chrisl

I want to retire someplace quiet and dig a deep hole.  Watch 80s movies on DVDs off grid.  And maybe die in peace before our machine overlords enslave us all.

You are mixing up a few things here. Camera and LIDAR are about detecting and tracking objects, localisation (e.g. finding my position in relation to known landmarks) and finding out how many lanes there are on a road and on which you are (in case you don't have an HD map). The task of driving itself is (usually) not learned via camera or lidar directly but using trajectories which involve odometry (which can include above sensors, though).
Nitpicking aside, loads of training data are important but you can, and really have to, use synthetic data, i.e. simulation, too. This is because your autonomous system will experience situations that the excellent human driver hasn't shown you and it won't know how to get out of such a state. And you get there just by small compounding errors from localisation, odometry, etc.
The more relevant part for our discussion: You don't need bazillion tons of real life training data. If you have good simulation, the variation you get from that can offset the inaccuracies. What's more important, though: Again, we are really not talking about autonomous driving. Missing a truck in 1% of the cases kills people and ruins your company. So 99% accuracy isn't enough. But if my drone gets the tank in 50% of the cases and otherwise misses or hits something else I'm fine with that. And you can get there with way less than half the Internet for training data.
They do have China for that, I guess. But really I don't think you need specialized hardware for that. Much of the stuff will work on your average mobile.

I can see your point, economically-speaking.  However I think that strengthens an argument for pressing the vast majority of whatever economic capacity you do have for producing drones into the production of effective drone killers.
We are clearly at the beginning of the drone revolution that we all regularly discuss but we have only just got past duct-taping hand grenades to Mavic 3 Pros.  There is a hell of a long way to go before this domain resolves properly and we are able to clearly see what we need and how to use it.  There will almost certainly be a catalogue of false-start designs and dead-ends which sap countries production resources to little benefit (think multi-turreted tanks, turreted fighter aircraft, etc.).
My argument is that, while the above situation is ongoing, a smart country will absolutely engage in the general melee of drone and doctrine development (especially China, the US and anyone else for whom economic capacity isn’t such an issue) but will meanwhile maintain laser focus on a dirt-cheap design to hunt down and kill any small, airborne rf-emitter within 10km.
As has been noted by many already, if you lose the drone war in a future symmetrical, conventional conflict, you likely lose the war.  An efficient ‘drone fighter’ intended purely for area denial to all drones (except its own kind and until proper discrimination is practical) goes a long way towards mitigating that risk.

IDF and Hamas are not symmetrical conventional warfare, which is good news for hybrid warfare and insurgents.  Urban hybrid warfare is still unknown with respect to impacts….I guess we will see.  If the IDF had 1 million next gen UAS capable of autonomous targeting, backed up by some nightmare Boston Dynamics thing out of Black Mirror I suspect it would be a lot easier to take Gaza.
Having swarms and the C4ISR backbone behind them is not necessarily decisive…however, it is undecidable.  UAS currently cannot take and hold ground.  They have limited range but that is changing.  As such they are purpose built for denial.  We are seeing massive mutual denial in Ukraine right now and in 10 years this war will look like WW1 era AirPower with respect to technologies such as UAS and PGM…way too much at stake to not chase those.
What we have not see is the full potential of swarms on offence.  Here they will likely be part of an arms team - lighter infantry and deep fires seem to be the most likely suspects.  Corrosive warfare is a theory, and it has limits.  Manoeuvre warfare is nearly impossible if one’s opponent has working swarms you cannot counter and a C4ISR backbone behind it.  We have seen more than enough examples of why this is.  One could go for good ol Attrition warfare, seems to be Russias game.  But these new systems are just so damned cheap.  Short of Total War and crippling an opposing nations entire industry, it looks like one can swat UAS all day and never run out of targets.  PGM are also getting cheaper, as is data.
So we basically have a Big Undeciding in warfare.  Air Superiority, Maritime Superiority - both metrics of Control vs Denial.  Ground warfare was supposed to be the Domain of Decision, but it has become undecidable…until one can break an opponents C4ISR/PGM/Unmanned system while sustaining your own.
An Undecision is a powerful thing.

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. 

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.  

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

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?)
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.  
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.

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.

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.

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?)
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.  
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.

I'd think the Russians training waterfowl strapped with mines (two birds with one mine?)  would probably be more effective than anything "autonomous" that they can field today with their current resources.  Automatic?  Sure, that's Shahed.  Automatic with a basic IR sensor for picking out warm targets?  Probably, but not widely available.  Truly autonomous and using some kind of AI to pick targets?  Bring in the trained ducks.
Air defense against the Diamond Age swarm isn't going to be any single system - it's going to have to be many layers dispersed over a large volume, and insensitive to any particular node or 20 being knocked out.  Basically attack of the killer bees on both sides.  
Ground hugging drones is a nice approach for anything that can be a lightweight payload.  Lots of background to make them hard to pick out, but without the mobility issues of a UGV. Arguably a dumptruck full of ground hugging drones will be more effective than most UGV concepts.

In a very narrow domain.  Low SNR tracking of large numbers of objects at the resolution limit of my optical system using (deliberately) underpowered computers has been a headache of mine for the past decade. This is for targets entirely unrelated to anything of defense interest, but it's defense-adjacent, and there aren't good general solutions floating around out there.

In a very narrow domain.  Low SNR tracking of large numbers of objects at the resolution limit of my optical system using (deliberately) underpowered computers has been a headache of mine for the past decade. This is for targets entirely unrelated to anything of defense interest, but it's defense-adjacent, and there aren't good general solutions floating around out there.

Yeah, I'm very aware of that, and I suppose that's a cue for getting a little into why we don't have anti-drone drones.
There are two parts to the anti-drone drone: detection and attack.  The detection is the hard part.  Destruction is easy - we already have no end of systems that can very accurately destroy anything that you give them coordinates of.  We can accurately fire projectiles, exploding projectiles, exploding projectiles full of razor sharp hoops, high energy beams of photons, rings with chains on them, rings with strings on them, giant wads of gooey stuff, or anything you want to take out a drone.  But you have to detect it.
For an anti-drone drone, there are sort of two categories of drone you're targeting: open loop (no comm back to the sender) and closed loop (some comm back to the sender, whether full two-way control, occasional updates, or whatever).  
Detection of the first type (no comm), which includes Shaheds, is tricky - unlike the F-35, these *start* with the radar cross section of a goose* and then you can make that even smaller.  These things are all small on visual and radar cross sections because you can paint them and they don't have a lot of metal.  You're going to track them with frustrating "visual" algorithms, where "visual" can mean different things in the optical vs. radar wavelengths, but you're still trying to pick out changes in the scene to decide where the thing is.  I'm not going to spend much time on it, other than to say that unless you have really high signal to noise and high resolution (both of which the target is trying to reduce), it's a lot harder than you think, and in general you're not going to get there with simple image differencing.  And this problem exists for commless drones whether you're using another drone, a gun, or a death ray to take them down.  Shaheds at least have a very characteristic sound that you can probably use for detection and targeting once they're within audible range.
Detection of the second type (active comm) is easy.  It's transmitting, and transmitting enough to get clear signal back to its operator, who is farther away than you are if it's attacking you.  Triangulation is old technology.  Piece of cake: you lock onto the frequency, have some kind of sensor so you know your own orientation relative to the sensor, and just maneuver in a way to make the signal from the drone stronger until you hit it and destroy it with whatever mechanism you prefer.  Or have a few sensors that are networked to give you the position (helloooo MLAT) and shoot it with your favorite method of action-at-a-distance.
Except for one problem: whose drone did you just destroy?
In the Ukraine environment, IFF is the hard part of doing radio based anti-drone systems.  There are tons of things flying around, as evidenced by the daily releases of yet another view of every bit of ground combat we ever see.  It's not quite Diamond Age concentrations of them, but they're working on it.  And they're all sorts of random drones, including commercial drones, custom drones made with commercial off the shelf parts, custom drones with a mix of commercial and special mil parts, totally custom mil drones, and who knows what else. And they're all using similar frequencies, because the combination of physics and the atmosphere force you to the same frequencies if you want a particular range and data rate at powers that you can reasonably supply to both the ground operator and drone with batteries.  If you don't sort out the IFF thing and you set an autonomous anti-radiation based anti-drone system loose, it's just as likely to attack its allied drones as the enemy drones, because it has no way to tell them apart.  That means you have to have your complete drone ecosystem integrated (ring that cash register over at Lockheed/Northrop Grumman/Raytheon!!) or you're just going to be attacking your own stuff.  
And part of why we aren't seeing even rudimentary versions of it in Ukraine is that it's not a function that people were already spending much effort on for commercial/hobbyist drones. You can't just pop over to Robotshop.com or Alibaba and order tunable RF sensor kits (or a few thousand of them) the way you can other types of sensor, or actuators for operating your 3D printed grenade dropper.  It's possible to get relatively inexpensive software-defined radio modules that are small (that's what feeds ADSBExchange so you can see who's flying around Ukraine), but the environment is so variable, along with the need to confirm what drone you're attacking, that at least for now you're going to need a human in the loop, even if you can semi-automate your remote control drone sensor.  And even with a human in the loop, nobody is painting national flags on their drones, so unless you know "this is one that our side makes" after you get up close to it (assuming you're doing that, rather than sending a death ray at it from 5 km), you really don't know who you're shooting down.  So the basic tech isn't all that hard, but because it's not just point and shoot or point and drop, it's a lot more dependent on integration of the whole system to be usable.
*geese, like all waterfowl, are incredibly mean and probably deserve to die. That's why there's a book entitled "Ducks and how to make them pay".  If we can do an autonomous system for drones, it should probably be immediately applied to geese and ducks.

Yeah, I'm very aware of that, and I suppose that's a cue for getting a little into why we don't have anti-drone drones.
There are two parts to the anti-drone drone: detection and attack.  The detection is the hard part.  Destruction is easy - we already have no end of systems that can very accurately destroy anything that you give them coordinates of.  We can accurately fire projectiles, exploding projectiles, exploding projectiles full of razor sharp hoops, high energy beams of photons, rings with chains on them, rings with strings on them, giant wads of gooey stuff, or anything you want to take out a drone.  But you have to detect it.
For an anti-drone drone, there are sort of two categories of drone you're targeting: open loop (no comm back to the sender) and closed loop (some comm back to the sender, whether full two-way control, occasional updates, or whatever).  
Detection of the first type (no comm), which includes Shaheds, is tricky - unlike the F-35, these *start* with the radar cross section of a goose* and then you can make that even smaller.  These things are all small on visual and radar cross sections because you can paint them and they don't have a lot of metal.  You're going to track them with frustrating "visual" algorithms, where "visual" can mean different things in the optical vs. radar wavelengths, but you're still trying to pick out changes in the scene to decide where the thing is.  I'm not going to spend much time on it, other than to say that unless you have really high signal to noise and high resolution (both of which the target is trying to reduce), it's a lot harder than you think, and in general you're not going to get there with simple image differencing.  And this problem exists for commless drones whether you're using another drone, a gun, or a death ray to take them down.  Shaheds at least have a very characteristic sound that you can probably use for detection and targeting once they're within audible range.
Detection of the second type (active comm) is easy.  It's transmitting, and transmitting enough to get clear signal back to its operator, who is farther away than you are if it's attacking you.  Triangulation is old technology.  Piece of cake: you lock onto the frequency, have some kind of sensor so you know your own orientation relative to the sensor, and just maneuver in a way to make the signal from the drone stronger until you hit it and destroy it with whatever mechanism you prefer.  Or have a few sensors that are networked to give you the position (helloooo MLAT) and shoot it with your favorite method of action-at-a-distance.
Except for one problem: whose drone did you just destroy?
In the Ukraine environment, IFF is the hard part of doing radio based anti-drone systems.  There are tons of things flying around, as evidenced by the daily releases of yet another view of every bit of ground combat we ever see.  It's not quite Diamond Age concentrations of them, but they're working on it.  And they're all sorts of random drones, including commercial drones, custom drones made with commercial off the shelf parts, custom drones with a mix of commercial and special mil parts, totally custom mil drones, and who knows what else. And they're all using similar frequencies, because the combination of physics and the atmosphere force you to the same frequencies if you want a particular range and data rate at powers that you can reasonably supply to both the ground operator and drone with batteries.  If you don't sort out the IFF thing and you set an autonomous anti-radiation based anti-drone system loose, it's just as likely to attack its allied drones as the enemy drones, because it has no way to tell them apart.  That means you have to have your complete drone ecosystem integrated (ring that cash register over at Lockheed/Northrop Grumman/Raytheon!!) or you're just going to be attacking your own stuff.  
And part of why we aren't seeing even rudimentary versions of it in Ukraine is that it's not a function that people were already spending much effort on for commercial/hobbyist drones. You can't just pop over to Robotshop.com or Alibaba and order tunable RF sensor kits (or a few thousand of them) the way you can other types of sensor, or actuators for operating your 3D printed grenade dropper.  It's possible to get relatively inexpensive software-defined radio modules that are small (that's what feeds ADSBExchange so you can see who's flying around Ukraine), but the environment is so variable, along with the need to confirm what drone you're attacking, that at least for now you're going to need a human in the loop, even if you can semi-automate your remote control drone sensor.  And even with a human in the loop, nobody is painting national flags on their drones, so unless you know "this is one that our side makes" after you get up close to it (assuming you're doing that, rather than sending a death ray at it from 5 km), you really don't know who you're shooting down.  So the basic tech isn't all that hard, but because it's not just point and shoot or point and drop, it's a lot more dependent on integration of the whole system to be usable.
*geese, like all waterfowl, are incredibly mean and probably deserve to die. That's why there's a book entitled "Ducks and how to make them pay".  If we can do an autonomous system for drones, it should probably be immediately applied to geese and ducks.

In a very narrow domain.  Low SNR tracking of large numbers of objects at the resolution limit of my optical system using (deliberately) underpowered computers has been a headache of mine for the past decade. This is for targets entirely unrelated to anything of defense interest, but it's defense-adjacent, and there aren't good general solutions floating around out there.

In a very narrow domain.  Low SNR tracking of large numbers of objects at the resolution limit of my optical system using (deliberately) underpowered computers has been a headache of mine for the past decade. This is for targets entirely unrelated to anything of defense interest, but it's defense-adjacent, and there aren't good general solutions floating around out there.

I'd think the Russians training waterfowl strapped with mines (two birds with one mine?)  would probably be more effective than anything "autonomous" that they can field today with their current resources.  Automatic?  Sure, that's Shahed.  Automatic with a basic IR sensor for picking out warm targets?  Probably, but not widely available.  Truly autonomous and using some kind of AI to pick targets?  Bring in the trained ducks.
Air defense against the Diamond Age swarm isn't going to be any single system - it's going to have to be many layers dispersed over a large volume, and insensitive to any particular node or 20 being knocked out.  Basically attack of the killer bees on both sides.  
Ground hugging drones is a nice approach for anything that can be a lightweight payload.  Lots of background to make them hard to pick out, but without the mobility issues of a UGV. Arguably a dumptruck full of ground hugging drones will be more effective than most UGV concepts.

Yeah, I'm very aware of that, and I suppose that's a cue for getting a little into why we don't have anti-drone drones.
There are two parts to the anti-drone drone: detection and attack.  The detection is the hard part.  Destruction is easy - we already have no end of systems that can very accurately destroy anything that you give them coordinates of.  We can accurately fire projectiles, exploding projectiles, exploding projectiles full of razor sharp hoops, high energy beams of photons, rings with chains on them, rings with strings on them, giant wads of gooey stuff, or anything you want to take out a drone.  But you have to detect it.
For an anti-drone drone, there are sort of two categories of drone you're targeting: open loop (no comm back to the sender) and closed loop (some comm back to the sender, whether full two-way control, occasional updates, or whatever).  
Detection of the first type (no comm), which includes Shaheds, is tricky - unlike the F-35, these *start* with the radar cross section of a goose* and then you can make that even smaller.  These things are all small on visual and radar cross sections because you can paint them and they don't have a lot of metal.  You're going to track them with frustrating "visual" algorithms, where "visual" can mean different things in the optical vs. radar wavelengths, but you're still trying to pick out changes in the scene to decide where the thing is.  I'm not going to spend much time on it, other than to say that unless you have really high signal to noise and high resolution (both of which the target is trying to reduce), it's a lot harder than you think, and in general you're not going to get there with simple image differencing.  And this problem exists for commless drones whether you're using another drone, a gun, or a death ray to take them down.  Shaheds at least have a very characteristic sound that you can probably use for detection and targeting once they're within audible range.
Detection of the second type (active comm) is easy.  It's transmitting, and transmitting enough to get clear signal back to its operator, who is farther away than you are if it's attacking you.  Triangulation is old technology.  Piece of cake: you lock onto the frequency, have some kind of sensor so you know your own orientation relative to the sensor, and just maneuver in a way to make the signal from the drone stronger until you hit it and destroy it with whatever mechanism you prefer.  Or have a few sensors that are networked to give you the position (helloooo MLAT) and shoot it with your favorite method of action-at-a-distance.
Except for one problem: whose drone did you just destroy?
In the Ukraine environment, IFF is the hard part of doing radio based anti-drone systems.  There are tons of things flying around, as evidenced by the daily releases of yet another view of every bit of ground combat we ever see.  It's not quite Diamond Age concentrations of them, but they're working on it.  And they're all sorts of random drones, including commercial drones, custom drones made with commercial off the shelf parts, custom drones with a mix of commercial and special mil parts, totally custom mil drones, and who knows what else. And they're all using similar frequencies, because the combination of physics and the atmosphere force you to the same frequencies if you want a particular range and data rate at powers that you can reasonably supply to both the ground operator and drone with batteries.  If you don't sort out the IFF thing and you set an autonomous anti-radiation based anti-drone system loose, it's just as likely to attack its allied drones as the enemy drones, because it has no way to tell them apart.  That means you have to have your complete drone ecosystem integrated (ring that cash register over at Lockheed/Northrop Grumman/Raytheon!!) or you're just going to be attacking your own stuff.  
And part of why we aren't seeing even rudimentary versions of it in Ukraine is that it's not a function that people were already spending much effort on for commercial/hobbyist drones. You can't just pop over to Robotshop.com or Alibaba and order tunable RF sensor kits (or a few thousand of them) the way you can other types of sensor, or actuators for operating your 3D printed grenade dropper.  It's possible to get relatively inexpensive software-defined radio modules that are small (that's what feeds ADSBExchange so you can see who's flying around Ukraine), but the environment is so variable, along with the need to confirm what drone you're attacking, that at least for now you're going to need a human in the loop, even if you can semi-automate your remote control drone sensor.  And even with a human in the loop, nobody is painting national flags on their drones, so unless you know "this is one that our side makes" after you get up close to it (assuming you're doing that, rather than sending a death ray at it from 5 km), you really don't know who you're shooting down.  So the basic tech isn't all that hard, but because it's not just point and shoot or point and drop, it's a lot more dependent on integration of the whole system to be usable.
*geese, like all waterfowl, are incredibly mean and probably deserve to die. That's why there's a book entitled "Ducks and how to make them pay".  If we can do an autonomous system for drones, it should probably be immediately applied to geese and ducks.

Yeah, I'm very aware of that, and I suppose that's a cue for getting a little into why we don't have anti-drone drones.
There are two parts to the anti-drone drone: detection and attack.  The detection is the hard part.  Destruction is easy - we already have no end of systems that can very accurately destroy anything that you give them coordinates of.  We can accurately fire projectiles, exploding projectiles, exploding projectiles full of razor sharp hoops, high energy beams of photons, rings with chains on them, rings with strings on them, giant wads of gooey stuff, or anything you want to take out a drone.  But you have to detect it.
For an anti-drone drone, there are sort of two categories of drone you're targeting: open loop (no comm back to the sender) and closed loop (some comm back to the sender, whether full two-way control, occasional updates, or whatever).  
Detection of the first type (no comm), which includes Shaheds, is tricky - unlike the F-35, these *start* with the radar cross section of a goose* and then you can make that even smaller.  These things are all small on visual and radar cross sections because you can paint them and they don't have a lot of metal.  You're going to track them with frustrating "visual" algorithms, where "visual" can mean different things in the optical vs. radar wavelengths, but you're still trying to pick out changes in the scene to decide where the thing is.  I'm not going to spend much time on it, other than to say that unless you have really high signal to noise and high resolution (both of which the target is trying to reduce), it's a lot harder than you think, and in general you're not going to get there with simple image differencing.  And this problem exists for commless drones whether you're using another drone, a gun, or a death ray to take them down.  Shaheds at least have a very characteristic sound that you can probably use for detection and targeting once they're within audible range.
Detection of the second type (active comm) is easy.  It's transmitting, and transmitting enough to get clear signal back to its operator, who is farther away than you are if it's attacking you.  Triangulation is old technology.  Piece of cake: you lock onto the frequency, have some kind of sensor so you know your own orientation relative to the sensor, and just maneuver in a way to make the signal from the drone stronger until you hit it and destroy it with whatever mechanism you prefer.  Or have a few sensors that are networked to give you the position (helloooo MLAT) and shoot it with your favorite method of action-at-a-distance.
Except for one problem: whose drone did you just destroy?
In the Ukraine environment, IFF is the hard part of doing radio based anti-drone systems.  There are tons of things flying around, as evidenced by the daily releases of yet another view of every bit of ground combat we ever see.  It's not quite Diamond Age concentrations of them, but they're working on it.  And they're all sorts of random drones, including commercial drones, custom drones made with commercial off the shelf parts, custom drones with a mix of commercial and special mil parts, totally custom mil drones, and who knows what else. And they're all using similar frequencies, because the combination of physics and the atmosphere force you to the same frequencies if you want a particular range and data rate at powers that you can reasonably supply to both the ground operator and drone with batteries.  If you don't sort out the IFF thing and you set an autonomous anti-radiation based anti-drone system loose, it's just as likely to attack its allied drones as the enemy drones, because it has no way to tell them apart.  That means you have to have your complete drone ecosystem integrated (ring that cash register over at Lockheed/Northrop Grumman/Raytheon!!) or you're just going to be attacking your own stuff.  
And part of why we aren't seeing even rudimentary versions of it in Ukraine is that it's not a function that people were already spending much effort on for commercial/hobbyist drones. You can't just pop over to Robotshop.com or Alibaba and order tunable RF sensor kits (or a few thousand of them) the way you can other types of sensor, or actuators for operating your 3D printed grenade dropper.  It's possible to get relatively inexpensive software-defined radio modules that are small (that's what feeds ADSBExchange so you can see who's flying around Ukraine), but the environment is so variable, along with the need to confirm what drone you're attacking, that at least for now you're going to need a human in the loop, even if you can semi-automate your remote control drone sensor.  And even with a human in the loop, nobody is painting national flags on their drones, so unless you know "this is one that our side makes" after you get up close to it (assuming you're doing that, rather than sending a death ray at it from 5 km), you really don't know who you're shooting down.  So the basic tech isn't all that hard, but because it's not just point and shoot or point and drop, it's a lot more dependent on integration of the whole system to be usable.
*geese, like all waterfowl, are incredibly mean and probably deserve to die. That's why there's a book entitled "Ducks and how to make them pay".  If we can do an autonomous system for drones, it should probably be immediately applied to geese and ducks.

Yeah, I'm very aware of that, and I suppose that's a cue for getting a little into why we don't have anti-drone drones.
There are two parts to the anti-drone drone: detection and attack.  The detection is the hard part.  Destruction is easy - we already have no end of systems that can very accurately destroy anything that you give them coordinates of.  We can accurately fire projectiles, exploding projectiles, exploding projectiles full of razor sharp hoops, high energy beams of photons, rings with chains on them, rings with strings on them, giant wads of gooey stuff, or anything you want to take out a drone.  But you have to detect it.
For an anti-drone drone, there are sort of two categories of drone you're targeting: open loop (no comm back to the sender) and closed loop (some comm back to the sender, whether full two-way control, occasional updates, or whatever).  
Detection of the first type (no comm), which includes Shaheds, is tricky - unlike the F-35, these *start* with the radar cross section of a goose* and then you can make that even smaller.  These things are all small on visual and radar cross sections because you can paint them and they don't have a lot of metal.  You're going to track them with frustrating "visual" algorithms, where "visual" can mean different things in the optical vs. radar wavelengths, but you're still trying to pick out changes in the scene to decide where the thing is.  I'm not going to spend much time on it, other than to say that unless you have really high signal to noise and high resolution (both of which the target is trying to reduce), it's a lot harder than you think, and in general you're not going to get there with simple image differencing.  And this problem exists for commless drones whether you're using another drone, a gun, or a death ray to take them down.  Shaheds at least have a very characteristic sound that you can probably use for detection and targeting once they're within audible range.
Detection of the second type (active comm) is easy.  It's transmitting, and transmitting enough to get clear signal back to its operator, who is farther away than you are if it's attacking you.  Triangulation is old technology.  Piece of cake: you lock onto the frequency, have some kind of sensor so you know your own orientation relative to the sensor, and just maneuver in a way to make the signal from the drone stronger until you hit it and destroy it with whatever mechanism you prefer.  Or have a few sensors that are networked to give you the position (helloooo MLAT) and shoot it with your favorite method of action-at-a-distance.
Except for one problem: whose drone did you just destroy?
In the Ukraine environment, IFF is the hard part of doing radio based anti-drone systems.  There are tons of things flying around, as evidenced by the daily releases of yet another view of every bit of ground combat we ever see.  It's not quite Diamond Age concentrations of them, but they're working on it.  And they're all sorts of random drones, including commercial drones, custom drones made with commercial off the shelf parts, custom drones with a mix of commercial and special mil parts, totally custom mil drones, and who knows what else. And they're all using similar frequencies, because the combination of physics and the atmosphere force you to the same frequencies if you want a particular range and data rate at powers that you can reasonably supply to both the ground operator and drone with batteries.  If you don't sort out the IFF thing and you set an autonomous anti-radiation based anti-drone system loose, it's just as likely to attack its allied drones as the enemy drones, because it has no way to tell them apart.  That means you have to have your complete drone ecosystem integrated (ring that cash register over at Lockheed/Northrop Grumman/Raytheon!!) or you're just going to be attacking your own stuff.  
And part of why we aren't seeing even rudimentary versions of it in Ukraine is that it's not a function that people were already spending much effort on for commercial/hobbyist drones. You can't just pop over to Robotshop.com or Alibaba and order tunable RF sensor kits (or a few thousand of them) the way you can other types of sensor, or actuators for operating your 3D printed grenade dropper.  It's possible to get relatively inexpensive software-defined radio modules that are small (that's what feeds ADSBExchange so you can see who's flying around Ukraine), but the environment is so variable, along with the need to confirm what drone you're attacking, that at least for now you're going to need a human in the loop, even if you can semi-automate your remote control drone sensor.  And even with a human in the loop, nobody is painting national flags on their drones, so unless you know "this is one that our side makes" after you get up close to it (assuming you're doing that, rather than sending a death ray at it from 5 km), you really don't know who you're shooting down.  So the basic tech isn't all that hard, but because it's not just point and shoot or point and drop, it's a lot more dependent on integration of the whole system to be usable.
*geese, like all waterfowl, are incredibly mean and probably deserve to die. That's why there's a book entitled "Ducks and how to make them pay".  If we can do an autonomous system for drones, it should probably be immediately applied to geese and ducks.

Yeah, I'm very aware of that, and I suppose that's a cue for getting a little into why we don't have anti-drone drones.
There are two parts to the anti-drone drone: detection and attack.  The detection is the hard part.  Destruction is easy - we already have no end of systems that can very accurately destroy anything that you give them coordinates of.  We can accurately fire projectiles, exploding projectiles, exploding projectiles full of razor sharp hoops, high energy beams of photons, rings with chains on them, rings with strings on them, giant wads of gooey stuff, or anything you want to take out a drone.  But you have to detect it.
For an anti-drone drone, there are sort of two categories of drone you're targeting: open loop (no comm back to the sender) and closed loop (some comm back to the sender, whether full two-way control, occasional updates, or whatever).  
Detection of the first type (no comm), which includes Shaheds, is tricky - unlike the F-35, these *start* with the radar cross section of a goose* and then you can make that even smaller.  These things are all small on visual and radar cross sections because you can paint them and they don't have a lot of metal.  You're going to track them with frustrating "visual" algorithms, where "visual" can mean different things in the optical vs. radar wavelengths, but you're still trying to pick out changes in the scene to decide where the thing is.  I'm not going to spend much time on it, other than to say that unless you have really high signal to noise and high resolution (both of which the target is trying to reduce), it's a lot harder than you think, and in general you're not going to get there with simple image differencing.  And this problem exists for commless drones whether you're using another drone, a gun, or a death ray to take them down.  Shaheds at least have a very characteristic sound that you can probably use for detection and targeting once they're within audible range.
Detection of the second type (active comm) is easy.  It's transmitting, and transmitting enough to get clear signal back to its operator, who is farther away than you are if it's attacking you.  Triangulation is old technology.  Piece of cake: you lock onto the frequency, have some kind of sensor so you know your own orientation relative to the sensor, and just maneuver in a way to make the signal from the drone stronger until you hit it and destroy it with whatever mechanism you prefer.  Or have a few sensors that are networked to give you the position (helloooo MLAT) and shoot it with your favorite method of action-at-a-distance.
Except for one problem: whose drone did you just destroy?
In the Ukraine environment, IFF is the hard part of doing radio based anti-drone systems.  There are tons of things flying around, as evidenced by the daily releases of yet another view of every bit of ground combat we ever see.  It's not quite Diamond Age concentrations of them, but they're working on it.  And they're all sorts of random drones, including commercial drones, custom drones made with commercial off the shelf parts, custom drones with a mix of commercial and special mil parts, totally custom mil drones, and who knows what else. And they're all using similar frequencies, because the combination of physics and the atmosphere force you to the same frequencies if you want a particular range and data rate at powers that you can reasonably supply to both the ground operator and drone with batteries.  If you don't sort out the IFF thing and you set an autonomous anti-radiation based anti-drone system loose, it's just as likely to attack its allied drones as the enemy drones, because it has no way to tell them apart.  That means you have to have your complete drone ecosystem integrated (ring that cash register over at Lockheed/Northrop Grumman/Raytheon!!) or you're just going to be attacking your own stuff.  
And part of why we aren't seeing even rudimentary versions of it in Ukraine is that it's not a function that people were already spending much effort on for commercial/hobbyist drones. You can't just pop over to Robotshop.com or Alibaba and order tunable RF sensor kits (or a few thousand of them) the way you can other types of sensor, or actuators for operating your 3D printed grenade dropper.  It's possible to get relatively inexpensive software-defined radio modules that are small (that's what feeds ADSBExchange so you can see who's flying around Ukraine), but the environment is so variable, along with the need to confirm what drone you're attacking, that at least for now you're going to need a human in the loop, even if you can semi-automate your remote control drone sensor.  And even with a human in the loop, nobody is painting national flags on their drones, so unless you know "this is one that our side makes" after you get up close to it (assuming you're doing that, rather than sending a death ray at it from 5 km), you really don't know who you're shooting down.  So the basic tech isn't all that hard, but because it's not just point and shoot or point and drop, it's a lot more dependent on integration of the whole system to be usable.
*geese, like all waterfowl, are incredibly mean and probably deserve to die. That's why there's a book entitled "Ducks and how to make them pay".  If we can do an autonomous system for drones, it should probably be immediately applied to geese and ducks.

Yeah, I'm very aware of that, and I suppose that's a cue for getting a little into why we don't have anti-drone drones.
There are two parts to the anti-drone drone: detection and attack.  The detection is the hard part.  Destruction is easy - we already have no end of systems that can very accurately destroy anything that you give them coordinates of.  We can accurately fire projectiles, exploding projectiles, exploding projectiles full of razor sharp hoops, high energy beams of photons, rings with chains on them, rings with strings on them, giant wads of gooey stuff, or anything you want to take out a drone.  But you have to detect it.
For an anti-drone drone, there are sort of two categories of drone you're targeting: open loop (no comm back to the sender) and closed loop (some comm back to the sender, whether full two-way control, occasional updates, or whatever).  
Detection of the first type (no comm), which includes Shaheds, is tricky - unlike the F-35, these *start* with the radar cross section of a goose* and then you can make that even smaller.  These things are all small on visual and radar cross sections because you can paint them and they don't have a lot of metal.  You're going to track them with frustrating "visual" algorithms, where "visual" can mean different things in the optical vs. radar wavelengths, but you're still trying to pick out changes in the scene to decide where the thing is.  I'm not going to spend much time on it, other than to say that unless you have really high signal to noise and high resolution (both of which the target is trying to reduce), it's a lot harder than you think, and in general you're not going to get there with simple image differencing.  And this problem exists for commless drones whether you're using another drone, a gun, or a death ray to take them down.  Shaheds at least have a very characteristic sound that you can probably use for detection and targeting once they're within audible range.
Detection of the second type (active comm) is easy.  It's transmitting, and transmitting enough to get clear signal back to its operator, who is farther away than you are if it's attacking you.  Triangulation is old technology.  Piece of cake: you lock onto the frequency, have some kind of sensor so you know your own orientation relative to the sensor, and just maneuver in a way to make the signal from the drone stronger until you hit it and destroy it with whatever mechanism you prefer.  Or have a few sensors that are networked to give you the position (helloooo MLAT) and shoot it with your favorite method of action-at-a-distance.
Except for one problem: whose drone did you just destroy?
In the Ukraine environment, IFF is the hard part of doing radio based anti-drone systems.  There are tons of things flying around, as evidenced by the daily releases of yet another view of every bit of ground combat we ever see.  It's not quite Diamond Age concentrations of them, but they're working on it.  And they're all sorts of random drones, including commercial drones, custom drones made with commercial off the shelf parts, custom drones with a mix of commercial and special mil parts, totally custom mil drones, and who knows what else. And they're all using similar frequencies, because the combination of physics and the atmosphere force you to the same frequencies if you want a particular range and data rate at powers that you can reasonably supply to both the ground operator and drone with batteries.  If you don't sort out the IFF thing and you set an autonomous anti-radiation based anti-drone system loose, it's just as likely to attack its allied drones as the enemy drones, because it has no way to tell them apart.  That means you have to have your complete drone ecosystem integrated (ring that cash register over at Lockheed/Northrop Grumman/Raytheon!!) or you're just going to be attacking your own stuff.  
And part of why we aren't seeing even rudimentary versions of it in Ukraine is that it's not a function that people were already spending much effort on for commercial/hobbyist drones. You can't just pop over to Robotshop.com or Alibaba and order tunable RF sensor kits (or a few thousand of them) the way you can other types of sensor, or actuators for operating your 3D printed grenade dropper.  It's possible to get relatively inexpensive software-defined radio modules that are small (that's what feeds ADSBExchange so you can see who's flying around Ukraine), but the environment is so variable, along with the need to confirm what drone you're attacking, that at least for now you're going to need a human in the loop, even if you can semi-automate your remote control drone sensor.  And even with a human in the loop, nobody is painting national flags on their drones, so unless you know "this is one that our side makes" after you get up close to it (assuming you're doing that, rather than sending a death ray at it from 5 km), you really don't know who you're shooting down.  So the basic tech isn't all that hard, but because it's not just point and shoot or point and drop, it's a lot more dependent on integration of the whole system to be usable.
*geese, like all waterfowl, are incredibly mean and probably deserve to die. That's why there's a book entitled "Ducks and how to make them pay".  If we can do an autonomous system for drones, it should probably be immediately applied to geese and ducks.

Yeah, I'm very aware of that, and I suppose that's a cue for getting a little into why we don't have anti-drone drones.
There are two parts to the anti-drone drone: detection and attack.  The detection is the hard part.  Destruction is easy - we already have no end of systems that can very accurately destroy anything that you give them coordinates of.  We can accurately fire projectiles, exploding projectiles, exploding projectiles full of razor sharp hoops, high energy beams of photons, rings with chains on them, rings with strings on them, giant wads of gooey stuff, or anything you want to take out a drone.  But you have to detect it.
For an anti-drone drone, there are sort of two categories of drone you're targeting: open loop (no comm back to the sender) and closed loop (some comm back to the sender, whether full two-way control, occasional updates, or whatever).  
Detection of the first type (no comm), which includes Shaheds, is tricky - unlike the F-35, these *start* with the radar cross section of a goose* and then you can make that even smaller.  These things are all small on visual and radar cross sections because you can paint them and they don't have a lot of metal.  You're going to track them with frustrating "visual" algorithms, where "visual" can mean different things in the optical vs. radar wavelengths, but you're still trying to pick out changes in the scene to decide where the thing is.  I'm not going to spend much time on it, other than to say that unless you have really high signal to noise and high resolution (both of which the target is trying to reduce), it's a lot harder than you think, and in general you're not going to get there with simple image differencing.  And this problem exists for commless drones whether you're using another drone, a gun, or a death ray to take them down.  Shaheds at least have a very characteristic sound that you can probably use for detection and targeting once they're within audible range.
Detection of the second type (active comm) is easy.  It's transmitting, and transmitting enough to get clear signal back to its operator, who is farther away than you are if it's attacking you.  Triangulation is old technology.  Piece of cake: you lock onto the frequency, have some kind of sensor so you know your own orientation relative to the sensor, and just maneuver in a way to make the signal from the drone stronger until you hit it and destroy it with whatever mechanism you prefer.  Or have a few sensors that are networked to give you the position (helloooo MLAT) and shoot it with your favorite method of action-at-a-distance.
Except for one problem: whose drone did you just destroy?
In the Ukraine environment, IFF is the hard part of doing radio based anti-drone systems.  There are tons of things flying around, as evidenced by the daily releases of yet another view of every bit of ground combat we ever see.  It's not quite Diamond Age concentrations of them, but they're working on it.  And they're all sorts of random drones, including commercial drones, custom drones made with commercial off the shelf parts, custom drones with a mix of commercial and special mil parts, totally custom mil drones, and who knows what else. And they're all using similar frequencies, because the combination of physics and the atmosphere force you to the same frequencies if you want a particular range and data rate at powers that you can reasonably supply to both the ground operator and drone with batteries.  If you don't sort out the IFF thing and you set an autonomous anti-radiation based anti-drone system loose, it's just as likely to attack its allied drones as the enemy drones, because it has no way to tell them apart.  That means you have to have your complete drone ecosystem integrated (ring that cash register over at Lockheed/Northrop Grumman/Raytheon!!) or you're just going to be attacking your own stuff.  
And part of why we aren't seeing even rudimentary versions of it in Ukraine is that it's not a function that people were already spending much effort on for commercial/hobbyist drones. You can't just pop over to Robotshop.com or Alibaba and order tunable RF sensor kits (or a few thousand of them) the way you can other types of sensor, or actuators for operating your 3D printed grenade dropper.  It's possible to get relatively inexpensive software-defined radio modules that are small (that's what feeds ADSBExchange so you can see who's flying around Ukraine), but the environment is so variable, along with the need to confirm what drone you're attacking, that at least for now you're going to need a human in the loop, even if you can semi-automate your remote control drone sensor.  And even with a human in the loop, nobody is painting national flags on their drones, so unless you know "this is one that our side makes" after you get up close to it (assuming you're doing that, rather than sending a death ray at it from 5 km), you really don't know who you're shooting down.  So the basic tech isn't all that hard, but because it's not just point and shoot or point and drop, it's a lot more dependent on integration of the whole system to be usable.
*geese, like all waterfowl, are incredibly mean and probably deserve to die. That's why there's a book entitled "Ducks and how to make them pay".  If we can do an autonomous system for drones, it should probably be immediately applied to geese and ducks.