Patent · US Active

Reinforcement learning for contact-rich tasks in automation systems

US12304072B2 · kind B2 · utility

0Cited by

1References

8Claims

0Family size

Assignees

Siemens Aktiengesellschaft · DE
The Regents of the University of California · US

Inventors

Eugen Solowjow · Berkeley, US
Juan L. Aparicio Ojea · Doylestown, US
Chengtao Wen · Redwood City, US
Jianlan Luo · Mountain View, US

Key dates

Filing date	Sep 13, 2018
Grant date	May 20, 2025
Priority date	—
Expiry date	Dec 4, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG05B2219/50391
WIPO fieldHandling
WIPO sectorMechanical engineering

Abstract

Systems and methods for controlling robots including industrial robots. A method includes executing (402) a program (550) to control a robot (102) by the robot control system (120, 500). The method includes receiving (404) robot state information (554). The method includes receiving (406) force torque feedback (556) inputs from a sensor (554) on the robot (102). The method includes producing (410) a robot control command for the robot (102) based on the robot state information (554) and the force torque feedback (556) inputs. The method includes controlling (412) the robot (102) using the robot control command.

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