公开(公告)号：US20190385022A1

公开(公告)日：2019-12-19

申请号：US16443765

申请日：2019-06-17

Applicant: Google LLC

Inventor： Eric Victor Jang ,  Sergey Vladimir Levine ,  Coline Manon Devin

IPC: G06K9/62 ,  G06N3/08 ,  G06K9/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an object representation neural network. One of the methods includes obtaining training sets of images, each training set comprising: (i) a before image of a before scene of the environment, (ii) an after image of an after scene of the environment after the robot has removed a particular object, and (iii) an object image of the particular object, and training the object representation neural network on the batch of training data, comprising determining an update to the object representation parameters that encourages the vector embedding of the particular object in each training set to be closer to a difference between (i) the vector embedding of the after scene in the training set and (ii) the vector embedding of the before scene in the training set.