Volume 01 | Issue 12 | August 25, 2020
AI Dogfighting, Spectrum & Insurance

Welcome back to the Future of Aerospace.

The FAA’s solicitation for drone detection and mitigation systems has been released, beginning the agency’s likely years-long process of creating standards for safe use of these systems near airports.

Ten detection and mitigation systems will be tested first at Atlantic City International Airport and then potentially at one or more of four other airports, which are yet to be determined. Testing is expected to take a total of 18 months, so don’t hold your breath for an advisory circular.

In today’s issue, we cover: Connectivity, Autonomy & AI, and something that’s hard to categorize…insurance!

Thanks for reading.

—The Future of Aerospace Team
Compatibility, Standards Key to Future Growth of Aviation Spectrum Applications in US
Spectrum remains one of the greatest barriers to introducing new wireless applications and services for communications, navigation and surveillance on aircraft flying within U.S. airspace.

Breaking that barrier will require some unique decision-making and collaborative spectrum sharing and re-purposing by government and industry stakeholders, according to experts featured on a recent RTCA broadcast.

The FAA is already the nation’s second largest government agency user of spectrum, and air transportation faces competition from other industries that seek to share or use adjacent frequency bands used for safety of life aeronautical communications.

5G and L-band Digital Aeronautical Communications System (LDACS) are two technologies with near term potential use in aviation. But as radio and transceiver manufacturers start to consider development of aircraft systems that use these two new spectrum-dependent signals, their compatibility with other aviation spectrum transmissions needs to be addressed through minimum operational performance standards.

“There are no unused frequencies left,” said Andrew Roy, director of engineering services for Aviation Spectrum Resources Inc.
  • The FAA has already made efforts to repurpose some of the spectrum it has been assigned in support of safety of life transmissions for several decades.

  • One example: The introduction of AeroMACS, a WiMAX system the enables wireless broadband connectivity use by aircraft terminals on airport surfaces, has required some repurposing of the 5 GHz band historically used in the U.S. in support of the microwave landing system (MLS).

  • Michael Richmond, manager of the Spectrum International and Planning Team, Spectrum Engineering Services Group at the FAA: “When regulators consider new allocations, the considerations should be, what will be the impact to incumbent systems, that are co-channeled or adjacent channeled.”

  • The 960-1215 MHz band features some of the most frequency-intensive aviation transmissions, including: Automatic Dependent Surveillance-Broadcast (ADS-B)’ Tactical Air Navigation (TACAN); Secondary Surveillance Radar (SSR), and military Identification Friend or Foe (IFF) transmissions.

  • “If you throw a spectrum analyzer at it and you go across 960-1215, you see continuous peak above the noise floor there,” said Dr. Sai Kalyanaraman, a technical fellow at Collins Aerospace, where he oversees GNSS receiver design and development.
Commercial airline pilots could also see major benefits as a result of the introduction of LDACs, 5G, AeroMACS and other next generation wireless aircraft communications applications.

“We as the end user want to be able to take advantage of a lot of those technologies, 5G being one of them, Internet Protocol being another one, and we need to explore ways to get a lot of this data and communication onto and off of the airplane,” said David Sambrano, chief technical pilot communications, United Airlines.

Read the full story here.
Heron Systems Shows Future Potential of AI in Win Over Top F-16 Weapons Instructor
Heron Systems Inc. defeated an F-16 weapons instructor during the conclusion of DARPA's Alpha Dog fighter AI competition on Aug. 21. (DARPA)

Heron Systems was declared the winner of the Defense Advanced Research Projects Agency (DARPA) AlphaDogfight trials between artificial intelligence (AI)-enabled F-16 simulators and U.S. Air Force, Navy, and Marine Corps pilots.

The Air Force picked eight teams to compete last year to show advanced AI algorithms to permit autonomous F-16 dogfighting. The teams were Boeing‘s Aurora Flight Sciences, Lockheed Martin, Perspecta Labs, EpiSys Science, Inc., Heron Systems, PhysicsAI, SoarTech, and the Georgia Tech Research Institute.

How Heron, a small business of 30 employees, defeated one of the U.S. Air Force’s most experienced F-16 weapons instructors in all five rounds of a simulated battle restricted to use of the nose cannon only:
  • Benjamin Bell, a senior machine learning engineer at Heron Systems, Inc., said afterward that he believed one of the advantages of their AI agent was the way they configured its neural network combat learning capabilities.

  • Bell: “Our advantages were that we were only using reinforcement learning, so we tried to create an action scheme where the neural network can control the plane in a way that is both smooth, which you didn’t see our competitors doing, but also at a high enough rate that we’re able to make some of those high aspect shots and keep that machine level targeting of our opponents."

  • “We were trying to create smooth output so that we’re not spazzing on the control and controlling around 10 hertz actually, most of our competitors seemed like they were controlling at around 50 hertz, and one of the nice parts is it helps the agent to be certain. If it is limited in controlling the plane, then when it lines up for the plane it has to know that the trajectory from now until the next three seconds is going to keep its opponent in that one degree cone and win the game."

  • Justin “Glock Mock,” an Air Force weapons school graduate, described the AI targeting capabilities provided by Heron Systems as “superhuman,” while cautioning that the simulation was still a far cry from going out and doing real F-16 combat training. One of the major differences for example was that Heron’s AI agent has perfect state information about both machines, which is something that never happens in actual theater.
Read the full story here.
How Flock Provides Real-Time, Risk-Adjusted Insurance to Human and AI Drone Pilots
Image: Flock Cover

Last month, Flock Cover was widely reported as the “first company to insure an [artificial intelligence] AI pilot” as it signed a deal with Lorenz Technology to insure its AI-Link autonomous system, a small attachment for drones that allows for autonomous flight, primarily used for visual data collection by the maritime, security and facility management industries.

But how Flock insured the AI pilot may be the least interesting part of the company, which claims to have a lower loss ratio (read: a more accurate grasp of risks) than other companies offering insurance to drone operators.

Quantifying the risk of drone operations is precisely the problem regulators are grappling with as they attempt to allow more complex operations in more crowded environments. For Flock, it’s a matter of pulling in the right data. The level of a pilot — human or AI — is just one of those data points.
  • Flock’s product: The London-based insurance tech startup sells insurance, underwritten by Allianz, to individual or enterprise drone operators that is priced based on a real-time risk profile of the intended operation.

  • Data feeds: Pilot experience, drone model, projected weather conditions, airspace type, and nearby population density and high-risk facilities (such as schools) are all fed into the company’s risk intelligence engine.

    Sam Golden, Flock’s sales and marketing lead: “We require from manufacturers a spec sheet on the drone … the information that is used in the calculation for risk includes what kind of propulsion system it’s using, the operating temperatures of the batteries, the wind resistance of the craft, the diameter of the wing span and whether it is a fixed-wing or multirotor drone.”

  • From Flock’s perspective, with tens of thousands of flights insured, it is still very much the early days of drone operations and most customers are not using unmanned traffic management services to create strategic risk mitigation at this point. But customers that do “will benefit from our policies,” according to Golden.
Back to the AI pilot: Insuring autonomy is simple for Flock — just treat the AI as a pilot.

Golden: “It’s listed as a pilot on the insurance policy, so as it gains more experience without claims, it’s classified as a safer pilot and therefore the insurance costs will go down over time.”

The real benefit is for Lorenz’s customers (or the customers of other AI pilots).

“That means that a company that has zero drone experience can essentially buy off the shelf a qualified drone pilot with a thousand hours of experience.”
Thank you for reading the Future of Aerospace, brought to you by Aviation Today.

View in web browser

This message was sent to lhofmann@accessintel.com

Access Intelligence LLC * 9211 Corporate Blvd., 4th Floor, Rockville, MD 20850
Unsubscribe | Privacy Policy | Contact Us