Electromagnetic interference is everywhere, coming from appliances and electrical systems.
Now a team from Microsoft Research wants to harness this unorganized ambient noise as an affordable way to control everything from the TV channel to room temperature. Their experiments demonstrate that human interaction with the noise is actually predictable.
"Our goal is to get you the benefits of a large interaction surface everywhere in your house without making you tear out all the drywall and replace it with millions of dollars in sensitive touch screens," said Dan Morris, a researcher with Microsoft Research.
He worked on the proof of concept with Desney Tan, senior researcher at Microsoft Research, and Shwetak Patel, University of Washington assistant professor of computer science and engineering.
The researchers set up controlled experiments in 10 homes representing different construction types.
In the setup, a participant wore a backpack containing a laptop and a data acquisition device connected through a wire to a conductive pad on the back of the participant's neck. The pad measured the voltages picked up by participants, who performed specific gestures around light switches. Software in the laptop generated positioning instructions and at each switch, the gesture order was randomized to eliminate bias.
The experiments showed that electromagnetic noise is so predictable that it can be used it to figure out where a person is standing, what the person is doing, and even where a hand is placed on a wall. The team used a simple sensor that was essentially just a piece of metal, but Morris said that ultimately a sensor could be placed in the user's hand or anywhere else that the radio signals being picked up by the body can be gathered.
"Our bodies, it turns out, are actually really good and relatively colorful antennas," Morris said. The team presented their results earlier this week in Vancouver at the ACM CHI Conference on Human Factors in Computing Systems.
The researchers learned that in a typical house, the electromagnetic noise changes noticeably from room to room because of the various appliances in them. Then they applied artificial intelligence to the data.
"The noise is different enough in those different environments that the computer can actually use machine learning to tell the difference," Morris said.
This predictability could allow users to control home lighting, stereo volume and the temperature just by touching the walls in a certain way. Morris said light switching functionality could be moved lower down on a wall, making it accessible to young children.
"Home automation feels natural to do since the input surface is the house itself," he said. "Instead of going to find a remote control, I might just tap two times on the wall to change the channel."
Morris regards their work as a successful proof of concept. "We've demonstrated all the fundamental principles, and demonstrated the techniques required to do it," he said.
The next step will be building a working interactive system. Currently the team is researching the engineering challenges that arise when a user moves around in a less controlled environment than the ones in their experiments.
Matt Reynolds is an assistant professor in electrical and computer engineering at Duke University who studies harnessing energy from environmental signals to power radio frequency identification tags.
One future challenge for the researchers, he said, will be training such an interactive electromagnetic field system to work consistently in many different types of buildings. However, he pointed out that the team has demonstrated the potential for interactivity without the need for special signal generation.
"In the academic literature it's called a signal of opportunity," Reynolds said. "These electromagnetic fields are everywhere in a home environment and in an office. Showing that they can be used for sensing is very exciting."