies—including sensors, effectors, and jammers—designed to detect, identify, and neutralize enemy UAS. Among them were a “fishing net” interceptor drone from Germany’s Argus Interception, which tosses a small net over the enemy’s aircraft, and a jet-powered drone from DDTS (another German firm) that can fly up to 310 mph to intercept fast-moving UAS.

Britain’s MOD believes the ability for different C-UAS to talk to each other through SAPIENT could one day lead to technology that can take control of enemy drones like a parasite, guiding them to a new target or location.

Representatives from several private companies at TIE23 referenced how these systems could combat low-cost, self-detonating Iranian Shahed drones, which are being deployed in droves by Russia in its war on Ukraine. In theory, SAPIENT could allow Ukrainian forces to fire Shahed drones back at its aggressor.

No Ukrainian officials were present for the exercises. But Claudio Palestini, a NATO science officer, said the organization is having “ongoing discussions” with the country about C-UAS issues. Major General Hans Folmer, a senior NATO officer in the NCI Agency, added SAPIENT will bring “big benefits” to alliance members.

Ukraine is not a NATO member—at least, not yet. At present, it’s a partner country, meaning it works closely with the organization but is not a part of it. However, NATO leaders in July agreed to “expedite” its membership. 

There is no hard date for Ukraine to join NATO. If it does, the adoption of SAPIENT could change the calculus of the war in its favor. That will all depend, though, on current members’ acceptance of the proposed framework.

Like this story? We think you’ll also like the Future of FLYING newsletter sent every Thursday afternoon. Sign up now.

The post NATO Set to Adopt British MOD Standard for Counter-Drone Technology appeared first on FLYING Magazine.

Modernizing ATC 

One of the key components of MOSAIC is the modernization of air traffic control systems. The FAA wants to replace its aging radar-based systems with new, more advanced technologies such as Automatic Dependent Surveillance-Broadcast (ADS-B) and NextGen Data Communications (Data Comm). These new technologies will enable air traffic controllers to have a more precise and accurate picture of aircraft in the airspace, which will allow more efficient aircraft routing and separation.

To improve the overall air travel experience for passengers, MOSAIC seeks to reduce delays and improve flight efficiency by implementing new procedures and technologies such as Performance Based Navigation (PBN) and Airspace Flow Programs (AFP). These new procedures will reduce the risk of collisions and other accidents and enable aircraft to fly more direct routes, reducing flight times and fuel consumption.

• READ MORE: Will MOSAIC Allow LSAs To Do More?

The air traffic control system is critical to airline and passenger safety—and the economy. Air traffic controllers across the United States handle thousands of complex tasks that require constant attention and quick decision-making. Controllers are responsible for the safe and efficient movement of aircraft in the airspace, and they use a variety of tools, including radar, communication systems, and weather information, to do so. However, as air traffic has increased, controllers’ workloads have also grown, increasing concerns about safety and efficiency.

Can AI improve the ATC system?

Artificial Intelligence has the potential to revolutionize the field of ATC by automating repetitive and mundane tasks, improving flight plans, and enhancing both safety and communication. When combined with other advanced technologies, such as ADS-B and NextGen Data Communications, AI systems will be used to process large amounts of ATC data quickly and accurately. They will make decisions and predictions in real-time to improve the overall functionality of the ATC system. 

For example, an AI system could automatically detect and track aircraft in the airspace and generate conflict alerts if two aircraft are on a collision course. When AI is combined with natural language technology, pilot alerts and instructions could be mostly automated, freeing human controllers to focus on other tasks, such as communicating with pilots and coordinating aircraft movements. 

Pilot-to-controller communication should also become more efficient and less prone to errors. Pilots will appreciate faster responses and individual alerts, especially on days when the ATC system is overloaded due to weather events or other issues. 

However, it is important to note that AI is not a magic solution and will not replace human air traffic controllers. AI systems require human supervision, and it will be necessary to have controllers who can intervene and make decisions in situations that an AI system is not able to handle. Additionally, it will take time for the necessary infrastructure and technology to be developed and implemented to make an AI-based system possible.

Unmanned Aerial Systems, Light Sport Aircraft

Another important aspect of the MOSAIC program is the integration of unmanned aircraft systems (UAS) into the national airspace. The FAA is developing regulations and procedures to safely integrate drones into the airspace while addressing security and privacy concerns. This will open up new opportunities for the commercial use of drones, such as package delivery and aerial surveying, while reducing the number of manned aircraft in the airspace and the risk of collisions.

In addition to the modernization of air traffic control systems and the integration of UAS, MOSAIC also includes proposed changes to the rules for light sport aircraft (LSA), defined as small, lightweight aircraft typically used for recreation and training. The new LSA rules will focus on increasing safety and accessibility for pilots and aircraft owners.

The new rules will include changes to the LSA certification process, making it easier for aircraft manufacturers to certify this type of aircraft while ensuring that they meet specific safety standards. This will make it more cost-effective for aircraft manufacturers to produce LSAs, which will in turn make them more affordable for pilots and aircraft owners.

The new rules will also include changes to the requirements for pilots who operate LSAs. The FAA is expected to reduce the minimum number of flight hours required for pilots to fly LSAs, making it easier for individuals to obtain a pilot’s license and allowing more pilots to have access to these aircraft.

New rules are also expected to include changes to LSA operating limitations, allowing pilots to fly them in more challenging weather conditions and at higher altitudes. These proposed rules will make LSAs more versatile and useful for a wider range of applications, such as aerial surveying and photography.

Review and Approval Process

The MOSAIC proposals are part of the FAA’s long-term effort to modernize the NAS. Originally scheduled to be announced in 2022, a MOSAIC notice of proposed rulemaking (NPRM) is currently scheduled to be ready by August. However, before any new regulations are implemented, once the NPRM is released, there will be a period for public comment, and then a final rule will be published. The specific timing for each step of the process can vary depending on the complexity of the rule, and the volume of public comments received.  

Whatever parts of the MOSAIC proposal that are approved likely will be implemented in phases;  it is expected to be a multi-year process that will continue to evolve as new technologies and procedures are developed. 

The post AI Aims to Enhance Aviation Safety, Reduce Delays appeared first on FLYING Magazine.

The recent exercise is an advancement toward a “military Metaverse” for combat flight training that allows multiple pilots to communicate at the same time while using a synthetic training environment, Red 6 said in an announcement made during the UP.Summit mobility conference underway this week in Bentonville, Arkansas.

During the test flight, pilots in two Berkut 540 experimental aircraft departed Santa Monica Airport (KSMO) in California and entered Red 6’s AR environment, called the Combined Augmented Reality Battlespace Operation Network (CARBON).

• Virtual Reality in Flight Training: More Than a Fad

Once linked in CARBON, the pilots could see and interact with an AR generated Boeing KC-46 Pegasus Tanker. Through AR, one pilot conducted a training mission with the tanker, while the other pilot observed in real time.

“We are thrilled that our thesis has been validated, and this achievement is a major step forward towards the creation of an outdoor Military Metaverse in which all warfighters, across all domains can train together,” said Daniel Robinson, founder and CEO of Red 6, in a statement. 

The test flight comes two years after Red 6 conducted what it said was the “world-first live dogfight” against a virtual aircraft driven by artificial intelligence.

“The flight showcased the groundbreaking display and control systems needed to bring AR into the real world, while simultaneously integrating tactical AI into the Red 6 system,” the company said.

Red 6 is now looking at AR solutions on the ground, according to Robinson.

“We are in the early stages of exploring dismounted solutions and the ability to connect a dismounted soldier to pilots in an airplane to allow them to see a common picture,” he told FLYING.

• Augmented Reality Brings Jets Into The Classroom

The aviation industry is increasingly turning to AR, for applications from air traffic control operations to pilot training. 

Last fall, students at Embry-Riddle Aeronautical University, Prescott, developed AR holograms that create 3D models of the CRJ-700 and allow the student to move around inside the aircraft systems.

The post Military Metaverse: Red 6 Conducts Multi-Aircraft Augmented Reality Training Flight appeared first on FLYING Magazine.