IP Library › Granted Patent US 12,648,823
Granted Patent B2
US 12,648,823 · App. 18/708,608 · Granted Jun 9, 2026

Control system, control device, and actuator

Inventors: Shunsuke Yajima (Tokyo, JP); Jun Arai (Tokyo, JP)
Assignee: Sony Group Corporation
A61B34/30B25J9/102B25J9/126A61B2034/301A61B2034/305
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 12,648,823
App. No.
18/708,608
Granted
Jun 9, 2026
Kind
B2
Abstract

A control system of an aspect according to the present disclosure includes a robot including an actuator, and an estimation section that estimates external force received by the robot on the basis of state information of the robot, in which the actuator includes an encoder on an output shaft side, a speed reducer that has backdrivability, that is coupled to the encoder on the output shaft side, and that is a load element, a motor coupled to the speed reducer, and an encoder on an input shaft side which encoder is coupled to the motor.

Claims (57)

1 . A control system comprising:

a robot having an actuator; and

processing circuitry configured to

estimate external force received by the robot by subtracting a disturbance estimation value of when it is assumed that the robot is in an unloaded state from a disturbance estimation value of when the robot is in a loaded state,

acquire the disturbance estimation value of when it is assumed that the robot is in the unloaded state,

output, by a learned model, when state information of the robot is input, the disturbance estimation value of when it is assumed that the robot is in the unloaded state,

wherein the learned model is a model acquired by an input of time-series information of an acceleration reference value of an input shaft and an angle and an angular velocity of the input shaft and an output shaft to a neural network,

wherein the actuator includes,

an encoder on an output shaft side,

a speed reducer coupled to the encoder on the output shaft side and having backdrivability,

a motor coupled to the speed reducer, and

an encoder on an input shaft side which encoder is coupled to the motor.

2 . The control system according to claim 1 , wherein

the disturbance estimation value of when the robot is in the loaded state is a disturbance estimation value of a disturbance observer.

3 . The control system according to claim 1 , wherein

the learned model includes a long short-term memory (LSTM) block, and

the state information of the robot is time-series information.

4 . The control system according to claim 1 , wherein the processing circuitry is further configured to

estimate external force received by a joint section or a distal end of the robot.

5 . The control system according to claim 4 , wherein

the robot includes an arm.

6 . The control system according to claim 1 , wherein

the robot includes a joint section having the actuator,

the state information of the robot includes a torque reference value, an angle, and an angular velocity of the joint section, and

the processing circuitry is further configured to estimate external force received by the joint section.

7 . The control system according to claim 1 , wherein

the robot includes a distal end having the actuator,

the state information of the robot includes an acceleration reference value, a position, and a speed of the distal end, and

the processing circuitry is further configured to estimate external force received by the distal end.

8 . The control system according to claim 1 , wherein

the speed reducer is a speed reducer having forward driving efficiency of 60% or more.

9 . The control system according to claim 1 , wherein

the speed reducer is a speed reducer having a backlash lower than a predetermined value.

10 . The control system according to claim 1 , wherein

the speed reducer is a speed reducer having no backlash.

11 . The control system according to claim 1 , wherein

the speed reducer includes a plurality of gears, and

the plurality of gears has coating layers that reduce friction on outer peripheral sections that mesh with each other.

12 . The control system according to claim 1 , wherein

the motor is a motor in which cogging torque is 50% or less of motor rated torque.

13 . The control system according to claim 1 , wherein

the motor is a motor in which a winding wire is configured by a flexible substrate.

14 . The control system according to claim 1 , wherein

the robot is a robot that holds an endoscope.

15 . The control system according to claim 1 , wherein

the robot is a master robot or a slave robot.

16 . A control device comprising:

processing circuitry configured to

estimate external force received by a robot by subtracting a disturbance estimation value of when it is assumed that the robot is in an unloaded state from a disturbance estimation value of when the robot is in a loaded state,

acquire the disturbance estimation value of when it is assumed that the robot is in the unloaded state,

output, by a learned model, when state information of the robot is input, the disturbance estimation value of when it is assumed that the robot is in the unloaded state,

wherein the learned model is a model acquired by an input of time-series information of an acceleration reference value of an input shaft and an angle and an angular velocity of the input shaft and an output shaft to a neural network,

wherein an actuator includes

an encoder on an output shaft side,

a speed reducer coupled to the encoder on the output shaft side and having backdrivability,

a motor coupled to the speed reducer, and

an encoder on an input shaft side which encoder is coupled to the motor.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 9, 2024
From: YAJIMA, SHUNSUKE; ARAI, JUN
To: SONY GROUP CORPORATION
Reel/Frame 067358/0161 →
Priority Claims (1)
JP 2021-186535 · Nov 16, 2021 · national
Continuity (1)
Related Publication 20250009446A1 · Jan 9, 2025
References Cited (21)
US 20130074636A1 · Doi · 2013 [cited by examiner]
US 20180023753A1 · Kawamori · 2018 [cited by examiner]
US 20180241283A1 · Kokubo · 2018 [cited by examiner]
US 20180325713A1 · Gregg · 2018 [cited by examiner]
US 20180361576A1 · Sakai · 2018 [cited by examiner]
US 20190064756A1 · Tajima · 2019 [cited by examiner]
US 20190368594A1 · Sakata · 2019 [cited by examiner]
US 20190391566A1 · Ishikawa · 2019 [cited by examiner]
US 20200272122A1 · Oikawa · 2020 [cited by examiner]
US 20210276183A1 · Takahashi · 2021 [cited by examiner]
US 20220226993A1 · Madsen · 2022 [cited by examiner]
CN 109483597A · 2019 [cited by applicant]
JP H03065041A · 1991 [cited by applicant]
JP H0365041A · 1991 [cited by examiner]
JP H07319558A · 1995 [cited by applicant]
JP 2019049852A · 2019 [cited by applicant]
JP 2021049597A · 2021 [cited by applicant]
WO 2012127532A1 · 2012 [cited by applicant]
WO 2015133291A1 · 2015 [cited by applicant]
WO WO2020213062A1 · 2020 [cited by examiner]
International Search Report and Written Opinion mailed on Jan. 31, 2023, received for International Application No. PCT/JP2022/041566, filed on Nov. 8, 2022, 11 pages including English Translation. [cited by applicant]