Robots Can Stop To Smell The Roses Now, Thanks To AI And A Biological Sensor

Researchers at the University of Tel Aviv have developed a robot that can "smell" using an innovative biological sensor. The sensor transfers electrical information in response to the presence of an odor, which the robot is capable of detecting and interpreting. However, the technology is still lags far behind what of millions of years of evolution has enabled.

The breakthrough out of the University of Tel Aviv has researchers hopeful that the new technology could be used in the future to identify explosives, drugs, diseases, and more. This is due to the fact that they were able to identify odors with a level of sensitivity 10,000 times higher than that of a commonly used electronic device that's employed today.

"An example of this can be found at the airport where we go through a magnetometer that costs millions of dollars and can detect if we are carrying any metal devices. But when they want to check if a passenger is smuggling drugs, they bring in a dog to sniff him," stated Dr. Ben Maoz of the Fleishman Faculty of Engineering and the Sagol School of Neuroscience.

Researchers provided the example of a mosquito, which can detect "a 0.01 percent difference in the level of carbon dioxide in the air." Professor Amir Ayali of the School of Zoology and the Sagol Neuroscience added, "Today, we are far from producing sensors whose capabilities come close to those of insects."

Humans and other animals use their eyes, ears, and noses as receptors that can identify and distinguish between different incoming signals. The sensory organ then translates those signals into electrical impulses, which the brain then decodes. Here lies the dilemma of trying to connect a biosensor to an electronic system that can decode the electrical signals from the receptors.

Professor Yossi Yovel of the School of Zoology and the Sagol School of Neuroscience explained, "We connected the biological sensor and let it smell different odors while we measured the electrical activity that each odor induced. The system allowed us to detect each odor at the level of the insect's primary sensory organ. Then, in the second step, we used machine learning to create a 'library' of smells."

During the study, researchers were able to characterize 8 odors, such as lemon and marzipan. Once the experiment was over, they continued to identify additional unusual smells, such as various types of Scotch whiskey.
 
"In this work, we created a bio-hybrid odor discriminator utilizing the desert locust’s primary olfactory apparatus – its antennae, together with simple electroantennogram technology and artificial intelligence tools for signal analysis," according to Dr Maoz.

While nature is still far more advanced than any biosensor to date, the principle the researchers demonstrated could still be applied to other senses, such as sight and touch.

Dr. Maoz concluded, "For example, some animals have amazing abilities to detect explosives or drugs; 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. Some animals know how to detect diseases. Others can sense earthquakes. The sky is the limit."