F-35, F-22 Artificial Intelligence to Control Drones in the Air
By Kris Osborn
Test enemy air defenses or perform intelligence, reconnaissance and surveillance missions in high risk areas, senior Air Force officials said.
Citing ongoing progress with computer algorithms and some degree of AI (artificial intelligence) already engineered into the F-35, Air Force Chief Scientist Gregory Zacharias said that technology was progressing quickly at the Air Force Research Lab - to the point where much higher degrees of autonomy and manned-unmanned teaming is expected to emerge in the near future.
“This involves an attempt to have another platform fly alongside a human, perhaps serving as a weapons truck carrying a bunch of missiles,” Zacharias said in an interview with Scout Warrior.
An F-35 computer system, Autonomic Logistics Information System, involves early applications of artificial intelligence wherein computers make assessments, go through checklists, organize information and make some decisions by themselves – without needing human intervention.
“We are working on making platforms more autonomous with multi-int fusion systems and data from across different intel streams,” Zacharias explained.
The computer, called ALIS, makes the aircraft’s logistics tail more automated and is able to radio back information about engine health or other avionics.
A single, secure information environment provides users with up-to-date information on any of these areas using web-enabled applications on a distributed network, a statement from ALIS- builder Lockheed Martin says.
ALIS serves as the information infrastructure for the F-35, transmitting aircraft health and maintenance action information to the appropriate users on a globally-distributed network to technicians worldwide, the statement continues.
However, despite the promise of advancing computer technology and increasingly levels of autonomy, Zacharias emphasized that dynamic human cognition is, in many respects, far more capable than computers.
Computers can more quickly complete checklists and various procedures, whereas human perception abilities can more quickly process changing information in many respects.
“A computer might have to go through a big long checklist, whereas a pilot might immediately know that the engines are out without going through a checklist. He is able to make a quicker decision about where to land,” Zacharias said.
The F-35s so-called “sensor fusion” uses computer algorithms to acquire, distill, organize and present otherwise disparate pieces of intelligence into a single picture for the pilot. The technology, Zacharias said, also exhibit some early implementations of artificial intelligence.
Systems such as a 360-degree sensor suite, called the Distributed Aperture System, is linked with targeting technologies, such as the aircraft’s Electro-Optical Targeting System.
F-35 to Control Drones
As a result, F-35 pilots will be able to control a small group of drones flying nearby from the aircraft cockpit in the air, performing sensing, reconnaissance and targeting functions.
At the moment, the flight path, sensor payload and weapons disposal of airborne drones such as Air Force Predators and Reapers are coordinated from ground control stations.
“The more autonomy and intelligence you can put on these vehicles, the more useful they will become,” Zacharias said.
This development could greatly enhance mission scope, flexibility and effectiveness by enabling a fighter jet to conduct a mission with more weapons, sensors, targeting technology and cargo, Zacharias explained.
For instance, real-time video feeds from the electro-optical/infrared sensors on board an Air Force Predator, Reaper or Global Hawk drone could go directly into an F-35 cockpit, without needing to go to a ground control station. This could speed up targeting and tactical input from drones on reconnaisance missions in the vicinity of where a fighter pilot might want to attack. In fast-moving combat circumstances involving both air-to-air and air-to-ground threats, increased speed could make a large difference.
“It’s almost inevitable people will be saying - I want more missiles on board to get through defenses or I need some EW (electronic warfare) countermeasures because I don't have the payload to carry a super big pod,” he explained. “A high powered microwave may have some potential that will require a dedicated platform. The negative side is you have to watch out that you don’t overload the pilot,” Zacharias added.
In addition, drones could be programmed to fly into heavily defended or high-risk areas ahead of manned-fighter jets in order to assess enemy air defenses and reduce risk to pilots.
“Decision aides will be in cockpit or on the ground and more platform oriented autonomous systems. A wing-man, for instance, might be carrying extra weapons, conduct ISR tasks or help to defend an area,” he said.
Advances in computer power, processing speed and areas referred to as “artificial intelligence” are rapidly changing the scope of what platforms are able to perform without needing human intervention. This is mostly developing in the form of what Zacharias referred to as “decision aide support,” meaning machines will be able to better interpret, organize, analyze and communicate information to a much greater extent – without have humans manage each individual task.
“A person comes in and does command and control while having a drone execute functions. The resource allocation will be done by humans,” Zacharias said.
Another advantage of these technological advances is that one human may have an ability to control multiple drones and perform a command and control function – while drones execute various tasks such as sensor functions, targeting, weapons transport or electronic warfare activities.
At the moment, multiple humans are often needed to control a single drone, and new algorithms increasing autonomy for drones could greatly change this ratio. Zacharias explained a potential future scenario wherein one human is able to control 10 – or even 100 - drones.
Algorithms could progress to the point where a drone, such as a Predator or a Reaper, might be able to follow a fighter aircraft by itself – without needing its flight path navigated from human direction from the ground.
Unlike ground robotics wherein autonomy algorithms have to contend with an ability to move quickly in relation to unanticipated developments and other moving objects, simple autonomous flight guidance from the air is much more manageable to accomplish.
Since there are often fewer obstacles in the air compared with the ground, drones above the ground can be programmed more easily to fly toward certain pre-determined locations, often called a “way-points.”
At the same time, unanticipated movements, objects or combat circumstances can easily occur in the skies as well, Zacharias said.
“The hardest thing is ground robotics. I think that is really tough. I think the air basically is today effectively a solved problem. The question is what happens when you have to react more to your environment and a threat is coming after you,” he said.
As a result, scientists are now working on advancing autonomy to the point where a drone can, for example, be programmed to spoof a radar system, see where threats are and more quickly identify targets independently.
“We will get beyond simple guidance and control and will get into tactics and execution,” Zacharias added.
Wargames, exercises and simulations are one of the ways the Air Force is working to advance autonomous technologies.
“Right now we are using lots of bandwidth to send our real-time video. One of the things that we have is a smarter on-board processor. These systems can learn over time and be a force multiplier. There's plenty of opportunity to go beyond the code base of an original designer and work on a greater ability to sense your environment or sense what your teammate might be telling you as a human,” he said.
For example, with advances in computer technology, autonomy and artificial intelligence, drones will be able to stay above a certain area and identify particular identified relevant objects or targets at certain times, without needing a human operator, Zacharias added.
This is particularly relevant because the exorbitant amount of ISR video feeds collected needs organizing algorithms and technology to help process and sift through the vast volumes of gathered footage – in order to pinpoint and communicate what is tactically relevant.
“With image processing and pattern recognition, you could just send a signal instead of using up all this bandwidth saying ‘hey I just saw something 30-seconds ago you might want to look at the video feed I am sending right now,’” he explained.
The Army has advanced manned-unmanned teaming technology in its helicopter fleet --successfully engineering Apache and Kiowa air crews to control UAS flight paths and sensor payloads from the air in the cockpit. Army officials say this technology has yielded successful combat results in Afghanistan.
Senior Air Force leaders have said that the services' new next-generation bomber program, the B-21 Raider, will be engineered to fly manned and unmanned missions.
Also, in September of 2013, the Air Force and Boeing flew an unmanned F-16 Falcon at supersonic speeds for the first time at Tyndall Air Force Base, Fla. The unmanned fighter was able to launch, maneuver and return to base without a pilot.
At the same time, despite the speed at which unmanned technology is progressing, many scientist and weapons’ developers are of the view that human pilots will still be needed – given the speed at which the human brain can quickly respond to unanticipated developments.
There is often a two-second long lag time before a UAS in the air can respond to or implement directions from a remote pilot in a ground station, a circumstance which underscores the need for manned pilots when it comes to fighter jets, Air Force officials said.
Therefore, while cargo planes or bombers with less of a need to maneuver in the skies might be more easily able to embrace autonomous flight – fighter jets will still greatly benefit from human piloting, Air Force scientists have said.
While computer processing speed and algorithms continue to evolve at an alarming pace, it still remains difficult to engineer a machine able to instantly respond to other moving objects or emerging circumstances, Air Force scientists have argued.
However, sensor technology is progressing quickly to the point where fighter pilots will increasingly be able to identify threats at much greater distances, therefore remove the need to dogfight. As a result, there may be room for an unmanned fighter jet in the not-too-distant future, given the pace of improving autonomous technology.