Engineers at the Massachusetts Institute of Technology (MIT) have developed a new RF-Grasp robot. It uses radio waves that can pass through walls to detect closed objects.
In recent years, robots have gained artificial vision, touch and even smell. “Researchers give robots a human perception,” says MIT associate professor Fadel Adib. In a new article, Adib’s team pushes the technology even further – “We’re trying to give robots a superhuman experience.”
Researchers have developed a robot that uses radio waves. Their peculiarity is that they pass through walls to detect hidden objects. The RF-Grasp robot combines powerful sensing with more traditional computer vision to detect and capture objects that might otherwise be blocked from view. Progress may one day simplify e-commerce in warehouses.
The study will be presented in May at the IEEE International Conference on Robotics and Automation. The lead author of the article is Tara Borushaki, Research Fellow at the Signal Kinetics Group at the MIT Media Lab.
The e-commerce industry continues to grow, but warehouse operations are still usually the domain of humans rather than robots, despite sometimes hazardous working conditions. This is partly due to the fact that it is difficult for robots to find and grab objects in such a crowded environment. Perception and choice are two barriers in the industry today, scientists explain. Using only optical vision, robots cannot detect the presence of an item packed in a box or hidden behind another item on a shelf. The point is that visible light waves do not pass through walls.
When creating the robot, radio frequency (RF) identification systems were used. This is a method for automatically identifying objects in which data stored in so-called transponders, or RFID tags, is read or written by means of radio signals.
Any RFID system consists of a reader (reader, reader or interrogator) and a transponder (aka RFID tag, sometimes the term RFID tag is also used).
RF-Grasp uses a camera and RF reader to find and capture marked objects, even if they are completely obscured by the camera. The camera is located on the wrist of a robotic arm attached to the body. At the same time, the RF-reader does not depend on the robot and transmits information to the control algorithm. In this way, it constantly collects both RF tracking data and a visual picture of its surroundings.
The detailed design of the robot is described in a press release from the Massachusetts Institute of Technology.