Back to news

July 6, 2021 | International, C4ISR, Security

The Air Force Skyborg AI Flight Program is Getting Smarter, Stealthier

The artificial intelligence piloting program is rapidly gaining experience and could fly alongside manned pilots in the not-so-distant future.

https://nationalinterest.org/blog/buzz/air-force-skyborg-ai-flight-program-getting-smarter-stealthier-189085

On the same subject

  • Saab delivers first Global Eye early-warning plane to UAE

    April 30, 2020 | International, Aerospace

    Saab delivers first Global Eye early-warning plane to UAE

    By: Sebastian Sprenger COLOGNE, Germany — Saab has delivered its first GlobalEye early-warning plane to the United Arab Emirates, the company announced Wednesday. The aircraft arrived in Dubai during the late morning of April 29 following a brief stopover in Bulgaria on its way from Sweden, Saab CEO Micael Johansson said during a call with reporters. The delivery caps four and a half years of work since the UAE and Saab signed a contract for three of the planes — modified Bombardier 6000 business jets equipped with Saab's Erieye long-range radar and other surveillance sensors. Saab is advertising GlobalEye as able to provide ground, air and maritime surveillance in a single package. “The delivery of the first GlobalEye is a major milestone for Saab, but also an important step in the history of airborne early warning and control,” Johansson said. “We have set a new standard for the market, and I am proud to say that we have delivered the most advanced airborne surveillance solution in the world to the United Arab Emirates.” The company, which has been spared from work stoppages in Sweden caused elsewhere by the coronavirus pandemic, had to take “a number of mitigating actions” to prevent the virus from spreading during the actual handover and during the weeks leading up to it, Johansson said. The measures included testing workers for the virus, quarantining them if warranted and retesting them afterward, according to Johansson. Saab is still working to produce the additional two aircraft owed under the 2015 contract. Those would be delivered “rather shortly,” the executive told reporters, declining to be more specific. The company is eyeing the potential sale of yet two more GlobalEye aircraft to the UAE. Such an option is included in the original deal, though details have yet to be finalized. Johansson cited Finland and South Korea as countries also interested in the GlobalEye technology. If Saab manages to drum up additional customers, future offerings are slated to include the Global 6500 jet as carriers, he said. https://www.defensenews.com/global/europe/2020/04/29/saab-delivers-first-global-eye-early-warning-plane-to-uae

  • How the Office of Naval Research hopes to revolutionize manufacturing

    October 16, 2018 | International, Naval

    How the Office of Naval Research hopes to revolutionize manufacturing

    By: Daniel Cebul WASHINGTON — The Office of Naval Research awarded Lockheed Martin Oct. 1 a two-year, $5.8 million contract to explore how machine learning and artificial intelligence can make complex 3-D printing more reliable and save hours of tedious post-production inspections. In today's factories, 3-D printing parts requires persistent monitoring by specialists to ensure intricate parts are produced without impurities and imperfections that can compromise the integrity of the part overall. To improve this laborious process, the Navy is tasking Lockheed Martin with developing multi-axis robots that use lasers to deposit material and oversee the printing of parts. Lockheed Martin has multiple partners on the contract including Carnegie Mellon University, Iowa State University, Colorado School of Mines, America Makes, GKN and Wolf Robotics and Oak Ridge National Laboratory. The contract covers what Glynn Adams, a senior engineer with Lockheed Martin, describes as the pre-flight model of the program's development. Initial work will focus on developing computer models that can predict the microstructures and mechanical properties of 3-D printed materials to generate simulation data to train with. Adams said the Carnegie Mellon team will look at variables such as, “the spot size of the laser beam, the rate of feed of the titanium wire [and]the total amount energy density input into the material while it is being manufactured.” This information helps the team predict the microstructure, or organizational structure of a material on a very small scale, that influences the physical properties of the additive manufactured part. This data will then be shared with Iowa State, who will plug the information into a model that predicts the mechanical properties of the printed component. By taking temperature and spot size measurements, the team can also ensure they are, “accurately controlling energy density, the power of both the laser and the hot wire that goes into the process,” Adams said.. “All of that is happening before you actually try to do any kind of machine learning or artificial neural networks with the robot itself. That's just to try to train the models to the point where we have confidence in the models,” Adams said. Sounds easy, right? But one key problem could come in cleaning up the data and removing excess noise from the measurements. “Thermal measurements are pretty easy and not data intensive, but when you start looking at optical measurements you can collect just an enormous amount of data that is difficult to manage,” Adams explained. Lockheed Martin wants to learn how shrink the size of that dataset without sacrificing key parameters. The Colorado School of Mines and America Makes will tackle the problem of compressing and manipulating this data to extract the key information needed to train the algorithms. After this work has been completed, the algorithms then will be sent to Oak Ridge National Laboratory, where robots will begin producing 3-D titanium parts and learn how to reliably construct geometrically and structurally sound parts. This portion of the program will confront challenges from the additive manufacturing and AI components of the project. On the additive manufacturing side, the team will work with new manufacturing process, “trying to understand exactly what the primary, secondary and tertiary interactions are between all those different process parameters,” Adams said. “If you think about it, as you are building the part depending on the geometric complexity, now those interactions change based on the path the robot has to take to manufacture that part. One of the biggest challenges is going to be to understand exactly which of those parameters are the primary, which are the tertiary and to what level of control we need to be able to manipulate or control those process parameters in order to generate the confidence in the parts that we want.” At the same time, researchers also will tackle AI machine learning challenges. Like with other AI programs, it's crucial the algorithm is learning the right information, the right way. The models will give the algorithms a good starting point, but Adams said this will be an iterative process that depends on the algorithm's ability to self-correct. “At some point, there are some inaccuracies that could come into that model,” Adams explained. “So now, the system itself has to understand it may be getting into a regime that is not going to produce the mechanical properties or microstructures that you want, and be able to self-correct to make certain that instead of going into that regime it goes into a regime that produces the geometric part that you want.” With a complete algorithm that can be trusted to produce structurally sound 3-D printed parts, time-consuming post-production inspections will become a thing of the past. Instead of nondestructive inspections and evaluations, if you “have enough control on the process, enough in situ measurements, enough models to show that that process and the robot performed exactly as you thought it would, and produced a part that you know what its capabilities are going to be, you can immediately deploy that part,” said Adams. “That's the end game, that's what we're trying to get to, is to build the quality into the part instead of inspecting it in afterwards." Confidence in 3-D printed parts could have dramatic consequences for soldiers are across the services. As opposed to waiting for replacement parts, service members could readily search a database of components, find the part they need and have a replacement they can trust in hours rather than days or weeks. “When you can trust a robotic system to make a quality part, that opens the door to who can build usable parts and where you build them,” said Zach Loftus, Lockheed Martin Fellow for additive manufacturing. “Think about sustainment and how a maintainer can print a replacement part at sea, or a mechanic print a replacement part for a truck deep in the desert. This takes 3-D printing to the next, big step of deployment.” https://www.c4isrnet.com/industry/2018/10/15/how-the-office-of-naval-research-hopes-to-revolutionize-manufacturing

  • Lockheed slated to miss F-35 delivery target in 2020 as supply chain struggles to keep up

    May 20, 2020 | International, Aerospace

    Lockheed slated to miss F-35 delivery target in 2020 as supply chain struggles to keep up

    By: Valerie Insinna   20 hours ago WASHINGTON — Lockheed Martin will throttle back the pace of F-35 production on May 23, leaving it anywhere from 18 to 24 jets short of the 141 scheduled for delivery this year. The COVID-19 pandemic has made it more difficult for Lockheed's supply chain to make components on time, and as a result the company is moving to an adjusted work schedule where production will slow over the next three months, said Greg Ulmer, Lockheed's vice president for the F-35 program. Ultimately, Lockheed aims to accelerate production as soon as possible and hopes to decrease the number of aircraft that will delivered late. However, Ulmer said there are too many variables to say precisely how long buyers will be left waiting for their F-35s. “If I have the ability to speed up or recover sooner, then I will do so,” Ulmer said. “If there are other unknown COVID-19 impacts that I don't know about that come on the horizon — I don't know that either. ... As we go forward, probably late summer or early fall, we'll have a pretty good sense of where we're going to be.” Beginning on May 23, Lockheed will divide the approximately 2,500 employees who staff the F-35 production line in Fort Worth, Texas, into three groups, moving them to new schedule where each group works for two weeks and then has a week off. After one three-week rotation, the company will determine whether the system is successful and can either alter the schedule or continue until Sept. 4, it said in a statement. Rotating smaller groups of employees on the line allows Lockheed to move to a slower pace of operations while at the same time ensuring that workers retain their expertise and don't need to be retrained when the production rate returns to normal, Ulmer said. “It really maximizes our ability to recover production on the backside and retain our workforce with no loss of learning.” Lockheed Martin executives first disclosed that F-35 deliveries could be delayed during an April 21 earnings call with investors. “There are local distancing requirements that are being more stringently applied across the globe. There is workforce disruption,” Kenneth Possenriede, the company's chief financial officer, said at the time. “We've actually had some issues with shipping constraints.” Most of the supply chain pressure on the program stems from constraints on low-tier suppliers that produce components that feed into larger portions of the F-35. While the production line tries to do as much work on each section as possible, workers are having to slow down and wait for missing parts to arrive, Ulmer said. Lockheed has also had challenges getting connectors for the jet on time — another problem that makes it difficult for the company to merge F-35 sub-assemblies into a finished aircraft, Ulmer said. Once aircraft are completed and go through acceptance testing, the sequence of deliveries will remain the same, he said. The slowdown of the F-35's production rate comes days after President Donald Trump voiced support for moving more of the jet's production to the United States. Currently, international partners who helped fund development of the F-35 can compete for work on the jet, reducing the cost of the aircraft and giving foreign buyers an industrial incentive to support the program. “The problem is if we have a problem with a country, you can't make the jet. We get parts from all over the place. It's so crazy. We should make everything in the United States,” Trump said on Thursday. However, the industrial challenges currently faced by Lockheed do not appear to be caused by the international supply base. Ulmer said European suppliers, who were hardest hit before the United States, are now rebounding from the pandemic. “I really see Europe kind of [on the] leading edge of the recovery side of this,” he said. In particular, northern Italy struggled with high numbers of confirmed COVID-19 cases, leading Italian defense firm Leonardo, which runs an F-35 final assembly and check out plant in Cameri, to shut down operations over a two day period in March to clean the facility. With the number of new cases receding, Italy began reopening nonessential businesses this month. “Leonardo today is north of 90 percent manned, fully operating. They're pretty much back to normal operations,” Ulmer said. The ongoing expulsion of Turkish suppliers from the F-35 program is also unlikely to be affected by the production slowdown at Fort Worth, as Lockheed has already identified companies to take over that work, he said. “With the vast majority of those, that alternate sourcing has been accomplished. I really don't see this as an impact to that." Ramping production back up Unless COVID-19 cases spike in the coming months, Lockheed believes it will be able to return workers to a normal production schedule in the late summer or early fall. What will vary is timing for when suppliers can return to their usual production rates, and whether those suppliers have the capacity to expedite the manufacturing of key parts, Ulmer said. Once the supply chain has fully recovered, it will take the Fort Wort line two to three months to resume full rate production. “There are 1,900 suppliers across the program” in the United States, Ulmer said. “So we take all that information in, we determine what rate they can deliver to, we determine if they have any kind of constraints we can help them deal with, and then we have to balance that into the production system to dial in the production rate we can execute.” “I am optimistic that the majority of industry is on the backside. I'm reluctant to say that because there could be a rebound,” Ulmer said, “but we're at the very back end of the impact.” https://www.defensenews.com/breaking-news/2020/05/19/lockheed-to-slow-f-35-production-as-supply-chain-struggles-to-keep-up

All news