The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Sep. 07, 2021

Filed:

Sep. 13, 2019
Applicant:

Toyota Research Institute, Inc., Los Altos, CA (US);

Inventors:

Kevin Stone, Menlo Park, CA (US);

Krishna Shankar, Los Altos, CA (US);

Michael Laskey, San Jose, CA (US);

Assignee:

TOYOTA RESEARCH INSTITUTE, INC., Los Altos, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06T 7/73 (2017.01); G06K 9/62 (2006.01); B25J 9/16 (2006.01); G06K 9/00 (2006.01); G06T 7/55 (2017.01); G06N 3/08 (2006.01); G06T 19/20 (2011.01);
U.S. Cl.
CPC ...
G06K 9/00664 (2013.01); B25J 9/1605 (2013.01); B25J 9/1661 (2013.01); B25J 9/1664 (2013.01); B25J 9/1671 (2013.01); B25J 9/1697 (2013.01); G06K 9/6202 (2013.01); G06K 9/6255 (2013.01); G06K 9/6256 (2013.01); G06N 3/08 (2013.01); G06T 7/55 (2017.01); G06T 7/74 (2017.01); G06T 19/20 (2013.01); B25J 9/163 (2013.01); G06T 2200/04 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/20104 (2013.01);
Abstract

A method for training a deep neural network of a robotic device is described. The method includes constructing a 3D model using images captured via a 3D camera of the robotic device in a training environment. The method also includes generating pairs of 3D images from the 3D model by artificially adjusting parameters of the training environment to form manipulated images using the deep neural network. The method further includes processing the pairs of 3D images to form a reference image including embedded descriptors of common objects between the pairs of 3D images. The method also includes using the reference image from training of the neural network to determine correlations to identify detected objects in future images.


Find Patent Forward Citations

Loading…