Magazino, a German firm, has built advanced mobile robots called Toru, which are intelligent and perceptually controlled for internal logistics of warehouses.
The technology used in the robots help identify individual objects on shelves and localize them for references. Frederik Brantner said that Toru robots are particularly advantageous for orders that involve several items.
In case of a four-item order, Toru can perform better than the Amazon warehouse robots. Toru can go to each of the four shelves one after the other and deliver them all to the shipping station in one trip. And there are no shelves to return.
The team created a 3D model of each warehouse where the robots will operate and allowed Toru to build a 2D map of its own using two laser sensors. By measuring the time taken for the laser light to return to the sensor as it bounces off things in its path, Toru could identify walls, columns of shelves, and human legs.
This data will also be shared with other Toru robots working in the same warehouse so that the network information is well known among the bots.
After reaching a particular shelf, the robot surveyed for the desired item using lasers and cameras to determine the item’s orientation on the shelf. This data will help determine how the gripper should grasp the object. The item is then stored in the robot’s internal shelving while it drives around the warehouse to complete the order.
Magazino basically manufactures three types of Torus depending on the kind of item to be handled. Toru Cube is for gripping single rectangular objects, Toru Box is for standardized containers, boxes, or trays and Toru Flex can be used to pick up irregular shapes, such as an individual teddy bear from a box of bears.
Magazino believes that the robots are best suited for warehouses where employees pick individual orders, which is often the case for e-commerce warehouses. So far five Toru robots have been sold which includes one for Sigloch, a book distributor at Germany.
Speaking about the performance of Toru, Willy Shih, professor at Harvard Business School who specializes in technology and operations management said, “It’s using more sensing and analysis technology in terms of sizing the object and figuring out how to pick it up. I think it will be saving a lot of energy because it doesn’t have to move all that weight around.”
Image credits: Magazino, Video credits: MIT Technology Review