MIT's WiTrack Tracks 3D Motion for Gaming through Walls

• By Dian Schaffhauser
• 12/16/13

A technology in development at MIT allows for precise 3D tracking of people via radio signals, even through walls, enabling devices located elsewhere to be controlled simply with the movement of their bodies. WiTrack, as the research team calls it, can pinpoint a person's location and activities within four to eight inches, making it a promising tool for gamers who want to move outside the immediate boundaries of their game controllers. But it also has other applications, including detecting when a person falls in his or her home and when a user wants to control an appliance with a hand gesture.

WiTrack works by tracking specialized radio signals that reflect off a person's body to determine location and movement. In its prototype form, the system uses four antennas, one for transmitting signals and three for receiving. The setup then creates a geometric model of the user's location by transmitting signals and determining how long it takes for the reflections to transmit back to the receivers in order to estimate the distance between the antennas and the user. Best, of all, the user doesn't have to carry any type of device for the tracking to work.

The findings are described in "3D Tracking via Body Radio Reflections," a paper that will be presented during the Usenix Symposium on Networked Systems Design and Implementation in Seattle in April 2014. The work was completed at MIT Computer Science and Artificial Intelligence Lab (CSAIL).

"Today, if you are playing a game with the Xbox Kinect or Nintendo Wii, you have to stand right in front of your gaming console, which limits the types of games you can play," said Dina Katabi, a professor of computer science and engineering and co-director of the MIT Center for Wireless Networks and Mobile Computing. "Imagine playing an interactive video game that transforms your entire home into a virtual world. The game console tracks you as you run down real hallways away from video game enemies, or as you hide from other players behind couches and walls. This is what WiTrack can bring to video gaming."

Earlier this year, Katabi and graduate student Fadel Adib unveiled WiVi, a system that can detect humans through walls and detect their motion using Wi-Fi signals. But WiTrack has significantly higher accuracy and can track both two-dimensional and three-dimensional movement using wireless signals whose power is 100 times smaller than Wi-Fi.

Besides the gaming application, the researchers have tested fall detection, which can, as an example, assist elderly people. Typically, the solution is to wear a sensor, which is frequently forgotten, or to set up cameras, which don't leave much room for privacy. WiTrack detects falls by looking at the change in elevation and the speed with which the fall happens to determine whether it was intentional or an emergency. In a population of 11 users and 133 experiments, WiTrack distinguished a fall from standing, walking, sitting on a chair, and sitting on the floor with an accuracy of nearly 97 percent.

WiTrack could also be used to control appliances, such as turning a lamp on or off, by pointing at them, the paper explained. "We consider a gesture in which the user lifts her arm, points at an appliance, and drops her arm. By comparing the position of the arm over time, WiTrack can identify the pointing direction."

Now the research team is working on enhancements to WiTrack that will enable it to track the motions of more than one person at a time.