MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) has created a new system called Chronos that can accurately detect the position of a person or object inside a room within tens of centimeters, using WiFi signals only.
Chronos works without the aid of any secondary sensors, only using a technology called time-of-flight calculation, which measures the time it takes data to travel from the WiFi access point to the user's device.
According to MIT, this new system is 20 times more accurate than the current WiFi-based tracking systems. Researchers say that Chronos was 94 percent successful in detecting which room a person is currently in, and 97 percent successful in determining if a shop's customer was inside or outside the store.
Researchers say that coffee shops and stores can benefit from something like Chronos because it will allow them to use passwordless WiFi connections for their clients, preventing nearby users from loitering on their WiFi.
Additionally, since Chronos can locate persons within tens of centimeters, researchers say that they could be mounted on drones and allow them to survey indoor locations while also keeping away from room occupants.
With Chronos you need only one access point. Previous WiFi tracking systems needed at least four, which would work together three at a time, in various combinations, performing triangulation operations to detect a person's position in the room.
MIT researches say that by multiplying the time-in-flight value they receive from each user with the speed of light, they were able to detect each user's distance to the central WiFi access point.
Because the WiFi device can work at various frequencies, Chronos will often switch frequencies to double-check calculated values.
Scientists also said that they've removed background data coming from WiFi signals reflected from nearby objects, along with other smaller nuisance factors.
You can check a video below of Chronos in action, you can read the entire research paper, or view the researchers' presentation from USENIX Symposium on Networked Systems Design and Implementation (NSDI '16).
