Thought this would get lost in the nato thread so posted it in the f16 subforum 
itâs already scaring they are using drones to fight!
itâs even more scaring they will use ai to drive drones!
hope there will be some ai weapons no proliferation agreement!
hope the pilot could smash the ai with cunning and intuition!
thinking more about itâŠ
hope the research could give us, better ai!
we deserve it 
Yeah but itâs DARPAâŠwhat have they done since they invented the Internet? 
1 Like
Seems like this will be another case of âbig defense industry and govât doesnât understand how modern tech works.â
1 Like
Early stages in a controlled environment, but here we goâŠ
1 Like
The event so far was interesting to watch. The AI doesnât seem to mind the negative G and tends to win by being carefree with its existence - aggression wins etc.
The fight starts here - https://youtu.be/NzdhIA2S35w?t=16732
4 Likes
Hmm. But doesnât the AI know, always, where the human is? Seems in the RW this would require some serious sensor ability. âLet me at em!â 
âPerfect State informationâ they statedâŠalways knows where the other object is - presumably that includes knowing speed AoA etc if its only eyes are access to object parameters!
It would need something similar to EODAS in the real world I guess.
Interesting that their future vision is a manned jet where the AI does the flying and BFM and pilot is a passenger who handles the cognitive thinking side.
I guess an early step would be to ârecommendâ things, as in man in the loop stuff. The winning AI was running on a laptop, so weâre not talking super computer stuff. Itâs a huge (huge) leap from this to âAI fighter pilotâ though, as that was just a game with very artificial rules. Some of the rules (like keeping it under 9G) help the human, but sensor omniscient powers is nice for the AI - not that AIâs canât be good at detecting visual imagery and motion (think how well an AI could have a âhead on a swivelâ in 360).
Just like fly-by-wire means the pilots isnât actually moving the elevator but telling a computer of their intent to do something, I guess some combat âhintsâ can use an AI like this type of for fighting. Itâs still the human fighting, itâs just a tool to augment. As in Airbus has Flight Law, maybe one day theyâll be âFight Lawâ where itâll ignore stuff that will get you killed in WVR. 
I imagine the whizzbang stuff in F-35âs and F-22âs is already pretty âaugmentedâ for BVR regardless of learning AI models.
The difference between this and a missile expert system decision process built into a AIM-120 is that the AI model went through 100,000+ fights before hand to âtrainâ the model. So effectively every time it does something statistically wrong it corrects and learns. AI models are split between a training part and an evaluation part (where it runs), so you can throw computer resources at the training side (racks of GPUs etc) but then the evaluation run-time is small and efficient (like how an iPhone recognizes a face locally).
I donât particularly want a world of AI drones with the ability to independently fight, but then again, both the good guys and the bad guys have access to all this stuff as the tech advances. In some aspects itâs inevitable to some degree, and the ability to adapt will dictate who does well.
4 Likes
At the end of the day this progression is necessary.
They (the DARPA program manager ex F-16/F-22) were at one point talking about how back in the day some had an idea to send the Calvary horses to the front line by train - that way they would be fresh when they arrived, and run rings around the Tanks they were facingâŠanyway
1 Like
1 Like
This setup is quite disrespectful to someone who is doing his service tbh, and I would not be surprised if the tables were turned if the fight was IRL, if even machine learning could possibly counter perifial vision of a human pilot. But regarding the displayed bfm competency and tactics the verdict is pretty harsh from the bfm pro armchair pilots over at benchmarksims and a clear indication that heâs out of his element. The most striking example being the lead turn at 600 kts, with real life reference instead of a VR hat I donât believe there is a way that a professional fighter pilot would ever do that if his life depended in it.
Itâs a âdumbed downâ setup to make the machine learning problem manageable. They were pretty upfront about this, though.
I think we need to remember that âmachine learningâ at this stage is essentially just pattern matching arithmetic. Powerful when done right, but itâs not really autonomous; it builds from known data and extrapolates from that. Itâs been applied for years (for example, the AH-64âs FCS uses Kalman filters to calculate where to aim the weapons to hit) and really isnât anything new in the defense industry. In essence, this is what we can do now, under current systems and inside of those limitations.
Was this whole thing a game changer? No, I donât think so; this looks more like a âCongress gib money plz kthxbyeâ from the DOD/DARPA/mil industry. Perhaps for good reason, given that it is the future, but having experienced the DOD/govâts inner workings, more likely for ridiculous reasons. Thereâs a reason you see a lot more advances in these regards at places like Google, SpaceX, etc. as opposed to Boeing, LockMart, and so on; the people good at working on these kinds of things arenât exactly chomping at the bit to go work in mil-defense.
For me, most of all is we donât know what Bangerâs background is. By that, I donât mean his flying record, but how involved in computers is he? Has he or does he play a lot of games? Does he have a grasp of how simulation AI works in more crude/primitive forms? Without knowing any of this, Iâm not willing to say that this was really much more than a DARPA advertisement.
As has been proven time and time again, you bring out some fancy new technology and call it unbreakable in the lab, then in the field it falls apart in 5 seconds because PVT Chucklenuts and SPC Schmuckatelli immersed it in a vat of solvent to clean it faster because they didnât want to scrub it properly. All too often, the people building and making this tech forget about the people actually using it, and they especially forget that the people using it arenât exactly the cream of the crop.
2 Likes
This reminded me of somethingâŠ
WAY back in the early 90âs I think it was, I knew a guy, who knew a guy, that let me stroll through an Air Traffic âFuture worldâ. He was a consultant helping them evaluate the system - it was what I know loosely as an âExpert Systemâ. The AI was going to control everything. Theyâd been working on it for years then. Conceptually itâs all pretty simple, but!
The guy I chatted with told me that one day they (the âhumansâ) asked if they could script in some thunderstorms during an 80% scenario (traffic at 80% of max capacity). The gist of it was: the AI couldnât adapt, at all. I speculate that a big reason is the humans in the aircraft werenât, well, AI themselves; TWA123 wants to go left around a cell, and Eastern 456 wants to go right. We humans adapt.
So, they shut it (the AI) down and, hereâs the interesting part, the humans had a real hard time dealing with the scenario now because theyâd been, essentially, observers for weeks at a time - their skills had gotten rusty. Now, replace all this with BFM/ACM and yeah, they need to think about that.
2 Likes
While i agree with the rest of your post, this i disagree with. It just isnât possible to solve this kind of complex optimization problem with a Kalman Filter. The Kalman Filter was developed to solve a problem that this AI did not have, namely dealing with noisy and/or incomplete data. The Kalman Filter uses a state space model (e.g. equations of motion) and a statistical noise model (plus sensor fusion if multiple sensors are available) to give you an optimal estimate of (classically) where something is and where it is going (but can be used for other problems where a state space model can help). It can not directly give you steering input. It also would not be able to conserve energy (i.e. trade position for energy to better maneuver at a later point).
Itâs true that it is not autonomous because this thing in its present form couldnât even bring the plane back to base. Like a dog chasing cars it would go after any plane it finds and kill it or be killed by it until it runs out of fuel. But what it does is still way, way more complex than a Kalman Filter.
5 Likes
Yep, just to +1 @sobek there. A Kalman filter is not really like a recurrent or convolutional neural network, as the layers change and the parameters are learnt and not fixed. While none of this stuff is (or perhaps ever will be) Buck Rodgers, thereâs been advances in the last 20 years that are decent, mainly through the commodization of parallel computing and newer back-propagation algorithms that work with these parallel units. A good and approachable resource if interested in learning about the area is here - http://neuralnetworksanddeeplearning.com/
Another way to think of these games is really the scenarios of what happens if the bad guys get into it first, as in, itâs not just a case of wanting to replace USAF warm bodies, itâs more to understand how to fight against a threat like that. Swarms of cheap drones with specialized AI could be a thing one day, so itâs good to âthreat modelâ it like crazy. Competitions like this help with that (a bit, although I would suspect what we see in public is not even state of the artâŠ)
3 Likes
I look at it all as taking known data and extrapolating from that; Iâm sorry to say Iâm a bit dumb when it comes to arithmetic and matters associated with such. But one thing I can say is Iâm tired of everyone and their brother frothing about âAIâ and âSkynet is coming!â when itâs really far from that nefarious and isnât so much âlearningâ as it is doing fancy stuff with pattern matching. From my dumb, uneducated perspective, of course.
1 Like
There is a huge amount of bullshit in the whole area of AI, and if you know about Kalman Filters then you arenât even a little bit dumb
1 Like