Skip to main content

By Kris Osborn - Warrior Maven

(Washington, D.C.) The Air Force Research Lab is flying autonomous drones able to navigate uneven, rigorous terrain, independently find and transmit target specifics, perform manned-unmanned teaming missions and operate a large number of functions without needing pilot control. 

Newer applications of software, hardware and computing could also possibly lead to unmanned-unmanned teaming and wherein autonomous drones operate swarms of attritable mini drones designed to blanket an area with surveillance, test enemy air defenses, find targets over high-threat areas and perhaps themselves function as mini-explosives.

Skyborg Autonomy Core System Program

This growing mission scope is enabled by the service’s emerging Skyborg Autonomy Core System program, a suite of integrated sensing, computing and payload technologies engineered for greater operational autonomy and manned-unmanned systems. 

Following a successful first flight in April 2021 on board a Kratos UTAP-22 drone, the Air Force Research Laboratory recently conducted a second flight with Skyborg ACS on a General Atomics MQ-20 Avenger.

The flight, which took place at Edwards Air Force Base, Calif., is part of a critical AFRL prototyping effort to introduce new levels of autonomy into air war, therefore greatly expanding the mission envelope.

U.S. Air Force Skyborg Autonomy Core System

The Skyborg autonomy core system launches aboard a Kratos UTAP-22 tactical unmanned vehicle at Tyndall Air Force Base, Fla, April 29, 2021. (U.S. Air Force photo)

Humans will of course maintain supervisory command and control and, per Pentagon doctrine, ensure any use of lethal force is decided upon by a human pilot. However, Skyborg ACS will introduce breakthrough levels of autonomy enabling drones to perform a much wider sphere of operations without needing each individual action directed by a human.

“Military pilots receive key information about their surroundings when teamed aircraft with integrated autonomy detect potential air and ground threats, determine threat proximity, analyze imminent danger, and identify suitable options for striking or evading enemy aircraft,” an Air Force Research Laboratory paper on Skyborg says. “The program will enable airborne combat mass by building a transferable autonomy foundation for a family of layered, unmanned air vehicles.”

Modernized Technology

Skyborg ACS is enabled by advanced computer algorithms engineered to gather, distill, organize, analyze, solve problems and ultimately streamline key data points of relevance to humans.

“Embedded within the teamed aircraft, complex algorithms and cutting-edge sensors enable the autonomy to make decisions based on established rules of engagement set by manned teammates,” the AFRL paper says.

Additional field testing and development of Skyborg ACS is being planned to further ensure the algorithm's accuracy and performance consistency. 

U.S. Air Force Skyborg

The Skyborg autonomy core system launches aboard a Kratos UTAP-22 tactical unmanned vehicle at Tyndall Air Force Base, Fla., April 29, 2021. (U.S. Air Force photo)

Scroll to Continue

Recommended for You

As testing and technical maturation continues to progress, the possibilities with a technology of this kind are quite significant. For many years now, aerial drones have been able to follow GPS-determined “waypoints,” however greater autonomy will likely enable drones to independently adjust to new information such as target movements or emerging terrain obstacles. 

This decreases the procedural functions human pilots need to perform, therefore moving toward establishing an optimal blend of man and machine in combat. The long-term plan with autonomy, is to

The tactical advantages are numerous, as a greater ability for drones to perform a wider range of functions without needing human intervention could enable extended ranges, greater mission scopes, in-flight adjustments and perhaps an ability for a single pilot to supervise a small fleet of drones. 

Humans will remain in a Command and Control role, yet many procedural functions such as target data processing, route adjustments, networking and information analysis will be done by AI-enabled computers, freeing up human pilot to use those faculties unique to human cognition such as intuition, reasoning and ability to weight numerous more subjective variables in relation to one another.

General Atomics MQ-20 Avenger Drone

Use of GA’s Avenger drone is quite significant, given that Skyborg introduces new levels of autonomy into an advanced, jet-powered drone capable of producing 5,000 pounds of thrust. This means the Avenger can operate with a runway length under 5,000 feet, GA data explains. 

The Avenger is also fast, as it is able to reach speeds of 400 Knots and can reach altitudes above 50,000 feet. Like other drones, an unmanned system such as Avenger brings levels of endurance not sustainable by human pilots, as it can operate for more than 20 hours on a single mission.

U.S. Air Force Skyborg General Atomics

A General Atomics MQ-20 Avenger unmanned vehicle returns to El Mirage Airfield, Calif. June 24, 2021. The MQ-20 successfully participated in Edwards Air Force Base’s Orange Flag 21-2 to test the Skyborg Autonomy Core System. (Photo courtesy of General Atomics)

Weapons capacity is also a critical factor, because while decisions about lethal attack will be made by humans, a well-armed Avenger can independently find targets and bring weapons into position for optimal strike positions.

“Its significant wing hardpoint payload mounting capacity enables it to carry multiple sensors, while its internal weapons bay can house 3,000 pounds of precision munitions or larger sensor payloads,” a General Atomics statement says.

Greater levels of autonomy can also bring yet another unprecedented attribute … speed. In many cases, especially those infused with AI-capable systems, perform millions of procedural functions in seconds while also conducting near “real-time” analytics sufficient to organize data and identify crucial items of interest. 

AI-capable computing can instantly assess a host of otherwise disparate or disconnected variables to coordinate an integrated battlefield picture for human decision-makers, such as which methods of attack have proven the most effective. 

For example, moving target specifics can be compared against previously compiled details to discern an optimal method of attack, something which could even recommend a weapon of choice for an Avenger pilot making the ultimate decision about a strike.

-- Kris Osborn is the Managing Editor of Warrior Maven and The Defense Editor of The National Interest -- 

Kris Osborn is the defense editor for the National Interest. Osborn previously served at the Pentagon as a Highly Qualified Expert with the Office of the Assistant Secretary of the Army—Acquisition, Logistics & Technology. Osborn has also worked as an anchor and on-air military specialist at national TV networks. He has appeared as a guest military expert on Fox News, MSNBC, The Military Channel, and The History Channel. He also has a Master's Degree in Comparative Literature from Columbia University.