Objects give off different electro-magnetic signals depending on their operations and composition. Using the human body as an antenna, the EM-Sense watch filters these signals to determine what objects the user is in contact with. Software can distinguish between a host of different everyday items, from drills and door handles, to computer screens and toothbrushes. The work is published at Disney Research.
“Our approach exploits unintentional EM noise emitted by many everyday electrical and electromechanical objects, such as kitchen appliances, computing devices, power tools and automobiles,” the study’s abstract states.
“These signals tend to be highly characteristic, owing to unique internal operations (e.g., brushless motors, capacitive touchscreens) and different enclosure designs, material composition and shielding. When a user makes physical contact with these objects, electrical signals propagate through the user’s body, as it is conductive. By modifying a commodity software-defined radio receiver, we can detect and classify these signals in real time, enabling robust, on-touch object detection.”
This ability to quantify the surrounding environment through touch alone has a range of practical applications. Calendar reminders could be activated by touching different objects, such as the handle of a door at home or in an office. Navigation information could be delivered when car keys are picked up, or instructions and diagrams provided when using power tools.
Because the EM-Sense prototype uses an off-the-shelf software-defined radio, the technology could potentially be incorporated into smartwatches and other products in the near future.