Machine learning with laser and no more cockroaches

Ildar Rakhmatulin, a research associate at Heriot-Watt is into machine learning. In a study – conducted last year but published in Oriental Insects on last week – Rakhmatulin and colleagues used a laser insect control device automated with machine vision to perform a series of experiments on cockroaches.

cockroaches

So they managed not only to detect the cockroaches with high accuracy, but also to keep them at a distance of 1,2 meters.

"I started using a Jetson Nano that allowed me to use deep learning technologies more accurately to detect an object," says Rakhmatulin. Jetson Nano is a small s that can run machine learning algorithms. THE ς επεξεργάζεται ένα ψηφιακό from two cameras to determine the location of the cockroach.

It transmits this information to a galvanometer (a machine that measures electric current), which changes the direction of the laser to "shoot" the target. According to the publication, Rakhmatulin tested the above at different power levels for the laser.

toin a 2121777 f0001 oc

At a lower power level, he found that he could influence the behavior of cockroaches. So they could possibly be trained not to take refuge in a certain dark area. At a higher potency level, the cockroaches were effectively "neutralized", in other words, killed.

“I use very cheap material and cheap and everything is open source," Rakhmatulin said. "All sources are rising on my GitHub and you can use them. If it can harm cockroaches, it can also harm other pests in agriculture.”

However, it is not ready for home use. "It's not recommended because it's a bit dangerous," Rakhmatulin said. "Lasers can not only harm cockroaches but also your eyes."

See one of the device in action

https://www.youtube.com/watch?v=VwZunUqHbiU

iGuRu.gr The Best Technology Site in Greecefgns

every publication, directly to your inbox

Join the 2.100 registrants.

Written by giorgos

George still wonders what he's doing here ...

Leave a reply

Your email address is not published. Required fields are mentioned with *

Your message will not be published if:
1. Contains insulting, defamatory, racist, offensive or inappropriate comments.
2. Causes harm to minors.
3. It interferes with the privacy and individual and social rights of other users.
4. Advertises products or services or websites.
5. Contains personal information (address, phone, etc.).