A robot that finds lost items

A busy commuter is prompt to walk out the door only to substantiate theyve misplaced their keys and must search through piles of stuff to find them. Rapidly sifting through clutter they wish they could aspect out which pile was hiding the keys.

Researchers at MIT have created a robotic method that can do just that. The method RFusion is a robotic arm with a camera and radio frequency (RF) antenna attached to its gripper. It fuses signals from the antenna with visual input from the camera to place and recover an item even if the item is buried below a pile and fully out of view.

The RFusion prototype the investigationers developed relies on RFID tags which are common battery-less tags that can be stuck to an item and return signals sent by an antenna. Because RF signals can journey through most surfaces (like the mound of dirty laundry that may be obscuring the keys) RFusion is able to place a tagged item within a pile.

Using machine learning the robotic arm automatically zeroes-in on the objects exact location moves the items on top of it grasps the object and verifies that it picked up the right thing. The camera antenna robotic arm and AI are fully integrated so RFusion can work in any environment without requiring a particular set up.

While finding lost keys is helpful RFusion could have many broader applications in the forthcoming like sorting through piles to fulfill orders in a warehouse identifying and installing components in an auto manufacturing set or helping an elderly personal accomplish daily tasks in the home though the running prototype isnt perfectly fast sufficient yet for these uses.

’This idea of being able to find items in a chaotic globe is an open problem that weve been working on for a few years. Having robots that are able to search for things below a pile is a growing need in activity today. Right now you can ponder of this as a Roomba on steroids but in the near term this could have a lot of applications in manufacturing and warehouse environments’ said senior creator Fadel Adib companion professor in the Department of Electrical Engineering and Computer Science and ruler of the Signal Kinetics cluster in the MIT Media Lab.

Co-creators include investigation helper Tara Boroushaki the lead creator; electrical engineering and computer science graduate student Isaac Perper; investigation companion Mergen Nachin; and Alberto Rodriguez the Class of 1957 Associate Professor in the Department of Mechanical Engineering. The investigation will be presented at the Association for Computing Machinery Conference on Embedded Networked Senor Systems next month.