Researchers at MIT have developed a robotic arm called RFusion that can find lost things. The system consists of a camera and a radio frequency antenna attached to its gripper. It combines signals from the antenna with visual information from the camera to identify and recover an object, even if it is buried behind a pile or out of sight. The developed RFusion prototype is based on inexpensive RFID tags battery-free tags that may be attached to an object and reflect signals sent by an antenna. Because RF signals can pass through most surfaces, RFusion can find a tagged object inside a pile.

Machine learning helps the robotic arm to automatically focus on the exact location of the object, move the objects on top of it, grasp the object, and confirm that it has picked up the proper thing. Because the camera, antenna, robotic arm, and AI are all fully integrated, RFusion can function in any environment without any specific setup. RFusion has the potential to have many broader applications in the future, such as sorting through piles to fulfill orders in a warehouse, identifying and installing components in an auto manufacturing plant, or assisting an elderly individual with daily tasks in the home, though the current prototype isn’t quite fast enough for these uses yet.