MIT Associate Professor Fadel Adib’s group is trying to give robots superhuman perception and have developed a robot that uses radio waves to sense hidden objects. Named RF-Grasp, the robot features powerful sensing and traditional computer vision to locate and grasp items that might otherwise be blocked from view.
MIT researchers developed a picking robot that finds and grasps objects, even if they’re hidden from view.
Perception and picking are two roadblocks for robots. With optical vision alone, robots can’t perceive the presence of an item packed away in a box or hidden behind another object on the shelf as visible light waves, of course, don’t pass through walls. However, radio waves do.
RFID systems are based on a reader and a tag, which can be adapted to this application. The reflected signal provides information about the location and identity of the tagged item. Since Japan is planning to use RF tracking for nearly all retail purchases in a matter of years, the profusion of RF could be a boon for robots, providing another mode of perception.
RF Grasp consists of a robotic arm attached to a grasping hand. A camera sits on the robot’s wrist. The RF reader stands independent of the robot and relays tracking information to the robot’s control algorithm. The robot constantly collects RF tracking data and a visual picture of its surroundings.
The robot initiates the seek-and-pluck process by pinging the target object’s RF tag for a sense of its whereabouts and uses RF to focus the attention of vision. Vision is then used to navigate fine maneuvers. Efficiency during testing has already been proved. RF Grasp displayed the unique ability to “declutter” its environment, removing obstacles in its way in order to access the target. RF Grasp could one day perform fulfillment in packed e-commerce warehouses.
The research will be presented in May at the IEEE International Conference on Robotics and Automation.
Original Release: Eureka Alert