How Hot is Ukraine Gonna Get?

[Butschi]

43 minutes ago, The_Capt said:

Don't we kinda already have this?  Modern ATGM guidance systems look pretty sophisticated in their ability to stay looked onto one large hunk of metal vs a burning garbage truck.

"The tracker is key to guidance/control for an eventual hit. The signals from each of the 4,096 detector elements (64×64 pixel array) in the seeker are passed to the FPA readout integrated circuits which reads then creates a video frame that is sent to the tracker system for processing. By comparing the individual frames, the tracker determines the need to correct so as to keep the missile on target. The tracker must be able to determine which portion of the image represents the target.

The target is initially defined by the gunner, who places a configurable frame around it. The tracker then uses algorithms to compare that region of the frame based on image, geometric, and movement data to the new image frames being sent from the seeker, similar to pattern recognition algorithms. At the end of each frame, the reference is updated. The tracker is able to keep track of the target even though the seeker's point of view can change radically in the course of flight.

The missile is equipped with four movable tail fins and eight fixed wings at mid-body. To guide the missile, the tracker locates the target in the current frame and compares this position with the aim point. If this position is off center, the tracker computes a correction and passes it to the guidance system, which makes the appropriate adjustments to the four movable tail fins. This is an autopilot. To guide the missile, the system has sensors that check that the fins are positioned as requested. If not, the deviation is sent back to the controller for further adjustment. This is a closed-loop controller."

Yes, of course that technology is there already. Although we are now talking about restricted stuff vs publicly available. Anyway, it really boils down to replacing the "The target is initially defined by the gunner" part.

And I think it really makes a difference whether you have an ATGM where missing may give the target the opportunity to return fire (or a Sidewinder where missing may mean losing a multi-million dollar asset plus a crew that took years to train) or a relatively cheap drone where you don't care if half of them go after a car instead of a tank as long as the other half kills the tank.

[dan/california]

It really seems to me that at least 75% of the work needed for a competent drone swarm was done to build this thing. You just have to have each submunition delivered by a quadcopter. Also, they should start making a new version of this for both HIMARS and ATACAMS/PRISM. 

Edited October 29, 2023 by dan/california

[chrisl]

5 hours ago, Butschi said:

Anyway, for image classification you don't need to be an AI or expert (which is not to say the Russians don't have any). Most high end research in that field is public, often even including code. What you need to do is train the (usually) neural net to identify stuff you are interested in (not cats and dogs). But that is easy to do if you have enough training data.

 

That's always the hard part.  Not just enough training data, but the right training data.

If you're Google and just trying to squeeze another fractional percent out of your ad revenue, you can use half the internet to train and the other half as a test set.  And you only need a tiny improvement in performance to make it worth the effort to get mediocre results.

If you're Tesla it's trickier. You can put cameras on cars driven by people with excellent driving records and then correlate the video to the drivers' actions and hope you got it right.  Sometimes they seem to drive into firetrucks, though. (Dude, where's my LIDAR?)

Quote

Of course it is not only detection and classification but also tracking... but that, too, is really available on the Internet.

Once trained you can either strip the net down to something manageable by less potent hardware or possibly design a dedicated FPGA or similar.

At the low SNR, barely resolved limit, the tracking is easier than the detection - once you identify all the things, figuring out who is who from frame to frame isn't terrible if you've got a high enough frame rate.  But at low SNR the noise and the signal look very similar in any frame, so you have to watch things (noise) move around, and then throw out things that only exist for a few frames in a row because they're noise.  (or maybe they're drones popping up above the weeds to take a shot and then disappearing)

All of that isn't so bad to do if you're looking for large targets, like vehicles, and trying to separate them from bald monkeys and buildings. Maybe even separating trucks from tanks from IFVs.  It's a lot harder if you're Russia and don't have an internal semiconductor industry base.  I wouldn't be all that surprised if they had well developed algorithms derived from open source, maybe even partially trained on video data, but not enough hardware to go past a few prototype units.  But they'll have a terrible time doing it for drones - there are multiple pieces of silicon that you need to put in a row that are practically free in the west but will depend on some unreliable machinations in Russia.  

Quote

And let's keep in mind that this task is simpler than autonomous driving if you don't mind having a higher misidentification rate and don't care about collateral damage, or even friendly fire as long as sufficiently many of your (cheap?) drones hit something you want them to hit. All of which is probably true for the Russians and less so for Ukraine.

As you said yourself, steering the drone towards that target is the simple part.

Now the level of autonomy is the other variable here. Of course having a drone where you just press the start button and it plans a sensible search pattern, without relying on GPS, using terrain to its advantage etc. is complicated. Steering the drone manually or programming a path to an area of interest and then switching on "hunt mode" with some pre-programmed search algorithm (like a robot vacuum cleaner does) is rather simple.

Which reminds me that I saw a spoof prototype of The Captain's wandering mines over on the site formerly known as twitter, but didn't notice it here or have time to link it before it disappeared in the ether.  Someone did a little photo sequence pointing out that the Russian AT mines look like they fit neatly atop a Roomba, with the obvious extrapolation.

[chrisl]

5 hours ago, The_Capt said:

I have a physics degree and most of this is way above my head.  One thing is becoming apparent though - if modern militaries cannot solve for unmanned air war below 2000ft then we are entering into an different era of warfare.

Denial and Defence will rule conventional warfare until we can crack the unmanned problem.  Military implications for this are enormous, especially considering we have built for Interventions/Offence for the last 30 years at least.  Political ramifications of this are not small considering that entry costs for these technologies are low.

Well if anyone is looking for a career, this sector will be booming for years.

If one side has the Diamond Age swarm and the other doesn't, the swarm side is going to have an advantage no matter whether they're on attack or defense.  So far they aren't quite overwhelming the defenders, but we saw the dystopian science fiction video a few pages ago, and that kind of quantity isn't all that far away.  The limit on those swarms is going to be battery endurance.

[kimbosbread]

5 hours ago, Butschi said:

It depends on how you define "AI" and "autonomous". I'm involved with the prediction and planning part of autonomous driving, not flying drones and not (directly) the perception part, so take what I say with a pinch of salt.

Anyway, for image classification you don't need to be an AI or expert (which is not to say the Russians don't have any). Most high end research in that field is public, often even including code. What you need to do is train the (usually) neural net to identify stuff you are interested in (not cats and dogs). But that is easy to do if you have enough training data.

Yeah, you don’t need to be perfect either, as long as your false positive rate is zero. Training a model to recognize locomotives and train tracks is pretty trivial, and as discussed pages ago, this is something that should be done to crush Russian logistics. I think loitering for up to 12h and finding artillery would be the other. Just wait till it moves if you have a reasonable amount of drone density, say a few in a 10km square grid.

I really think the artillery hunter and train hunter cases a few bored people could build in a few months. If I manage to deliver my big project for day job this week or next, I’ll build a model post it on here with repro for everybody’s satisfaction. Sadly 10-12h days precludes working on anything else.

1 hour ago, Butschi said:

And I think it really makes a difference whether you have an ATGM where missing may give the target the opportunity to return fire (or a Sidewinder where missing may mean losing a multi-million dollar asset plus a crew that took years to train) or a relatively cheap drone where you don't care if half of them go after a car instead of a tank as long as the other half kills the tank.

The economics argument is on point.

5 minutes ago, dan/california said:

You just have to have each submunition delivered by a quadcopter. Also, the should start making a new version of this for both HIMARS and ATACAMS/PRISM. 

Rephrase it to “Each submunition has its own guidance system and locomotion”. Not necessarily a quadcopter, but the line between drone and smart munition is rather blurry.

[kimbosbread]

5 minutes ago, chrisl said:

The limit on those swarms is going to be battery endurance.

Why not gasoline? Those micro-turbines and whatnot gives way better endurance. I’ll grant that batteries have other advantages however.

[Haiduk]

"Kub" SAM, upgraded for RIM-7 SA missiles. 

UKR hadn't "Kubs" on armament, likely some Eastern European country aid, probably Poland.

Edited October 29, 2023 by Haiduk

[chrisl]

17 minutes ago, dan/california said:

It really seems to me that at least 75% of the work needed for a competent drone swarm was done to build this thing. You just have to have each submunition delivered by a quadcopter. Also, the should start making a new version of this for both HIMARS and ATACAMS/PRISM. 

Later versions even have a laser rangefinder in the submunitions.

Enough pieces already exist to do lots of these things we're talking about, at least as far as the swarm of loitering platforms goes.  For most of them it probably just comes down to someone in DOD getting the motivation to throw some money at doing it and making it a big enough pile of cash that the MIC frees up the right engineers to do it. 

[Haiduk]

Svatove - Borova direction of Kupiansk sector. Russians have "negatory advance" again. They already lost more than half of own gains of initially successful attack on this direction in July

UKR troops now approached to Serhiivka village

 

[chrisl]

10 minutes ago, kimbosbread said:

Why not gasoline? Those micro-turbines and whatnot gives way better endurance. I’ll grant that batteries have other advantages however.

Sure.  Some of those gas motors are even kind of cute.  

[Haiduk]

UKR BAT-2 tracklayer tries to fight with "rasputitsa", but after dozen vihicles will pass this road, the crew lekely will do this work again

 

Edited October 29, 2023 by Haiduk

[Hapless]

Apparently:

His replacement is apparently going to be Teplinksy. Didn't Teplinsky end up as the Russian's 2iC in Ukraine or something?
If so, looks like they're starting to worry about the Kherson front.

[chrisl]

1 minute ago, Hapless said:

Apparently:

His replacement is apparently going to be Teplinksy. Didn't Teplinsky end up as the Russian's 2iC in Ukraine or something?
If so, looks like they're starting to worry about the Kherson front.

To be found dead in a fall from a window in 3.....2.....

[Haiduk]

Situation near Avdiivka was slightly cooled in past days because rains and cloudy weather, so no one side couldn't use most type of drones. Russians, having lost many vehicles, came to Bakhmut scenario and now operate mostly with small assault groups of squad-platoon size, trying to pentrate our defense along railroad near Krasnohorivka on the northern flank of Avdiivka.

Despite Russians forced UKR troops to withdraw from slageheap and set a flags on it eastern slope, they reportedly couldn't gain foothold there and can't use this position neither for observation, nor for combat positions like ATGMs. Any movement and attempts there immediately are spotting and nipping in the bud.

UKR troops even didn't spare of FPV-drone to eliminate enemy flags over slageheap. It happened on 24th of Oct. As you can see no Russians on the top of slageheap.

  Here is UKR position and 16 destroyed Russian vehicles around it - real fields of death

Also known video of attack near Krasnohorivka but from other point of view. Now we can see hit of Russian UR-77 and Russian infantry supressed by fire (or even dead)

I was wrong, identifying BTRs as belonging to 15th MRB of Russia, they were from DNR "Sparta" recon-assault battalion, operating on southern flank.

Edited October 29, 2023 by Haiduk

[chrisl]

2 hours ago, Tux said:

First of all this was really interesting and clearly-written. Thank you.

Secondly, while solving the IFF issue will clearly confer an advantage, I’m not sure it’s necessary for early-generation drone fleets.  Instead I imagine a world where a fleet of Anti-Drone Drones (ADDs) is released to ‘purge’ the sky over a battlefield at a set time on a set date, designed to catch as many enemy drones in action as possible.  Orders to ground all friendly drones will ensure that the vast majority of ‘kills’ are of enemy drones.  All the ADDs need to be able to do is to tell ‘an ADD’ (so one specific image) from ‘not an ADD’ (nADDs?). 
This could obviously lead to all sorts of efforts to spoof the enemy into deploying their observation/FPV drones en mass so that you get a solid opportunity to “hit them in the nADDs” and hopefully achieve a short period of drone superiority for your own forces.

In that world IFF lends a significant advantage, enabling you to go for full drone supremacy over the battlefield, but it’s not absolutely necessary.

The Dalek approach to a defined area crossed my mind while I was writing, but I didn't address it.  As you point out, it has some rather spectacular failure/spoof modes.

If you don't solve the IFF problem, could end up with the "baby spider" situation, where they all just eat each other until there are one or two left, without regard for whose side they're on.

(btw - I've seen *actual Daleks* patrolling the new Economy Parking garage at LAX.  You have to be really careful getting to the shuttle)

[Haiduk]

This night UKR drone struck oil refinery in Krasnodar region. 

At the same time oil reservoir was set on fire in Komi Autonomous Republic (northern Ural) in Usinsk city. Reportedly explosions were hears before this, one man has died, one was injured. No information it was technical failure or diversion 

 

Edited October 29, 2023 by Haiduk

[Battlefront.com]

40 minutes ago, Haiduk said:

UKR BAT-2 tracklayer tries to fight with "rasputitsa", but after dozen vihicles will pass this road, the crew lekely will do this work again

 

First big rain and this will turn into a pig troth.  There's a reason road engineers have incorporated drainage ditches for a few hundred years when they build roads

Steve

[Haiduk]

45 minutes ago, Hapless said:

Apparently:

His replacement is apparently going to be Teplinksy. Didn't Teplinsky end up as the Russian's 2iC in Ukraine or something?
If so, looks like they're starting to worry about the Kherson front.

Here a thread about 137th marine battalion infiltration into Krynky village. 

According to today's information of some UKR TGs all Krynky so far under UKR control. Though it's doubtful because of this is very long village. 

Krynky on the map

 

Edited October 29, 2023 by Haiduk

[Beleg85]

22 minutes ago, Hapless said:

His replacement is apparently going to be Teplinksy. Didn't Teplinsky end up as the Russian's 2iC in Ukraine or something?
If so, looks like they're starting to worry about the Kherson front.

Could be personal sharades, with misconduct as  an excuse. There is entire carousel of names changing heir seats in high commands lately that even people familiar with mapping web of connections within muscovite generalship found rather chaotic. Perhaps delayed effects of Prigozhin march.

 

Video was posted here, but worth to paste upgraded, slowed and more detailed version of it.

https://twitter.com/Military_oO/status/1718611780115579345

 

[Tux]

8 minutes ago, chrisl said:

The Dalek approach to a defined area crossed my mind while I was writing, but I didn't address it.  As you point out, it has some rather spectacular failure/spoof modes.

If you don't solve the IFF problem, could end up with the "baby spider" situation, where they all just eat each other until there are one or two left, without regard for whose side they're on.

(btw - I've seen *actual Daleks* patrolling the new Economy Parking garage at LAX.  You have to be really careful getting to the shuttle)

The more I think about it, isn’t producing a cheap, mass-producible “dalek” drone actually the top priority, at this point?  If all else fails a fleet of daleks at least lets you wipe the sky clear altogether.  You could then even resurrect a few tanks and go all manoeuvrey again, if you wanted.

[Vet 0369]

On 10/27/2023 at 2:11 PM, dan/california said:

We have wasted eighteen months wishing and hoping Putin would make a rational deal, and things could get back almost to normal. It might be time to get a proper wartime ammo program underway before my sig becomes an unpleasant bit of prophecy.

Fixed that for you!

[The_Capt]

1 hour ago, chrisl said:

If one side has the Diamond Age swarm and the other doesn't, the swarm side is going to have an advantage no matter whether they're on attack or defense.  So far they aren't quite overwhelming the defenders, but we saw the dystopian science fiction video a few pages ago, and that kind of quantity isn't all that far away.  The limit on those swarms is going to be battery endurance.

If one side has swarms that work and other doesn't or a means to deny them, the war is over before it starts.  We are talking symmetrical conventional warfare here.  Every military in the world will be scrambling in what will become an unmanned arms race.  When two similar forces meet under the conditions we see before us Offensive warfare will be stumped.  Denial and Defensive will take primacy, they have before.  Until someone can solve for c-Swarm. 

The military term is "persistence", which is different than platform endurance.  Endurance is dependent on battery life.  Persistence is dependent on the capacity and resilience of the entire system to keep the capability effective and delivering effect.  That is bigger than batteries.  I can see a future battlespace where UAS are treated like artillery ammo (without barrel wear).  Massed precision beats everything.

Of course Unmanned are really just the last mile.  What is creating major shifts in warfare is C4ISR.  Illumination, Integration and Cognition.  Even without UAS, these impacts would be significant.  With them, along with PGM and we have a new ballgame in front of us.  

[Haiduk]

FPV drone of 11th public security brigade of National Guard has destroyed T-90M on left bank of Dnipro in Kherson oblast. This is the second T-90M destroyed there for 3-4 days. First one was destroyed near Pidstepne village, when it along with T-72B3 tried to attack UKR bridghead

 

Edited October 29, 2023 by Haiduk

[The_Capt]

1 hour ago, dan/california said:

It really seems to me that at least 75% of the work needed for a competent drone swarm was done to build this thing. You just have to have each submunition delivered by a quadcopter. Also, they should start making a new version of this for both HIMARS and ATACAMS/PRISM. 

APS ain't doing squat against that.

[Battlefront.com]

2 minutes ago, The_Capt said:

If one side has swarms that work and other doesn't or a means to deny them, the war is over before it starts. 

Some caveat I think are in order here!

First, swarms are inherently more of an advantage for a defender as they excel at disrupting something active (e.g. an armored attack) than something inactive (e.g. dismounted infantry sitting in trenches).  Therefore, an attacker with swarms and the ability to defeat them has an advantage, but not necessarily a decisive one.  Similar to how ISR + PGMs greatly favors the defender in this war.  On the other hand, if the defender has swarms and the attacker doesn't have a way to defeat them, then it is probably decisive.

Which gets us to the second caveat; swarms only work if you have enough of them to achieve your goals.  If you have 10,000 drones on hand and it takes 200 to get a tactical job done, then that's 500 attacks.  That might sound like a lot, but if this is what it takes to knock out a couple of vehicles, then no it isn't a lot at all.

Add these together and a defender with a large amount of swarms is likely to beat any attacker that lacks adequate counter measures.  "The war is over before it starts".  However, if the attacker has swarms and the defender lacks counter measures, the end result is less clear.  Current example... IDF with 1,000,000 drones for swarms may not make it significantly easier to take Gaza than if they had 0.  On the other hand, Hamas with 10,000 drones for swarms might be enough to stop IDF in its tracks if it can't stop them.

Steve