Researchers around the world have been working hard to give robots the ability to better sense the environment around them. Before robots can work side by side with humans, they need to be able to sense humans and other objects for safety and to be useful. Researchers at MIT have developed a new robot capable of sensing objects, even if they are hidden from view, using radio waves.
The radio waves used by the robot can pass through walls detecting hidden objects. The robot is called RF-Grasp and combines the powerful new detection technique with traditional computer vision to locate and grab items that may be blocked. The project scientists believe that the move could lead to simplified e-commerce service and deposits or an improved ability to help machines choose specific items, such as a screwdriver in a box full of tools.
The robot can be particularly useful as e-commerce continues to grow. The challenge for robots used to collect items for e-commerce orders today from warehouses around the world is that robots struggle to locate and grab objects in a crowded environment. The researchers say that perception and choice are two major obstacles in the industry today.
By relying only on optical vision, robots are unable to perceive an object packed in a box or hidden behind another object on a shelf. While light waves cannot pass through walls or other objects, radio waves can. MIT’s RF Grasp robot uses a camera and an RF reader to find and grab marked objects, even when blocked from the camera’s view.
The robot is simple and is just a robotic arm attached to a hand that grabs it. The RF reader is independent of the robot and relays the tracking information to the robot’s control algorithm. The researchers say that integrating RF tracking and a visual image of their surroundings was difficult because the robot had to learn to choose which data stream is most important at each moment. The team believes that the robot could one day service busy e-commerce warehouses and remove some of the industry’s limitations.