A robotics and computer-vision engineer in Cambridge spent the spring of 2026 building a machine in his living room: a DSLR, a thermal camera, a deep-learning detector, an aluminium gimbal, and a laser aimed at a mosquito in flight. The engineering is real, and the safety camera that cuts the beam near people is the cleverest part. For almost every home, the practical answer is still the simpler one.
On 28 May, a computer-vision and robotics engineer in Cambridge posted a video to X of a machine he had built on his living-room floor. It is the size of a small printer and rides on rollers. Bolted to it are a DSLR with a long zoom lens, a thermal camera, an aluminium gimbal, and a laser. In the video the gimbal swivels, the laser turns on, and a mosquito falls out of the air. A deep-learning model, trained on annotated mosquito images, does the seeing. A second wide-angle camera provides the safety check: the moment a person, a pet, or anything flammable crosses the beam path, it cuts the beam.
Steven Cheng calls it version 2.0 of his home laser system. It is real, it is genuinely clever, and for almost every household it is not the practical answer. The gap between a working prototype and a household tool is the useful part of the story.
What the machine actually does
Set aside the presentation and the build is a three-step chain. The DSLR scans the room and feeds frames to a model trained to recognise the silhouette and gait of a mosquito. When it flags a candidate, the thermal camera confirms a warm body against the background. The gimbal aims, and the laser turns on. Version 2.0, the one Cheng announced on 28 May, added harmonic drives, servo motors, and a reinforced aluminium mount. Those parts make the aim steady enough to hit an insect in flight.
The safety layer is the part most write-ups skip, and it is the most interesting engineering in the whole rig. A wide-angle camera watches the room. A logic gate prevents the laser from turning on whenever its path crosses a person, an animal, or a flammable surface. Cheng is blunt that the system is not for sale and not certified for eye safety. He runs it in his own home, at his own risk, with that camera as his only guarantee.
None of the idea is new. Intellectual Ventures floated a "laser mosquito" concept in the late 2000s. Versions of it have sat on university drawing boards for more than a decade. What Cheng added is not the theory. It is the willingness to build the thing on his carpet and film it running.
Certification is the hard part
Look at the nearest thing to a product. A device called Photonmatrix advertises up to 30 mosquitoes per second inside a 6-metre radius and sells from around $498 on Indiegogo. It also, by the account in the French technology press, cannot be certified for eye safety, the same limit Cheng meets in his living room. That is the quiet lesson of the whole category. The hard part was never getting a laser to hit a mosquito. The hard part is showing that it will never harm a child or a cat.
The results, so far, are a home video. Cheng reports that no mosquitoes remained in his home after a single night. There is no count, no control group, and no independent verification. Even the detection model, the cleverest part, is described in the coverage only as "rather good". No benchmark has been published.
Cheng is one example in a larger field
The reason to read past the video is that Cheng is the amateur version of an effort that is also running in funded labs. Sterile-male releases built on the Wolbachia technique are scaling across Europe and the Americas, with the largest proposed US releases now under EPA review. Italy logged 133 imported dengue cases in early 2026; Valencia's sterile-insect trial has cut local tiger-mosquito numbers. Gene-drive programmes in Tanzania are advancing under African scientific leadership. XPRIZE-style vector-control funding, which rewards cheap hardware and clever software, has paid for everything from acoustic mosquito sensors to AI species-identification apps. In the field, AI already counts and identifies mosquitoes in trap catches faster than any human could.
The pattern is the same everywhere: a sensor, a model, a software loop, wrapped around an old problem. Cheng's laser is simply the most photogenic entry on a long list.
Three things the prototype teaches
The software is no longer the bottleneck. A model that runs in real time can clear a room in a night. It has crossed a practical threshold. The payoff is not lasers. It is surveillance.
A trap count once needed a trained entomologist and a microscope. It can now run on a Raspberry Pi with a camera and a small model. That is the unglamorous plumbing of public health, and it is where this technology genuinely scales.
The hardware is the hard part, and it always will be. Anything that emits a laser in a family home has to be safe. It has to be certified and reliable. That is a multi-year regulatory process, not a weekend project.
The record is poor. The bug zapper did not deliver on its promise. The electric racket can overheat. The plug-in ultrasonic gadget is a placebo. Software has raced ahead, and hardware in this category has not.
Your living room is the wrong unit of measurement. A laser can clear one room. It cannot clear the garden, the courtyard, the park, or the schoolyard. Mosquito control is a numbers problem: a community has to reduce the local Aedes population, not pick off the few that drift indoors. The relevant question is not "what stops the mosquito in front of me" but "what stops the next generation reaching me at all". Cheng's laser answers the first question beautifully. It will never answer the second.
The simple measures keep working
Follow the public-health advice and it lands, every time, in the same unglamorous place. Take away the standing water: tip the saucers under the flowerpots, screen the gutters, empty anything that holds rain. Then put a physical barrier over the two places that matter, where you sleep and where you sit still. This is what French regional health agencies tell residents in the départements marked as "colonised zones" for the tiger mosquito. It runs through Italy's ISS season outlook, the Cyprus "new reality" framing from the ECDC, and the World Health Organization's 2026 insecticide-resistance update. It costs nothing like a £1,500 gimbal, it needs no model, and it works whether or not the next experimental control ever clears a regulator.
That is not a knock on Cheng. His build is exactly what a curious engineer with a thermal camera, a long lens, and a redundant safety chain should do with a spring. The trouble is the framing that follows it around. Coverage that calls a living-room laser "the future of mosquito control" quietly undersells the cheap, proven habits that already protect almost everyone.
What to watch next
Three signals will tell you where this goes. The first is a published benchmark: a confusion matrix on a public dataset would turn "rather good" into something the field can trust. The second is regulation: whether any national safety body certifies a Photonmatrix-style laser, the line between a hobbyist toy and a real product class. The third is the deployment numbers on the methods that already work at scale. These include Wolbachia in Singapore, sterile-male releases in Valencia, gene drives in Tanzania, and the Italian arbovirus season. None of them come with an AI-gimbal video, and all of them are reducing cases.
A laser that clears a living room is a remarkable piece of work. A window screen that keeps the tiger mosquito out in the first place is cheaper, safer, and, framed right, not much less impressive.
What we know
Sources cited
- Futura-Sciences, report on a home-built laser system for catching tiger mosquitoes (Patrick Ruiz, 2 June 2026). https://www.futura-sciences.com/tech/actualites/technologie-moustiques-tigres-cet-ingenieur-invente-arme-radicale-canon-laser-pilote-ia-134959/
- Numerama, coverage of the same home-built laser system and its safety chain. https://www.numerama.com/tech/2264839-il-fabrique-un-canon-laser-pilote-par-lia-pour-carboniser-les-moustiques-de-son-salon.html
- Les Numériques, report on the prototype and the Photonmatrix comparator (Patrick Ruiz, 2 June 2026, 12:36). https://www.lesnumeriques.com/societe-numerique/un-ingenieur-cree-le-tueur-de-moustiques-ultime-a-base-de-laser-et-d-ia-n256912.html
- Developpez.com, cross-check on the engineering of the build. https://intelligence-artificielle.developpez.com/actu/383750/Un-ingenieur-met-au-point-un-systeme-de-defense-laser-a-base-d-IA-pour-eliminer-tous-les-moustiques-d-un-domicile-IA-ingredient-incontournable-pour-deboucher-sur-le-tueur-de-moustiques-ultime/
This article is general information, not medical advice. Ask a doctor or pharmacist about your own health.