Simulation-real world feedback loop for learning robotic control policies

A machine learning system builds and uses computer models for controlling robotic performance of a task. Such computer models may be first trained using feedback on computer simulations of the robot performing the task, and then refined using feedback on real-world trials of the robot performing the...

Full description

Saved in:
Bibliographic Details
Main Authors Yu, Corrinne, Porter, Brandon William, Bachega, Leonardo Ruggiero, Vogelsong, Michael, Beckman, Brian C, Snyder, Benjamin Lev
Format Patent
LanguageEnglish
Published 13.10.2020
Subjects
CHAMBERS PROVIDED WITH MANIPULATION DEVICES
HAND TOOLS
MANIPULATORS
PERFORMING OPERATIONS
PORTABLE POWER-DRIVEN TOOLS
TRANSPORTING
Online AccessGet full text

Cover

More Information
Summary:A machine learning system builds and uses computer models for controlling robotic performance of a task. Such computer models may be first trained using feedback on computer simulations of the robot performing the task, and then refined using feedback on real-world trials of the robot performing the task. Some examples of the computer models can be trained to automatically evaluate robotic task performance and provide the feedback. This feedback can be used by a machine learning system, for example an evolution strategies system or reinforcement learning system, to generate and refine the controller.
Bibliography:Application Number: US201715842737