Air Combat Drones

[CoffmanStarter]

The link below covers an interesting article that appeared in "Popular Science" earlier this month mentioning that the US DARPA Organisation (Defense Advanced Research Projects Agency) is to look at the use of Drones/UAV's in the Air-to-Air combat role. The article also suggests a "mixed" use of such technology with manned aircraft.

DARPA : Teaching Drones to Fight Aircraft (http://www.popsci.com/article/technology/darpa-wants-teach-drones-fight-airplanes?dom=PSC&loc=recent&lnk=3&con=darpa-wants-to-teach-drones-to-fight-airplanes)

Just setting aside for a moment the technical challenges that will need to be overcome ... it might be interesting to speculate on what a future Air Combat Drone/UAV deployed capability might look like.

For example ... would it be best to control Air Combat Drones/UAV's from the ground (as with current Reconnaissance or Ordnance delivery UAV's), or controlled from the air by something like a Sentry ... or is it conceivable that a Fighter Pilot could even have Drones/UAV's as Wingmen that could then be deployed in a "fight"?

I suspect there will be some very experienced members who might say "it will never happen" ... but looking at the way military technology is progressing in this field ... it may not be too farfetched.

Coff.

[Eclectic]

Semi autonomous drones are well within current technology.
Tell them what is friendly and what is unfriendly within designated airspace.
Give them a sensor suite.
Existing technology weapons with full envelope data in the computer.
Software for air combat manoeuvring.
Predictive algorithms.
Rules of engagement.
Tactical priorities.
20G airframe.

Then you could mix and match them safely with manned aircraft.

[awblain]

Command delay. With a satellite link time-of-flight delay at the 0.2s level, there's going to have to be some considerable degree of autonomy. Plus, the satellite link can break for certain periods, and could be susceptible to concerted jamming.

Direct radio control via relay aircraft would be quicker.

Who wants to explain to the judge why the airliner was bumped by the intercepting drone having a senior moment?

[air pig]

Sounds like a Dale Brown techo novel coming true.

[safetypee]

From ‘Foyle’s War’; “Why did you survive when others did not, you must have been good?”
“No they (compatriots) were good; they used the conventional tactics which were countered with conventional response. I survived because I didn’t follow the rules and the opposition did not know what to expect.”

What drone will be able to think and act like that?

[gr4techie]

Air Combat Drones

SAM vs cruise missile ?

[tartare]

Knucky of the future, thy wingman shall be autonomous and be able to pull 20G.
"Watch my six" will be a button push away, or even a voice recognised command.
And the only thing that I think will be able to defeat such a UCAV will be a minaturised fast jet mounted HELLADS...

[Hempy]

if you look at the required specs, I'd say we'll be able to compare prices with the F-35 and see how much a pilot is worth. I'm guessing you can add another $200 mill for the luxury of being pilotless....

p.s which is only to say, just because it 'can' be done doesn't necessarily mean it should be done..

[Fox3WheresMyBanana]

Against unsophisticated opposition AD pilots in an environment where who is who is reasonably known, then it can probably be done in 10 years.
I think having a drone as a wingman should be the first step - human leader allocates targets.

[tartare]

I wonder if it is actually being tested as we speak.
Watch this video (https://www.youtube.com/watch?v=iNSHSBziyOo) from March 03.
Bunch of tomahawks flying in close formation.
If that could happen then, what's possible a decade later?

[500N]

Was always impressed by that piece of video. Just showed the capabilities of the Cruise Missile even back then.

I read that they flew very close to the border of some countries because the terrain in a lot of other parts was so plain it made it hard to navigate ?

[500N]

It was the Zargos Mountains in Iran.

[unmanned_droid]

Tartare, great vid, I haven't seen that one before.

Still massively impressed by the video of a Tomahawk flying down a street at roof top level in the first gulf war.

[tartare]

Was thinking about what UCAVs could really look like in reality.
Imagine an F35, with a 4 ship formation of UCAVs off his wingtip, flying in a perfect diamond formation each no more than a few metres apart.
Bogeys sighted - the pilot gives the Tally Ho command, and they snap out of formation in four different directions at rates of climb, negative G pushovers or rates of turn that seem like something out of a science fiction movie.
It's a chilling thought.

[500N]

tartare

And the bogeys don't even know they are there until simultaneous explosions
down the aircraft ?

[tartare]

Yes - exactly.
I've often wondered what kind of manned aircraft defence could kill an unmanned adversary that can easily tolerate +/-20g maneuverability and the very low wing loadings that some of these UCAV designs appear likely to have in future.

Probably only a laser, a minaturised aircraft mounted version of this (http://www.truthdig.com/eartotheground/item/anti_aircraft_laser_cannons_are_here_video_20130409), or some kind of ventral or dorsal self targeting gun turret, with the ability to move and train at extreme speed - coupled with a prodigious rate of fire - a sort of airborne close-in weapon system.
Maybe people who know more about ACM than I do can contribute... I assume the issue is how quickly a UCAV would be able to change its vector?

[Flap62]

We spend vast amounts on expensive aircraft with radar and DASS suites and yet they are limited in combat by the numbers of missiles they carry. The first step will be a "drone" which follows the sensor platform and carries another 8-12 missiles, targeted by the piloted main platform....probably.

[CoffmanStarter]

Thanks for everyones contribution ... it's certainly interesting to speculate on what might constitute a future viable Air Combat Drone capability. But as mentioned by Safetypee, the human brain remains the most agile and flexible CPU ever developed ... and will remain so for a very long time to come ... albeit that it is contained within a "package" that is now nearing the upper end of safe G tolerance. With the human body probably not safely withstanding much above -3/+9G this may be one of the primary drivers in progressing AC Drone solutions?

The Drone "Wingman" approach would bring a whole set of new challenges I guess ... not least ... how would you launch in a QRA scenario ... let alone how do you overcome command and control latency issues as some have highlighted above.

Definitely a "watch this space topic" I think ...

[awblain]

Those lasers are heavy and expensive, and will probably remain so.

They also need very fancy optics to ensure they concentrate on the target, and the lighter and less powerful they are, the more that's true.

To achieve 20g without stopping dead there has to be a lot of power, and that's expensive. Drones are relatively cheap because they cruise and loiter stealthily with light simple engines - if you want them to run like an unmanned F22 then the cost will go up.

Eyes also gather a lot of information, and it's going to be difficult to provide that remotely without a big and complex set of cameras that might cost more than the career training and salary of the person they're replacing (who still needs to be paid to be somewhere on the ground).

[500N]

How about non stealth drones to draw out the enemy, present a bigger target than they actually are and then when close to being engaged, stealth aircraft used to combat the enemy without them knowing ?

Possible loss of a drone for a higher success rate and low probability of crew loss ?

[tartare]

Blain - you think so?
I'm not so sure.
Some of the brightest minds in the `states are making sure that the laser problems are all solveable.
100 - 150kw class is what they're targeting - and HELLADS (https://en.wikipedia.org/wiki/High_Energy_Liquid_Laser_Area_Defense_System) is roadmapped to be aircraft mounted - maximum onboard space ocuupiued to be no more than 2 cubic m.
In fact several elements of JSF design are oriented towards integration of a high powered laser - power is not an issue; you take it off the engine; cooling is in fact one of the biggest practical problems, and you use fuel as the heat sink.
Interestingly, one of the real challenges they face is dealing with the optical distortions introduced by airflow around the laser turret. Adaptive optics continue to progress at a great rate, driven by IMINT needs for spy satellites and high altitude airborne platforms.
Some more detail here on when a laser might appear on the JSF (file:///C:/Documents%20and%20Settings/jamiesond/My%20Documents/Downloads/ADA515549.pdf).
Admittedly a 2007 paper, but even then the conclusion? A HEL laser could be fieldable by 2025.
R/e high G turns - all you have to do is exceed 9G, at which point the poor meat-pilot you're fighting succumbs to G-LOC...?
No doubt somewhere in the USAF or at Lockheed Martin a young accolyte of John Boyd is looking at drag polar charts for planned UCAVs and thinking about just these things.

[awblain]

There are good reasons that the 747 airborne laser is no longer.
Maybe it'll be viable at some point. Certainly seems unlikely before 2025.

Beyond 9g is difficult for people to deal with, but matters have gotten out of hand if that's necessary for success.

[GreenKnight121]

There are good reasons that the 747 airborne laser is no longer.

Yes - its a laser using 30+ year-old technology for a start.

The size that this forces meant a large aircraft to carry it, but newer laser technology provides the same power in a much smaller & lighter package.

The same goes for the mechanical components - and all of this also applies for the aiming system, power generator, etc.


Additionally, it was an ABM program, meaning it required a longer-range fire-control system, a longer-range focusing system, higher power to overcome atmospheric attenuation of the beam's power, and so on.


The one being designed to fit inside the lift-fan space on a modified F-35B airframe is intended for much closer range, with the attendant reductions in required power, capability of the tracking & aiming system, and so on.

[ORAC]

https://dtdnnp-01.darpa.mil/news-events/2019-05-08

DARPA: Training AI to Win a Dogfight

“.........The ACE program will train AI in the rules of aerial dogfighting similar to how new fighter pilots are taught, starting with basic fighter maneuvers in simple, one-on-one scenarios. While highly nonlinear in behavior, dogfights have a clearly defined objective, measureable outcome, and the inherent physical limitations of aircraft dynamics, making them a good test case for advanced tactical automation. Like human pilot combat training, the AI performance expansion will be closely monitored by fighter instructor pilots in the autonomous aircraft, which will help co-evolve tactics with the technology. These subject matter experts will play a key role throughout the program.

“Only after human pilots are confident that the AI algorithms are trustworthy in handling bounded, transparent and predictable behaviors will the aerial engagement scenarios increase in difficulty and realism,” Javorsek said. “Following virtual testing, we plan to demonstrate the dogfighting algorithms on sub-scale aircraft leading ultimately to live, full-scale manned-unmanned team dogfighting with operationally representative aircraft.”

DARPA seeks a broad spectrum of potential proposers for each area of study, including small companies and academics with little previous experience with the Defense Department. To that end, before Phase 1 of the program begins, DARPA will sponsor a stand-alone, limited-scope effort focused on the first technical area: automating individual tactical behavior for one-on-one dogfights. Called the “AlphaDogfight Trials,” this initial solicitation will be issued by AFWERX, an Air Force innovation catalyst with the mission of finding novel solutions to Air Force challenges at startup speed. The AFWERX trials will pit AI dogfighting algorithms against each other in a tournament-style competition...........”

[Wingless Walrus]

For example ... would it be best to control Air Combat Drones/UAV's from the ground (as with current Reconnaissance or Ordnance delivery UAV's), or controlled from the air by something like a Sentry ... or is it conceivable that a Fighter Pilot could even have Drones/UAV's as Wingmen that could then be deployed in a "fight"?
Coff.

Took a quick look on the web and found some interesting articles.

Drone shoots down drone:
The little known story of how a US Air Force MQ-9 Reaper shot down another drone with a heat seeking missile
https://fightersweep.com/12293/the-little-known-story-of-how-a-us-air-force-mq-9-reaper-shot-down-another-drone-with-a-heat-seeking-missile/

DARPA tech lets one pilot control multiple aircraft using only their brain
https://fightersweep.com/12291/darpa-tech-lets-one-pilot-control-multiple-aircraft-using-only-their-brain/

The Skyborg Program: The Air Force’s new plan to give fighter pilots drone sidekicks
https://fightersweep.com/12241/the-skyborg-program-the-air-forces-new-plan-to-give-fighter-pilots-drone-sidekicks/

Thread drift but maybe of interest:
Declassified supersonic spy drone flew multiple failed missions over China in the 1960s
https://fightersweep.com/12316/declassified-supersonic-spy-drone-flew-multiple-failed-missions-over-china-in-the-1960s/

War of the drones is on the horizon. It was also predicted by Nostradamus, according to a book I read in the 90's interpreting his writings of the future. Shame it didn't mention Euro-millions lottery numbers.

[Sun Who]

https://www.boeing.com/defense/airpower-teaming-system/index.page

[ORAC]

https://www.airforcemag.com/air-force-to-test-fighter-drone-against-human-pilot/

Air Force to Test Fighter Drone Against Human Pilot

[Bob Viking]

The detail that is missing from that article is what kind of fight are we talking about?

If it is a BVR scenario then I’m sure AI decision making could beat the human by a second or two.

If we are talking guns kills then I remain to be convinced it is worth the effort. Maybe the AI can eke out a few more bernouillis than a human.

In the world of all-aspect, high off-boresight missiles BFM (assuming no pre-merge kills) then, yes, the AI may well be able to get a firing solution quicker than a human.

Regardless of all of this, even the AI will still be constrained by the limits of radar and weapons.

It’s an interesting experiment that could go either way I suggest.

BV

[ORAC]

AlphaDogfight Trials Final will be streamed live on YouTube ? Alert 5 (http://alert5.com/2020/08/20/alphadogfight-trials-final-will-be-streamed-live-on-youtube/)

AlphaDogfight Trials Final will be streamed live on YouTube

The final event of Darpa’s AlphaDogfight Trials will be streamed live on YouTube Aug. 21. The winning AI team will go against a U.S. Air Force F-16 pilot.

DARPA’s AlphaDogfight Trials seeks to advance the state of artificial intelligence (AI) technologies applied to air combat operations. The trials are a computer-based competition designed to demonstrate advanced AI algorithms that can perform simulated within-visual-range air combat maneuvering, otherwise known as a dogfight. The goal is to use the dogfight as the challenge problem to increase performance and trust in AI algorithms and bring together the AI research and operator communities.

https://youtu.be/NzdhIA2S35w

[Darren_P]

https://youtu.be/kyfriipc61A

[ORAC]

https://youtu.be/kTROMPq1SAA

[NutLoose]

Well there are a couple of Reapers down over Syria, US says they had a mid air but other side claiming shot down as you would.

https://www.popularmechanics.com/military/aviation/a33647798/us-military-reaper-drones-collide-over-syria/

https://www.thedrive.com/the-war-zone/35775/two-mq-9-reaper-drones-collide-over-syria-after-days-of-sightings-from-those-on-the-ground

[ORAC]

Not air combat drones and the subject being discussed - and already up on the Syria thread.

https://www.pprune.org/military-aviation/513470-here-comes-syria-128.html#post10864773

[oldmansquipper]

https://link.defenseone.com/click/21272362.92918/aHR0cHM6Ly93d3cuZGVmZW5zZW9uZS5jb20vdGVjaG5vbG9neS8yMDIwLzA4 L2FpLWp1c3QtYmVhdC1odW1hbi1mLTE2LXBpbG90LWRvZ2ZpZ2h0LWFnYWlu LzE2Nzg3Mi8_b3JlZj1kZWZlbnNlX29uZV9icmVha2luZ19ubA/5f3990b01a42e5366b405197Bb0d80f36

[Fonsini]

Better start considering those alternate careers.

AI Controlled F-16 Defeats Pilot (https://uk.yahoo.com/news/ai-pilot-thoroughly-beats-human-095004286.html)

An AI pilot has defeated a US Air Force pilot in a virtual F-16 dogfight in a "coming of age" moment for artificial intelligence (http://www.independent.co.uk/topic/artificial-intelligence).

The US military's AlphaDogfight Trials was organised by the Defense Advanced Research Projects Agency (Darpa (http://www.independent.co.uk/topic/darpa)) - a secretive branch of the US Department of Defense responsible for the development of futuristic technologies.

It sought to demonstrate the "feasibility of developing effective, intelligent autonomous agents capable of defeating adversary aircraft in a dogfight."

The winning AI pilot, developed by Heron Systems, defeated other AI adversaries before going on to beat a human pilot wearing a VR helmet by a score of 5 - 0 in the final.

"We've gotten an opportunity to watch AI come of age [against] a very credible adversary in the human pilot," said Col. Dan Javorsek, program manager in Darpa's Strategic Technology Office.

"The AlphaDogfight Trials is all about increasing trust in AI. If the champion AI earns the respect of an F-16 pilot, we'll have come one step closer to achieving effective human-machine teaming in air combat."

The human pilot, who went by the name 'Banger', said that he was unable to match twisting techniques adopted by the AI pilot that he had not witnessed in human-to-human air combat.

"Standard things we do as fighter pilots are not working," he said during a live broadcast.

[NutLoose]

The question at the end of the day has to be what is the point? If you build an AI fighter and so presumably does your opposition to counter the threat, then the eventual outcome comes down to resources and attrition. It becomes a war won simply on production rates not on lost lives and a defeated population if that makes sense, which seems a pointless exercise to start with....

I can understand why an AI aircraft will eventually win out as an F16 with a pilot will always have to operate with in the limits of the pilots tolerance to G etc, a AI version is free from that constraint. It was one advantage Bader held over his German counterparts, without legs and the problems of blood pooling in his lower extremities, he was more G tolerant than his opposition.

[stilton]

The question at the end of the day has to be what is the point? If you build an AI fighter and so presumably does your opposition to counter the threat, then the eventual outcome comes down to resources and attrition. It becomes a war won simply on production rates not on lost lives and a defeated population if that makes sense, which seems a pointless exercise to start with....

I can understand why an AI aircraft will eventually win out as an F16 with a pilot will always have to operate with in the limits of the pilots tolerance to G etc, a AI version is free from that constraint. It was one advantage Bader held over his German counterparts, without legs and the problems of blood pooling in his lower extremities, he was more G tolerant than his opposition.


Good point


It just becomes a game of destroying each other’s expensive drones


Can’t see how an advantage is gained

[typerated]

Good point


It just becomes a game of destroying each other’s expensive drones


Can’t see how an advantage is gained


Really? What do you think warfare is?

It is just cutting the middle man out!

[stilton]

Really? What do you think warfare is?

It is just cutting the middle man out!


Disagree,


War at its most basic level is won by killing more of their people than they kill yours

[finestkind]

Disagree,


War at its most basic level is won by killing more of their people than they kill yoursMaybe at it's basic you are correct .But in the evolution of warfare from the castle keep scenario where a castle (or Genghis Khan sack the city) is taken and all are slaughtered to prevent retribution, to opposing armies facing off against each other in an open field whilst the populace is entertained on the hillside, to total war of which civilians are included an AI evolution might just be less brutal. You can see when one side has depleted it’s AI resources the only option is surrender as when faced with superior AI against human opponents it’s a no win.

[typerated]

Disagree,


War at its most basic level is won by killing more of their people than they kill yours

Wrong. Totally utterly wrong!

let me quote ― Sun Tzu,

“The supreme art of war is to subdue the enemy without fighting.”

or perhaps Clausewitz

“War is nothing but a continuation of politics.”

or “To achieve victory we must mass our forces at the hub of all power and movement. The enemy’s "center of gravity”

No mention of killing the most - What a ridiculous thought!

[stilton]

You still don’t win until you own the land of your invader


No matter how many of his gadgets you shoot down, in the end his people have to be subjugated


That’s why Normandy and the retaking of Axis Europe was necessary, the air war and the bombing raids were not enough


It still requires boots on the ground

[typerated]

You still don’t win until you own the land of your invader


No matter how many of his gadgets you shoot down, in the end his people have to be subjugated


That’s why Normandy and the retaking of Axis Europe was necessary, the air war and the bombing raids were not enough


It still requires boots on the ground

so you have changed your argument from killing the most to occupying the ground to win- and guess what!

Still wrong!

Perhaps quit while you are losing!

but let me give you some examples to ponder : Czechoslovakia 1938
Singapore 1942
Japan 1945

[beardy]

Disagree,


War at its most basic level is won by killing more of their people than they kill yours
I always thought that it was about gaining and holding ground.

[pr00ne]

beardy,

So how did the RAF win the Battle of Britain then?

[Mogwi]

beardy,

So how did the RAF win the Battle of Britain then?

It was the only "battle" where the enemy was not aware that there was one going on!

Mog

[beardy]

beardy,

So how did the RAF win the Battle of Britain then?
A battle that was part of a war which was won by gaining and holding territory.

[NutLoose]

Wrong. Totally utterly wrong!

let me quote ― Sun Tzu,

“The supreme art of war is to subdue the enemy without fighting.”

or perhaps Clausewitz

“War is nothing but a continuation of politics.”

or “To achieve victory we must mass our forces at the hub of all power and movement. The enemy’s "center of gravity”

No mention of killing the most - What a ridiculous thought!

Ok so all your AI asset takes out the other sides AI air capability and your tech on the ground takes out their tech on the ground..... end result you have won that war by out spending and out “teching” the opposition” But you haven’t won the war because all you have done is dominate the battle space without subduing the populace.

Afghanistan was “won” by dominating the airspace and destroying their heavier assets on the ground, but crucially they never In reality subdued the populace, those fighting melted away, and hence they “won” a war similar to the AI to AI you envisaged .

Now because you haven’t subdued the population you have to stick troops on the ground, but not in sufficient numbers to again totally subdue and dominate the population, this results in you having to build little defensive positions from which to operate while not actually controlling the Country you have supposedly taken.

It also leads to the scenarios where you build a base to protect a road that had no previous problems, but because the base is there the road now becomes a target to kill those protecting it... not exactly winning a war is it...

To win a war you need to destroy not just their tech, but also those on the ground actively participating in it, and that means killing them. Something that appears to have worked with some effect against ISIS.

[GlobalNav]

Aside from the philosophical arguments about what war is, AI drones don’t affect that, but may alter the balance of power in an air supremacy/dominance contest. They don’t have to completely replace manned fighters to have significant impact, but they may become an important contributor. Even if they didn’t always win a dogfight they could keep the enemy very occupied while other friendly forces perform their missions. Not to be trite, but they could be a force multiplier.

[etudiant]

The question at the end of the day has to be what is the point? If you build an AI fighter and so presumably does your opposition to counter the threat, then the eventual outcome comes down to resources and attrition. It becomes a war won simply on production rates not on lost lives and a defeated population if that makes sense, which seems a pointless exercise to start with....

I can understand why an AI aircraft will eventually win out as an F16 with a pilot will always have to operate with in the limits of the pilots tolerance to G etc, a AI version is free from that constraint. It was one advantage Bader held over his German counterparts, without legs and the problems of blood pooling in his lower extremities, he was more G tolerant than his opposition.

Surely this is more akin to the introduction of the 'Dreadnought' by Lord Fisher. He successfully cleared the decks for the Kaiser to start a battleship race by obsoleting the existing Royal Navy battle line, so all started from scratch.
This AI drone similarly potentially eliminates the US advantage of thousands of trained aircrews, leaving the competition to depend on production capacity, where China has or will soon have a substantial advantage.

[typerated]

Surely this is more akin to the introduction of the 'Dreadnought' by Lord Fisher. He successfully cleared the decks for the Kaiser to start a battleship race by obsoleting the existing Royal Navy battle line, so all started from scratch.
This AI drone similarly potentially eliminates the US advantage of thousands of trained aircrews, leaving the competition to depend on production capacity, where China has or will soon have a substantial advantage.
interesting point.

[John Eacott]

I'm still unsure how this (https://www.pprune.org/10867086-post35.html) has morphed into a categorical assumption that a drone will beat a live human in A2A combat? It was a simulation, not a real exercise, where a drone operator (on a computer) beat an F16 pilot (on a computer) with a result that can only be as real as the programming allows. Fully accept that the F16 pilot pointed out manoeuvres that he had never expected not trained for, but maybe they will/can be incorporated into future scenarios and be countered accordingly?

When a real drone in the air takes on a real pilot in a real fighter the results should then be considered realistic.

[stilton]

so you have changed your argument from killing the most to occupying the ground to win- and guess what!

Still wrong!

Perhaps quit while you are losing!

but let me give you some examples to ponder : Czechoslovakia 1938
Singapore 1942
Japan 1945


No change


It’s all part of the same problem, no matter how many of the enemies weapons you destroy you don’t defeat him completely until you kill and / or subjugate / nullify enough of his population, military and civilian, and occupy his territory


Then you can put the instigators of the conflict / war criminals on trial, punish them and maintain a presence in the aggressors country until the threat is eliminated


Worked pretty well with Japan and Germany

[typerated]

No change


It’s all part of the same problem, no matter how many of the enemies weapons you destroy you don’t defeat him completely until you kill and / or subjugate / nullify enough of his population, military and civilian, and occupy his territory


Then you can put the instigators of the conflict / war criminals on trial, punish them and maintain a presence in the aggressors country until the threat is eliminated


Worked pretty well with Japan and Germany

No - you don't get it.

Not even on the right page.

The example I gave you - you didn't need to kill, nullify or occupy- think about Czechoslovakia.
What was needed there? Certainly nothing of what you state!

The point of military action is to impose a political cost and then whether a government/people are willing to pay it or fold is the question.

[beardy]

I'm still unsure how this (https://www.pprune.org/10867086-post35.html) has morphed into a categorical assumption that a drone will beat a live human in A2A combat? It was a simulation, not a real exercise, where a drone operator (on a computer) beat an F16 pilot (on a computer) with a result that can only be as real as the programming allows. Fully accept that the F16 pilot pointed out manoeuvres that he had never expected not trained for, but maybe they will/can be incorporated into future scenarios and be countered accordingly?

When a real drone in the air takes on a real pilot in a real fighter the results should then be considered realistic.

The point is that the drone operator WAS the computer and while this was a simulation the drone operator, in the future, can be in the drone which may not be limited by human physiology.

It's another step towards machine supremacy in cognitive analysis and mechanical skill.

[SLXOwft]

For me the real game changer would be having AI in your BVR AAM/BVR SAM so that it effectively has a Mk.2 Eyeball and can actively distinguish its target from physical and electronic countermeasures. It would also be able to anticipate and counter manoeuvring by the target aircraft manned or unmanned to increase the probability of a kill. Granted it relies on politicians allowing BVR engagement in the ROE in any future conflict.

[pr00ne]

It was the only "battle" where the enemy was not aware that there was one going on!

Mog

Er, Hitler tasked the Luftwaffe with gaining air supremacy over the Channel and southern British Isles to permit an invasion. They tried, and failed. So I think they most certainly DID know that there was a battle going on.

[NutLoose]

Plus an Independent AI controlled missile.

Questions re AI Aircraft, it’s alright when you have something like the F16 where you have reams and reams of data and pilot experience to incorporate into the AI programme, but how will they fair with a new AI design?
After all, a lot of the current requirements can be binned and replaced with fuel or armaments, ie all the junk to keep the pilot alive and informed.

Do you give it the basics and expect it to learn as it fights? because a lot of pilots have died attempting that through the many wars, and if you do give it the ability to learn will it be able to pass this on via a data link to other AI aircraft, or will you be stuck at the learn as you go?

does that make sense?

[pr00ne]

A battle that was part of a war which was won by gaining and holding territory.

Correct right up until Hiroshima and Nagasaki.

After those two events the whole game changed. The cold war concept of MAD was not based on gaining and holding territory in any way shape or form.

If the allies had possessed enough atomic bombs in 1944 or 5 then D-Day would not have been necessary. Germany would have been a ruined and wrecked country after a half dozen 'Hiroshimas' and no land invasion would have been needed.

Japan wasn't invaded and conquered, it was occupied after surrendering.

[NutLoose]

If the allies had possessed enough atomic bombs in 1944 or 5 then D-Day would not have been necessary. Germany would have been a ruined and wrecked country after a half dozen 'Hiroshimas' and no land invasion would have been needed.

i think you will find Chernobyl put that idea to bed, the whole of Europe would end up affected.

[ORAC]

Do you give it the basics and expect it to learn as it fights? because a lot of pilots have died attempting that through the many wars, and if you do give it the ability to learn will it be able to pass this on via a data link to other AI aircraft, or will you be stuck at the learn as you go?
In this case they taught it nothing - even about the ground and how hard it is - and let it learn for itself.

If you equate that to science, they now use evolutionary algorithms to find new drugs and methods of design etc because the computer doesn’t have any preconceived ideas and they are finding solutions where humans never even thought to look. Which brings us back to the comment by Banger that it was doing things he had never seen/fought before. And of course the computer can be learn through millions of simulations in hours.

The main thing to note here is that the fight was in an environment where the computer knew where the enemy was at all times. Put it in an environment where the inputs are radar/IR/visual sensors with blind spots then, initially it may not be as effective as a human who extrapolate - but remember they said the same thing about chess computers.

To the computer everything is taking place in ultra slow time - it has the ability to change its mind a million times a second. The first iterations might be as an pilot assistance mode where it steps in to take action to save the aircraft from entering a position to get shot, or as a snapshot gun mode where it takes control to steer the nose and fire a burst for a kill - which is where the AI scored its kills in this trial. The next step, as in the current software which senses pilot incapacitation and takes over control, may be to press the button and let the AI take over the fight with the pilot monitoring.

The next step is incorporating the software into smart wingmen who are, like attack dogs, let off the leash and sent into the fight by the pilot of the command aircraft.

https://link.springer.com/article/10.1007/s00521-020-04832-8

[beardy]

Correct right up until Hiroshima and Nagasaki.

After those two events the whole game changed. The cold war concept of MAD was not based on gaining and holding territory in any way shape or form.

If the allies had possessed enough atomic bombs in 1944 or 5 then D-Day would not have been necessary. Germany would have been a ruined and wrecked country after a half dozen 'Hiroshimas' and no land invasion would have been needed.

Japan wasn't invaded and conquered, it was occupied after surrendering.

Quite correct, the allies gained and held Japanese territory following the Japanese surender. Which is what happens when one side loses, they lose control of their territory.

MAD was based around both sides being unable to win (and control territory), there would have been no winners, both sides were guaranteed to lose. The clue is in the name.

[monkey416]

I think Banger was talking about forward quarter gun attacks, which is where the Heron scored nearly all its hits and which USAF pilots (and pretty much those of every modern air force) are prohibited to train for due to safety risks. It looked to me like the AI's BFM was pretty weak compared to Banger actually. It certainly wasnt any better.

[etudiant]

I think Banger was talking about forward quarter gun attacks, which is where the Heron scored nearly all its hits and which USAF pilots (and pretty much those of every modern air force) are prohibited to train for due to safety risks. It looked to me like the AI's BFM was pretty weak compared to Banger actually. It certainly wasnt any better.

That suggests the central purpose of the air combat training has been subjugated to 'safety risks'.
I doubt a serious enemy would be similarly bound.
Sadly the reality of 75 years of peacetime with only punching bag opponents, the military are no longer primarily a fighting force.
Perhaps we need a vastly smaller military, wholly professional, which would again make effective fighting the core mission.

[ORAC]

https://csbaonline.org/uploads/documents/Air-to-Air-Report-.pdf

[monkey416]

That suggests the central purpose of the air combat training has been subjugated to 'safety risks'.
I doubt a serious enemy would be similarly bound.
Sadly the reality of 75 years of peacetime with only punching bag opponents, the military are no longer primarily a fighting force.
Perhaps we need a vastly smaller military, wholly professional, which would again make effective fighting the core mission.
No such limitation would exist in combat and I don't think there is any air force out there that practices forward quarter gunnery in the air to air environment.
Anyone with any time in fighters understands that there's a serious risk associated with ahead of 135 gun employment, with near zero training payoff. Theres a very good reason why its not done in training. You'd literally lose more aircraft in accidents than enemy you would take out with that added marginal skillset in combat.

[havoc]

https://www.msn.com/en-us/news/technology/former-navy-topgun-instructor-says-the-ai-that-defeated-a-human-pilot-in-a-simulated-dogfight-would-have-crashed-and-burned-in-the-real-world/ar-BB18oMCr?ocid=msedgdhp

Former Navy TOPGUN instructor says the AI that defeated a human pilot in a simulated dogfight would have 'crashed and burned' in the real world

An experienced US Air Force F-16 pilot went head-to-head with an artificial intelligence algorithm in a simulated dogfight last week and suffered five straight losses in the battle with the machine.
Former US Navy pilot and TOPGUN instructor Guy Snodgrass told Insider that he was "not surprised" by the AI victory, arguing that the the pilot was forced to play the AI's game and that the AI algorithm would likely have "crashed and burned" in the real world.
Former Air Force pilot and senior research fellow at the Heritage Foundation John "JV" Venable said the competition was "gamed to a point where you can't beat it."
That being said, both of the former pilots said they see a not-too-distant future where the US military has mission-capable AI-driven autonomous combat aircraft that can engage other combatants in air-to-air combat.
Visit Business Insider's homepage for more stories (https://www.businessinsider.com/?hprecirc-bullet).

An artificial intelligence algorithm absolutely destroyed a seasoned US fighter pilot (https://www.businessinsider.com/ai-just-beat-a-human-pilot-in-a-simulated-dogfight-2020-8) last week in a simulated dogfight, a result some observers say was to be expected.

"I was not surprised by that outcome," Guy 'Bus' Snodgrass, a former US Navy pilot and TOPGUN instructor, told Insider, arguing that the set-up of the engagement gave the AI an advantage. John "JV" Venable, a former US Air Force F-16 pilot, said the same.

The Defense Advanced Research Projects Agency (DARPA) held the last round of its third and final AlphaDogfight competition Thursday, putting an AI system designed by Heron Systems against a human pilot in a "simulated within-visual-range air combat (https://www.businessinsider.com/us-f-16-pilot-will-battle-ai-in-simulated-dogfight-2020-8)" situation.

The competing AI algorithm achieved a flawless victory, winning five straight matches without the human pilot — an experienced Air Force pilot and Weapons Instructor Course graduate with the callsign "Banger" — ever scoring a hit.

With advancements in air combat capabilities, there have long been questions about whether dogfighting even matters. Both Venable and Snodgrass said it remains relevant because pilots must be prepared to dogfight should their standoff capabilities be neutralized.

"In a best case scenario, dogfighting is completely irrelevant because you want to see your adversary as far away as possible," Snodgrass explained. But sometimes pilots are unable to defeat their opponent before they find themselves in close combat.

"Now, you're left to a bullet," Venable said.
https://img-s-msn-com.akamaized.net/tenant/amp/entityid/BB18ojBw.img?h=600&w=799&m=6&q=60&o=f&l=f© U.S. Air Force photo by Tech. Sgt. John Raven An F-16 during an approach at mission at Holloman Air Force Base, New Mexico, Apr. 21, 2019 U.S. Air Force photo by Tech. Sgt. John Raven'Gamed to a point where you can't beat it'Theresa Hitchens at Breaking Defense characterized the recent simulated engagement (https://breakingdefense.com/2020/08/ai-slays-top-f-16-pilot-in-darpa-dogfight-simulation/) as a "one-on-one combat scenario" in which combatants fired "forward guns in a classic, WWII-style dogfight," suggesting that it mimicked certain aspects of close air-to-air combat. That being said, the contest was not necessarily a fair or realistic fight.

"This was gamed to a point where you can't beat it," Venable said, arguing that the AI algorithm appears to have had access to information that it would not have in the real world. The combat environment, as Snodgrass also pointed out, was built to the AI's advantage.

"You have an artificial intelligence program that has been perfectly trained in that environment to conduct a simulated fight, and you have a US Air Force fighter pilot who you are forcing to wear VR goggles," Snodgrass said, saying that the human is "playing the AI's game."

With a background in computer science and experience with some of the Department of Defense's AI research, he explained that "if you give [AI] a very narrow, specific job to accomplish, once it's been trained, once it has had exposure to a very static environment, it does phenomenally well."

"You find that artificial intelligence can begin to outperform human operators in short order," he added.

But, where AI struggles is when it's put in a complex environment with unconstrained variables and asked to think and act like a human being. "We're nowhere near that," Snodgrass said.

"The AlphaDogfight trials were a significant step toward one day providing an unmanned aircraft that can perform dogfighting," the retired Navy commander said, "but what it does not demonstrate is that we're there now."

"I think it's promising for the development of artificial intelligence," he added, "but if you took that same algorithm, put it into an unmanned vehicle and said, 'Okay, go fight a real dogfight,' it would have crashed and burned pretty quick."

A mission-capable AI-driven autonomous combat aircraft is possible in the not-too-distant future though, both he and Venable told Insider.

The AlphaDogfight trials are aimed at moving DARPA's Air Combat Evolution (ACE) program forward.

The ACE program, according to DARPA (https://www.darpa.mil/program/air-combat-evolution), is designed to "deliver a capability that enables a pilot to attend to a broader, more global air command mission while their aircraft and teamed unmanned systems are engaged in individual tactics."

Col. Dan Javorsek, the program manager in DARPA's Strategic Technology Office, said last year (https://www.darpa.mil/news-events/2019-05-08) that the agency envisions "a future in which AI handles the split-second maneuvering during within-visual-range dogfights, keeping pilots safer and more effective as they orchestrate large numbers of unmanned systems into a web of overwhelming combat effects."

The agency's research is aimed at delivering advanced manned-unmanned teaming both inside and outside the cockpit, and DARPA is just one of several teams looking at these capabilities for the US military.

"When you think about all the advancements that have occurred in the last decade, in the last hundred years, I would never bet against technological progress," Snodagrass said.

"I think there's a point in time where the US military will have unmanned aircraft that you could give a mission, load it up, have it take off, and have it potentially fight its way in and fight its way back out," he added. "That's absolutely possible and something likely to happen probably sooner than we ever imagined."

As part of the ongoing Skyborg project, the Air Force is currently working to develop low-cost, attritable AI-driven autonomous aerial combat vehicles to fly alongside manned fighter aircraft in combat as early as 2023. The military is also talking about putting one of these unmanned systems against a manned aircraft in aerial combat as early as next year.

But developing the technology is only part of the process of fielding new warfighting capabilities. The technology also has to be accepted and trusted by pilots.

"The recent 5 to 0 victory of an Artificial Intelligence (AI) pilot developed by Heron Systems over an Air Force F-16 human pilot does not have me scrambling to send out applications for a new job," Navy Cmdr. Colin 'Farva' Price, a F/A-18 squadron commander, wrote in an article for The War Zone (https://www.thedrive.com/the-war-zone/35947/navy-f-a-18-squadron-commanders-take-on-ai-repeatedly-beating-real-pilot-in-dogfight). "However, I was impressed by the AlphaDogfight trials and recognize its value in determining where the military can capitalize on AI applications."

He expressed interest in AI-enhanced systems in an aircraft assisting and augmenting the combat capabilities of fighter pilots through machine learning, something the Air Force is already looking at.

Explaining that top US pilots have thousands of hours of experience during a 2018 interview with Inside Defense (https://insidedefense.com/daily-news/rapid-autonomy-development-team-sets-18-month-plan-autonomous-fighter-jet), Steven Rogers, the head of autonomy at the Air Force Research Laboratory, asked the question, "What happens if I can augment their ability with a system that can have literally millions of hours of training time?"

"I am not ready for Skynet to become self-aware," Price wrote, referring to the evil AI enemy in the Terminator films, "but I am certainly ready to invite AI into the cockpit."

[PEI_3721]

There is a lot of hype around what was just a technology demonstration. Until AI can explain how it wins, then there is little value for operations or training.

So you take two of these AI enabled 'aircraft' and start a fight; which one wins, when (fuel, time), and how would we know.

[etudiant]

No such limitation would exist in combat and I don't think there is any air force out there that practices forward quarter gunnery in the air to air environment.
Anyone with any time in fighters understands that there's a serious risk associated with ahead of 135 gun employment, with near zero training payoff. Theres a very good reason why its not done in training. You'd literally lose more aircraft in accidents than enemy you would take out with that added marginal skillset in combat.

This simulation was the equivalent of combat and the human pilot was unprepared for it. If the head on attack is too risky to be trained in real life, perhaps it should at least be done in a simulator.
That might avoid embarrassing results such as we just saw, a 'top gun' surprised by a tactic he never expected before it happened in real life.
The 'near zero training payoff' clearly applies only if the eventual opponent has the same opinion about this tactic.

It does seem the rules of engagement need to be rethought here, the training fails to reflect reality.

[PEI_3721]

'… surprised by a tactic he never expected before… '
Would AI think of firing an out-of-envelope 'Winder' (Phantom), or jettison the drag chute (Vulcan), or a low fast runout and drop a 1000 lb retard (Buccaneer); the tactics may not win the fight, but surprise and distraction (in AI terms - not programmed for) could switch focus from attack to defence - advantage to the defender.

'This simulation was the equivalent of combat and the human pilot was unprepared for it. … the training fails to reflect reality … '
Capt Kirk, Star Trek, Kobayashi Maru simulation; no win situation, training objective to assess human reaction under stress, probable death.
Kirk hacks the simulator, everyone survives. Crew fails the training course, didn't follow the rules; but they would win the war.

He who sees first wins - with AI becomes a battle of sensors, how to blind AI. He who understands first … AI lacks context.

[ORAC]

https://www.defensenews.com/congress/2020/09/10/ais-dogfight-triumph-a-step-toward-human-machine-teaming/

AI’s dogfight triumph a step toward human-machine teaming

WASHINGTON ― Human fighter pilots, your jobs are safe for now.

Weeks after an artificial intelligence algorithm defeated (https://www.c4isrnet.com/artificial-intelligence/2020/08/21/ai-algorithm-defeats-human-fighter-pilot-in-simulated-dogfight/) a human pilot in a simulated dogfight between F-16 jets, the Pentagon’s director of research and engineering for modernization said Thursday at the Defense News Conference (https://www.defensenews.com/smr/defense-news-conference/) that it’s more likely an AI will team with military pilots than replace them.

“I don’t see human pilots being phased out, I see them being enhanced, not physically, but I see their work, their effectiveness being enhanced by cooperation with artificial intelligence systems,” said Mark Lewis, who also serves as the acting deputy undersecretary of defense for research and engineering.

The AlphaDogfight Trials in August marked the finale of the Pentagon research agency’s AI air combat competition. The now-notorious algorithm, developed by Heron Systems, easily defeated the fighter pilot in all five rounds that capped off a yearlong competition hosted by the Defense Advanced Research Projects Agency ― which is overseen by Lewis and the Defense Department’s research and engineering shop.

“The key takeaway from that was the artificial intelligence system did so well because it wasn’t so concerned about self-preservation, it was willing to do things that a human pilot wouldn’t do. And that’s the advantage of artificial intelligence,” Lewis said. “I think the real answer is teaming AI with a human for the best combination of both. So I’m pretty confident we’re going to have human pilots into the future.”"..........

Fiscal 2023 will see the first in a yearlong series of trials using tactical fighter-class aircraft (currently L-39 trainers), with safety pilots on board to assist in case of trouble. Those pilots would be given “higher cognitive level battle management tasks while their aircraft fly dogfights,” all while sensors gauge the pilot’s attention, stress and trust in the AI, Adams said.

DARPA foresees a single human pilot serving as a mission commander in a manned aircraft, orchestrating multiple autonomous, unmanned platforms that would all be engaged in individual tactics. ACE would ultimately deliver that capability.

“ACE, therefore, seeks to create a hierarchical framework for autonomy in which higher-level cognitive functions (e.g., developing an overall engagement strategy, selecting and prioritizing targets, determining best weapon or effect, etc.) may be performed by a human, while lower-level functions (i.e., details of aircraft maneuver and engagement tactics) is left to the autonomous system,” Adams said.

“In order for this to be possible, the pilot must be able to trust the autonomy to conduct complex combat behaviors in scenarios such as the within-visual-range dogfight before progressing to beyond-visual-range engagements.”........

But Esper warned that both Russia and China were pursuing fully autonomous systems, and drew a distinction between them and what he described as the U.S. military’s ethically guided approach to AI.

“At this moment, Chinese weapons manufacturers are selling autonomous drones they claim can conduct lethal targeted strikes,” he said. “Meanwhile, the Chinese government is advancing the development of next-generation stealth UAVs, which they are preparing to export internationally.”

[etudiant]

The schedule for the trials does not seem particularly urgent, surprisingly so in light of the demonstrated effectiveness of drones both in actual combat as well as in simulations.
Meanwhile, China has a good export business to the Med and the Mid East, as well as a hugely profitable small drone business selling mostly to the US consumer market.
If this is a race, I don't think the USAF is winning.

[gsa]

A friend of my son wrote “Predator Empire: Drone Warfare and Full Spectrum Dominance”. When I spoke to him last at length he said that it would take about 10 years for the drone combined with AI to full beat manned systems. So give it about another 5 years and we’ll fully see what technology can do.