IP Library Granted Patent US 12,304,072
Granted Patent B2
US 12,304,072 · App. 16/970,450 · Granted May 20, 2025

Reinforcement learning for contact-rich tasks in automation systems

Inventors: Eugen Solowjow (Berkeley, CA); Juan L. Aparicio Ojea (Moraga, CA); Chengtao Wen (Redwood City, CA); Jianlan Luo (Berkeley, CA)
Assignees: Siemens Aktiengesellschaft; The Regents of the University of California
B25J9/163B25J9/1633G05B2219/32335G05B2219/41387G05B2219/50391
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,304,072
App. No.
16/970,450
Granted
May 20, 2025
Kind
B2
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.

Claims (15)

1. A process performed by a robot control system, comprising:

executing a program to control a robot by the robot control system;

receiving robot state information by the robot control system;

receiving force torque feedback inputs from a sensor on the robot by the robot control system;

producing a robot control command for the robot using a guided policy search process, by the robot control system, based on the robot state information and the force torque feedback inputs and on a reference signal of a neural network, wherein the reference signal is based on the robot state information and the force torque feedback inputs, the force torque feedback inputs being added to a next-to-last layer of the neural network at force torque information nodes; and

controlling the robot using the robot control command, by the robot control system.

2. The process of claim 1 , further comprising filtering the force-torque feedback inputs using a low-pass filter.

3. The process of claim 1 , wherein an admittance controller is used to process the robot state information and the force torque feedback inputs.

4. The process of claim 1 , wherein producing the robot control command is performed using a mirror descent guided policy search process.

5. The process of claim 1 , wherein the sensor is a force/torque sensor mounted on a wrist of an arm of the robot.

6. The process of claim 1 , wherein the robot control system is a reinforcement learning control system.

7. A robot control system comprising:

a memory; and

a processor in communication with the memory, wherein processor is configured to perform a process as in claim 1 .

8. A non-transitory computer-readable medium storing executable instructions that, when executed, cause robot control system to perform a process as claim 1 .

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 9, 2020
From: SIEMENS CORPORATION
To: SIEMENS AKTIENGESELLSCHAFT
Reel/Frame 054014/0572 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 18, 2020
From: LUO, JIANLAN
To: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
Reel/Frame 053526/0934 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 17, 2020
From: SOLOWJOW, EUGEN; APARICIO OJEA, JUAN L.; WEN, CHENGTAO
To: SIEMENS CORPORATION
Reel/Frame 053510/0967 →
Continuity (3)
Provisional Application 62635757 · Feb 27, 2018
Provisional Application 62635771 · Feb 27, 2018
Related Publication 20210107142A1 · Apr 15, 2021
References Cited (10)
US 11188821B1 · Kalakrishnan · 2021 [cited by examiner]
US 20120283875A1 · Klumpp · 2012 [cited by examiner]
US 20170106542A1 · Wolf et al. · 2017 [cited by applicant]
US 20190184564A1 · Muraoka · 2019 [cited by examiner]
US 20200030970A1 · Mariyama · 2020 [cited by examiner]
US 20200129265A1 · Matsuda · 2020 [cited by examiner]
WO 20090020600A1 · 2009 [cited by applicant]
WO 20160010968A1 · 2016 [cited by applicant]
Tadanobu, Inoue et al: “Deep reinforcement learning for high precision assembly tasks”; 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE; Sep. 24, 2017 (Sep. 24, 2017), pp. 819-825, … [cited by applicant]
International Search Report mailed Feb. 11, 2019; International Application No. PCT/US2018/050862; 13 pages. [cited by applicant]