Sniffer algorithm leads robots to faint, faraway scents
Although having the boys in blue tracking you down based on your unique aroma fingerprints might seem frightening, just envision the terror that would ensue if an ultra-keen robot was onto your trail from miles away. Massimo Vergassola and and colleagues at the Pasteur Institute in Paris, France, have created an algorithm that can actually instruct a robot "how to move in order to gather as much olfactory information as possible." The mathematical formula allows a machine to home in on "even the faintest of scents" by analyzing which direction the smell is getting weaker or stronger in, the frequency of the whiffs, and eventually, it could even take into account disturbances such as wind gusts. After trialing the algorithm on computer-based robotic models searching for a scent, he found that the theoretical guinea pigs moved in "S-like patterns" to sniff things out, which is quite similar to the method used by moths (renowned for their sense of smell) when trying to discover the source of an odor. Researchers state that implementing the technique into an actual robot would be fairly "straightforward," and could also be used for other tasks that involve "searching with limited information" -- or alternatively, on bots who are already trained to chase down foes.
All products recommended by Engadget are selected by our editorial team, independent of our parent company. Some of our stories include affiliate links. If you buy something through one of these links, we may earn an affiliate commission.