Locust Married to AI Device Births Monstrous Smelling Bot

Scientists from Tel Aviv University have created a monster, but it might be a useful monster: a very sensitive odor-identification device built of electronics, artificial intelligence, and the antenna of the humble locust.

The device incorporates a biological sensor – i.e., an actual locust antenna – with an electronic system that can receive and decode the sensor’s electrical signals. The monstrosity on wheels (literal wheels), uses a machine-learning algorithm to identify odors, and it does it with much greater precision than contemporary detection devices.

“We used machine learning to create a ‘library’ of smells,” explains Professor Yossi Yovel on the university’s website. At first the library consisted of eight odors, such as geranium, lemon, marzipan. Later this “simple electro-antennogram technology” learned to identify additional smells, such as various types of Scotch.

The sensitivity of the insect’s nose is about 10,000 times higher than the devices that are in use today.

“Nature is much more advanced than we are, so we should take advantage of that,” says co-researcher Ben Maoz. “The creation of a robot with a biological nose could help us preserve human life and identify criminals in a way that is not possible today.… The sky is the limit.”

The thing looks like a hi-tech toy car, which makes sense since the next step will be to give the smell-bot navigation capability. The technology will probably find application at airports, public buildings, and anywhere else the state wishes to stick its nose in for a sniff.

The breakthrough research is published in the journal Biosensor and Bioelectronics. A brief explainer can be viewed here.

Photo credit: Tel Aviv University