Researchers from the Massachusetts Institute of Technology (MIT) have developed a system for robots called Dense Object Nets (DON), which interacts with objects of an unfamiliar form. It virtually decomposes the object into its constituent parts, remembers its characteristics and the way it interacts with it. When the algorithm encounters a new object, it tries to understand whether its parts are similar to those seen previously.
The system examines the object at different angles using cameras on the manipulator, then recognizes the images and determines the coordinates of all points of the object. On average, the analysis takes about 20 minutes.
During the training, the researchers showed the DON sneakers and taught the system to raise it in a certain way. When the algorithm first saw another shoe in different angles, it realized that it had a similar object in front of it, and raised it in the same way.
Another example is a mug with a liquid. Unlike most similar systems, DON can lift it by the handle, even if it stands upright or upside down.
Founders of DON hope that their technology will find use in warehouses of such large retailers as Amazon and Walmart. In addition, robots can work as house helper.