Alphabet Inc (NASDAQ:GOOGL)’s Machine Learning Is Teaching Robots How To Grasp Different …

Alphabet Inc (NASDAQ:GOOGL) is using its machine learning to train 14 dedicated robots to grasp household objects by mimicking the feedback processes of human’s hand-eye coordination. The standard way of doing this would be for the robot to survey the environment, device a plan of how to grasp the object and the execute it but according to Google scientist Sergey Levine this method always fails when real world mess confronts the robot. Hand-eye coordination is particular paramount to humans since it helps us make tiny adjustments to do things like washing dishes or serving tennis. Google is training the robots by a deep convolutional neural network (CNN) to enable them to predict the outcome of their grasp based on the camera input and motor commands. This is robot’s hand-eye coordination.…


Link to Full Article: Alphabet Inc (NASDAQ:GOOGL)’s Machine Learning Is Teaching Robots How To Grasp Different …

Pin It on Pinterest

Share This

Join Our Newsletter

Sign up to our mailing list to receive the latest news and updates about homeAI.info and the Informed.AI Network of AI related websites which includes Events.AI, Neurons.AI, Awards.AI, and Vocation.AI

You have Successfully Subscribed!