Patent · US Active

Using simulation and domain adaptation for robotic control

US11341364B2 · kind B2 · utility

2Cited by

0References

20Claims

0Family size

Assignee

Google LLC · US

Inventors

Konstantinos Bousmalis · London, GB
Alexander Irpan · Palo Alto, US
Paul Wohlhart · Sunnyvale, US
Yunfei Bai · Fremont, US
Mrinal Kalakrishnan · Palo Alto, US
Julian Ibarz · Mountain View, US
Sergey Levine · Redmond, US
Kurt Konolige · Menlo Park, US
Vincent O. Vanhoucke · San Francisco, US
Matthew Kelcey · Melbourne, AU

Key dates

Filing date	Sep 20, 2018
Grant date	May 24, 2022
Priority date	—
Expiry date	Apr 11, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/096
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network that is used to control a robotic agent interacting with a real-world environment.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.