Had a chance to see a live demo last month. Looks great, can do a lot more things than an SO-101 and the teleop via the app if both fun and useful. Would definitely buy if I had the money.
My roommate and I are still working on Tornyol, our mosquito killing drone! It uses ultrasonic sonar to detect mosquitoes, and missile control theory to ram into mosquitoes and grind them in its propellers.
Our target platform is a 40 grams tinywhoop so it’s safe to fly everywhere and makes almost no noise :). A Roomba for mosquitoes!
The main plus compared to traditional systems is that a drone can cover an enormous surface in a short time compared to static systems or man-portable insecticide spraying. Our goal is to be competitive with ITNs against Malaria.
Please make sure it is specific to mosquitos and does not attack other insects.
Insect populations worldwide are experiencing significant declines in both abundance and diversity, with several studies reporting reductions ranging from 40% to 75% over recent decades. Estimates suggest that 5%–10% of all insect species have disappeared in the last 150 years, and some global meta-analyses indicate terrestrial insect populations are declining by close to 9% per decade.
> If you don’t want to kill flies, wasps, bees, or other useful pollinators while eradicating the tiny little bloodsuckers that are the drone’s target, you need to be able to not only locate bugs, but discriminate mosquitoes from the others.
> For this, he uses the micro-doppler signatures that the different wing beats of the various insects put out. Wasps have a very wide-band doppler echo – their relatively long and thin wings are moving slower at the roots than at the tips. Flies, on the other hand, have stubbier wings, and emit a tighter echo signal. The mosquito signal is even tighter.
Fascinating engineering! Doesn't seem like it would be possible but it apparently is. There's also more visuals at about 17 minutes in the video embedded in that article, the signatures seem fairly distinct.
Imagine the sound a mosquito makes when it flies near your ear; it's quite distinct. I'm sure it's possible to distinguish mosquitos based on that (which is a factor related to the doppler signature mentioned).
I wonder how distinct it is, really. It sticks out to us, but “mosquitos is enemy #1” is one of the strongest evolutionary pressure we’ve got, right? And one of the few that persists to this day.
Our brains probably have a dedicated cluster of neurons in there somewhere specifically looking for the Mosquito noise.
Don't want to underestimate how disastrous this could be for other insects. Even ignoring the impact on them, the impact on our needs to maintain pollinator populations.
I mean.. if they venture into human indoors they are already doomed in the first place. Not much scope of proliferating in such an artificial environment.
Hadn't seen this before, this is awesome! I lived in Cameroon and Kenya briefly doing some consulting work and mosquitos still wreak havoc across the continent (and now living in DC I wouldn't mind having one of these in the summer for my place). I'm curious if you're also thinking about defense applications -- I would imagine that a super low cost drone that could help take out a shahed or other Russian drone that are wreaking havoc on Ukraine would be quite valuable
Glad to hear we could be of help! Some of our tech could be used for defense, but traditional defense companies and ukrainian startups already do low-cost shahed interceptors.
My impression is the solutions are still somewhat lacking/necessary -- I know Frankenburg, Eric Schmidt's stealth startup, and surely the primes are all working on it but given how many shaheds are still getting through (plus all the drone action at the frontline) I imagine there's still a market for low-cost; especially if they're largely autonomous
it’s a crowded market where politics and connections are worth more than technical expertise
This is 100% true.
Kill mosquitoes first. Then go for defense contracts when you can show you have sensors good enough to hunt and kill bugs.
I guarantee solving the bug use case first will put you head and shoulders above all the clueless UAS/cUAS companies out there these days - and there are TONS of them.
Just imagining how you'd test this in America. Just launch your target autonomous flying drone and then have the second one intercept it. Can you book range time at white sands?
This is an interesting idea. One thing that might help targeting is to have some sort of chemical that attracts the mosquitoes. In that way you can bring your target to you.
No to discourage you ,but how do you handle a real world cluttered room where mosquito's will be able to shelter in the clutter, under table, drawers etc.
mosquito generally bite you on your legs , say when you are sitting in a chair...the area under the chair is a pretty complex space to navigate for a flying bot
Very interesting idea! I wonder if a political campaign one day will be to start a program that eradicates mosquitos via drone fleets, not just in the context of malaria protection but also in just nuisance reduction. There are similar programs in place in certain metro areas that already do mosquito control (using chemicals of varying toxicity), so it's not as wild of an idea as it probably sounds.
My friend once came up with a joke idea for a solar powered ransomware drone that would fly to a random roof and jam wifi signal until someone paid it to leave.
There are bio solutions, e.g. my city puts mosquito-larva-killing bacteria in the river and the lakes.
It works okay, but they are unable target _all_ water surface. They use drones, they give out these bacteria to people so they put it in the rainwater tanks, etc.
Yeah, it’s one of our goal to work for government agencies at some point to implement city-wide mosquito control. 10 of our drones could cover a square kilometer, so we’d be a lot more efficient working at the city level rather than at the individual household level.
Ans there is also a recent post where someone use a similar device to light the mosquito https://news.ycombinator.com/item?id=44005200 (20 points | May 2025 | 5 comments) and you must give the final bow that sound safer. (Protip: Buy an Electric Fly Swatter)
there is a crowdfunding effort for one going on right now for such a device. I think the price is around $500. the videos are equally awesome and hilarious as they vaporize into a little puff of smoke
That will end up either dangerous or unreleased. Their system sends a 40W laser, which is what you use to cut plastics. There’s no way to make this safe as even a diffuse secondary reflection out of the field of view could blind someone.
ya, your absolutely right. still the idea of setting up an array of them around my house blasting the never ending barrage of West Nile virus attack drones as they cross the perimeter is pretty fun to think about. I suppose a well placed bat house would be just as fun to watch
I imagine once everything else is tuned with your product you could make a hot-swappable blade assembly that can be quickly swapped out and later cleaned. Like if the entire guard and blade assembly came off, that would be super convenient.
Would add some weight and complexity but if it’s purpose-built it would probably be less stress on the Drone than constantly pulling props off.
How does this compare in reducing mosquito populations over something braindead like putting some yard waste and water in a bucket for a few days and either adding mosquito dunks or pouring the larvae out?
Or is this more like a stand-in for bug spray/smoke?
Duuuude! Give me this. Please.
We have these mosquito bats/racquets that I've to use every day in a futile attempt to keep my family safe. I need something like what you're building. I looked up even laser mosquito killers.
Surface level thinking, ecological disaster in the making. Birds and bats and other bugs eat mosquitoes to live. Killing all the mosquitoes is like the Chinese killing all the sparrows. We do not understand, and we do not want to understand, the deep consequences of our actions.
People who think we can reengineer and shape ecology by eliminating key species are here on the dunning Kruger curve.
Better option, if you really want to fight malaria go fight that directly, leave mosquitoes out of it.
In general I agree that messing with ecosystems sometimes has unpredictable consequences.
In the case of mosquitos, though, they cause so much suffering, that it would be stupid to not work on eradicating them because of possible negative consequences.
We have to be careful, of course (widespread use of insecticides is a problem), but targeted measures are really unlikely to cause more harm than mosquitos already do.
Yeah well mosquitoes should definitely be made extinct btw but there’s no way a robot that kills bugs in your back yard is going to accomplish that so you can put your pitchfork down
They do in a YouTube video on their channel [0]. It’s 40 (!) watts. They also show it shooting indiscriminately at any small object, with an example where they feed it foam chips.
That's more than enough to permanently blind someone with a partial reflection, i.e. you point this at an insect and there's a small polished-metal object somewhere behind it.
In parts of the world bieng able to eliminate mosquitos(other more deadly bugs) will outweigh a great deal of risk assosiated with lasers.
and there are things that can be done.
heat and motion detectors that disarm the system if people/pets are present
fields of fire that are above 99.999 % of peoples eyes
fields of fire very close to walls, where mosquitos alight, but it is almost impossible to get in the way for humans
multiple laser turrets that indivualy dont have the power to hurt a human badly, but can zap a bug
through co ordinated action.....perhaps set up outdoors with artificial breath and infra red bait traps to bring the mosquitos above a crowd.
more robust systems to be used in agricultural contexts.
this will be about comfort and protecting vulnerable populations, mosquitos/other bugs wont be going anywhere, chemical control has proven to cause ecological probelms worse than the bugs, and the attempts at useing biological methods is only a partial solution.
I’m not here to sell my own startup, but there are other ways to kill mosquitoes than a 40 watts laser that could make someone blind from a secondary reflection (out of the mmWave radar detection range)
I think that by "secondary reflection" you are perhaps refering to a direct single reflection, rather than a double bank?
But in any case it is very very unlikely that there will anything availible outside of a high caliber optics lab that can reflect cohearant laser beams in such a way as to retain a dangerous power level.
The 40 watt laser is needed in order to provide a kill shot in in a small target in millisecond pulse, that only has to penetrate a fraction of a millimeter, and would be unlikely to penetrate a full cm into a human eye and do permanent damage even with a direct hit, not that anyone is going to advocate for useing lasers for eye surgery....oh wait
I may haven't fully understood your answer, but a typical household mirror could reflect 90% of the laser power in a single coherent direction. Any sufficiently polished metal tool would have dangerous specular direction. I'm not sure of the math for a diffuse reflection, but the laser classification is here for a reason.
A human eye being transparent up to the fragile retina, yes, a laser would penetrate the eye and be concentrated in an extremely small spot on the retina. That's exactly the reason why we have safety around lasers, and why everything above 5mw is strictly for enclosed use. 40 watts shot at random in the void is definitely dangerous by all measures.
any light reflected in a domestic situation will no longer be a cohearant laser.if it was very focused UV it could cause temporary blindness, but a milisecond pulse will not contain enough energy to burn @ 40 watts, all that said, it is a given that certifying lasers for full on autonomous bug zapping(a dream of billions), is a very steep regulatory hill to climb, and will not be decided on redit, or here
but as insectides get less effective while also proving to be realy bad for our environment, and the possibility of a true plauge bieng vectored by mosquitos a constant concern, I am absoulutly certain that research into laser bug zappers is going to progress
Light being coherent and light being dangerous are two completely orthogonal concepts. A laser is dangerous because of the very tight beam, but any household mirror keeps that beam focused. Plus, a mosquito needs 100millijoules to fry (from the intellectual ventures study) which is a lot more than what a retina can handle. The short duration actually makes it even worse, because the eye lids can’t close soon enough to avoid the retina burning (they take 100ms to close). That’s the reason why lasers are classed by power.
A retina being easier to burn than a mosquito is the fundamental reason why we haven’t seen that tech deployed. LiDAR detection with a 2D goniometer + high power laser has been available commercially for a while. There just never was someone to create something so deceptive as to sell a 40watts device as possibly safe.
darn!, but thanks as well alex, I get it, the human eye is ever so perfectly built to bring in and focus light, and I was spitballing based on the fact of laser eye surgery, which must be ever so carefully managed. I hate mosquitos and the rest of the blood sucking vermin that I have to deal with.The work I get up to is horribly dangerous sometimes, so my evaluation of risk and failure modes is not exactly common....nor do I expect it to be, but come on, hey!, laser bug zapers, it's right up there with personal raceing quadracopters, hoverboards, lightsabers, and colonys on mars.
I think that people have a reasonable expectation to get wild and crazy stuff, as it is what keeps them paying for all the ever so meticulously engineered stuff that they can care less about.
saftey third.
40W is scary strong for a laser. Almost like a nuke compared to a firecracker[0]:
> 5 milliwatts is wimpy. We can do better.
A 1-watt laser is an extremely dangerous thing. It’s not just powerful enough to blind you—it’s capable of burning skin and setting things on fire. Obviously, they’re not legal for consumer purchase in the US.
Tornyol | AI Control Research Intern | Embedded Systems Intern | ONSITE (Paris) | full-time | 2K€/month | https://tornyol.com
Tornyol is building anti-mosquito drones to fight against malaria. We use smartphone microphones to detect mosquitoes, than a policy learned with reinforcement learning to guide our drones towards mosquitoes. We're in the middle of raising a pre-seed, and are looking for two interns to join us for six months starting in September.
Here are the roles and requirements :
- AI Control Research Intern: code, test and deploy reinforcement learning-based drone control policies and simulation environments. We're looking for a background in either reinforcement learning or classical control.
- Embedded Systems Engineer: Design the physical platform. Responsibilities include everything from CAD to designing PCBs or writing embedded signal processing code.
Perks:
- Small but extremely talented team. The two founders are very technical and will help and guide you in all your missions.
- Lots of responsibilities right from the start. It's a startup.
- Pay is great
If you think you could be a great fit, please email a resume + a few lines on previous personal projects you've built at the email in our website's footer.
I’m interested in how to secure the firmware from reverse-engineering in a product. Is there somewhere an introduction to the techniques used by SpaceX there?
Step 1 is things like encrypted firmware, so I’d suspect SpaceX does nothing or is reactive - they had debug pins until someone published attacks utilizing them.
At a minimum you'd want to encrypt your rootfs using secrets that are hard to extract from secure elements. To go a step further you can employ something like ARM's TrustZone to hide away the sensitive operations (bootloader, decryptions, image signing, etc.)
The fact that they could just dump the filesystem tells me there's no protection employed at SpaceX aside from the boot loader mentioned in the article.
As someone who used a bunch of good products with less than great firmwares I would like you to ask to please consider not doing this, unless you have a strong, real and well-analyzed reason.
Rather, please consider spending your resources wisely, on something that benefits everyone and makes your product better. For power users, a theoretical ability to modify your product (possibly, in a ways you've never even thought about) can be a valuable benefit. So, unless you're certain to be seriously harmed by this in some way, please consider not wasting your (and your users') time on something of questionable value.
Just saying how it looks like from a technical end-user perspective. I'm just really tired and even somewhat depressed of having to hack my devices (lights, cat feeders, now a rowing machine) to make them work properly.
Incredible article, learned quite a lot. To me, a very good supplementary reading would be Structures by J. E. Gordon [1]. Helped me grasp a lot of the mechanical design notions necessary for that sort of work.
A nice mention about this is the outstanding and quiet work of the Cosys-Lab of the University of Antwerp. They once put a microphone array below a scorpio, and showed how bats moved their ultrasonic beam to scan for a scorpio. Incredible stuff [0].
1) and 3) are valid, but 2) isn't really. In that sort of pipeline, you usually do IQ sampling which allows you to phase-shift by any arbitrary value with a complex multiplication.
The main reason is that it's tough to have a uniform sound pressure distribution on a stage. That means the people at the front usually have very high sound levels, while those at the back have way lower. Technicians then make the tradeoff of having too high pressures at the front (where you must have earplugs) to afford to have medium levels at the back.
This is quite sad, I've been very inspired by the writings of Artem Litvinovich [1] (although he stopped publishing 8 years ago). I inspired a lot of my research on what he did.
