MIT robot uses radio waves to find and retrieve hidden objects


MIT researchers have developed a robot capable of detecting and grasping objects hidden behind walls or bulky objects.

The system, called RF-Grasp, uses radio waves to locate objects beyond the line of sight of a robot’s cameras. It could help warehouse robots pick up customer orders or tools hidden behind obstacles.

Existing mechanical search systems struggle to accomplish these tasks due to the constraints of their sensors. If an object is hidden, they usually have to explore the environment and search for the object.

Unlike visible light and infrared, RF (radio frequency) signals can pass through cardboard boxes, wooden walls, plastic covers and colored glass to perceive objects equipped with RFID tags.

[Read: How to use AI to better serve your customers]

“The researchers gave the robots a human perception,” said study co-author Fadel Adib. “We are trying to give robots superhuman perception.”

Robotic Perception

RF-Grasp consists of a camera on the robot’s wrist and a separate RF reader. Together they collect tracking data and create a visual map of the environment.

The system first pings the object’s RF tag to identify its location. It then determines the optimal path around the obstacles to reach the object.

As the robot gets closer to the object and begins to manipulate it, computer vision provides more precise directions.

During testing, RF-Grasp successfully identified and moved objects hidden behind packaging and other obstacles. The researchers say the system performed the tasks with about half the movement of similar robots equipped only with a camera.

The system depends on target objects tagged with RFID. But the widespread adoption of these chips as a replacement for barcodes in retail, manufacturing and warehousing means that RF-Grasp could already be having a practical impact.

You can read the study document here.

Greetings Humanoids! Did you know we have an AI newsletter? You can subscribe to it right here.


Comments are closed.