The team at the Massachusetts Institute of Technology (MIT) Computer Science and Artificial Intelligence Laboratory (CSAIL), developed an advanced system which allows robots inspect random objects and understand them. The robot after briefly inspecting the object will be ready to accomplish specific tasks.
We all had a dream wherein robots take instructions from man and complete each and every task as we order them. Surprisingly this might become true, the MIT developed robot is capable of moving objects from place to place which can be used for cleaning our house.
Wonder How the System is Capable of Recognizing Objects it has never seen before??
The system, dubbed Dense Object Nets(DON inshort), looks at objects as collections of points that serve as visual roadmaps of sorts. This helps the robots understand better and manipulate items and allows them to even pick up a specific object among a clutter of similar objects.
Lucas Manuelli, a student at CSAIL said "Many approaches to manipulation can't identify specific parts of an object across the many orientations that object may encounter," He added saying "For example, existing algorithms would be unable to grasp a mug by its handle, especially if the mug could be in multiple orientations, like upright, or on its side,"
How is DON's algorithm different from the previous algorithms?
The DON algorithm creates a series of coordinates on a given object, these coordinates serve as a kind visual roadmap of the object, which gives the robot a better chance of recognizing it and what it needs to grasp. This whole process is automated and no need of any human interaction or annotations.
A set of tests were done on a soft caterpillar toy, a kuka robotic arm powered by DON could grasp the toy's right ear from a range of different configurations. This study shows that the system has the ability to distinguish left from right on symmetrical objects.
These systems can replace the regular factory robots which are less efficient, Manuelli said. "But a system like this that can understand objects' orientations could just take a picture and be able to grasp and adjust the object accordingly."
Comment your Questions and Reviews Below..!!!
0 comments:
Post a Comment