Control apparatus, robot, learning apparatus, robot system, and method

Patent metadata

Field	Value
Publication number	US-2021283771-A1
Application number	US-202117173481-A
Country	US
Kind code	A1
Filing date	Feb 11, 2021
Priority date	Mar 13, 2020
Publication date	Sep 16, 2021
Grant date	—

Abstract

A control apparatus of a robot may include a state obtaining unit configured to obtain state observation data including flexible related observation data, which is observation data regarding a state of at least one of a flexible portion, a portion of the robot on a side where an object is gripped relative to the flexible portion, and the gripped object; and a controller configured to control the robot so as to output an action to be performed by the robot to perform predetermined work on the object, in response to receiving the state observation data, based on output obtained as a result of inputting the state observation data obtained by the state obtaining unit to a learning model, the learning model being learned in advance through machine learning and included in the controller.

First claim

1 . A control apparatus of a robot comprising:
a state obtaining unit configured to obtain state observation data comprising flexible related observation data, which is observation data regarding a state of at least one of a flexible portion, a portion of the robot on a side where an object is gripped relative to the flexible portion, and a gripped object, wherein the robot comprises:
a gripper configured to grip an object,
an arm configured to move the gripper, and
a physically flexible portion provided at least one of an intermediate position of the gripper, a position between the gripper and the arm, and an intermediate position of the arm; and
a controller configured to control the robot so as to output an action to be performed by the robot to perform predetermined work on the object, in response to receiving the state observation data, based on output obtained as a result of inputting the state observation data obtained by the state obtaining unit to a learning model , the learning model being learned in advance through machine learning and included in the controller.

2 . The control apparatus according to claim 1 , wherein
the predetermined work comprises a plurality of motion primitives, and the controller comprises a plurality of learning models corresponding to the plurality of motion primitives.

3 . The control apparatus according to claim 2 ,
wherein the plurality of motion primitives comprise at least one or more constraining motion primitives that control the robot so as to perform an action while maintaining a constrained state where the gripper or the object gripped by the gripper is brought into contact with or is near its environment.

4 . The control apparatus according to claim 3 ,
wherein the learning model corresponding to the constrained motion primitive is learned through learning processing in which a state space and an action space are subjected to dimension reduction.

5 . The control apparatus according to claim 1 ,
wherein the learning model outputs actions, for an entire operation not divided into a plurality of motion primitives or for one motion primitive, including an action such that an operation is performed while maintaining a constrained state where the gripper or the object gripped by the gripper is in contact with or near the environment.

6 . The control apparatus according to claim 5 ,
wherein the learning model regarding control of the robot while maintaining the constrained state is learned through learning processing in which a state space and an action space are subjected to dimension reduction.

7 . The control apparatus according to claim 1 , wherein
the flexible portion is positioned between the gripper and the arm, and the flexible related observation data comprises at least one of:
force-related sensing data related to a force taken on by the gripper from the object;
at least one of a position, speed, orientation, and angular velocity of a change in orientation of the gripper;
at least one of a relative distance and a relative angle between the gripper and the arm;
force-related sensing data related to a force taken on by the flexible portion; and
data that is based on a captured image of at least one of the object, the gripper, and the flexible portion.

8 . The control apparatus according to claim 2 , wherein
the flexible portion is positioned between the gripper and the arm, and the flexible related observation data comprises at least one of:
force-related sensing data related to a force taken on by the gripper from the object;
at least one of a position, speed, orientation, and angular velocity of a change in orientation of the gripper;
at least one of a relative distance and a relative angle between the gripper and the arm;
force-related sensing data related to a force taken on by the flexible portion; and
data that is based on a captured image of at least one of the object, the gripper, and the flexible portion.

9 . The control apparatus according to claim 3 , wherein
the flexible portion is positioned between the gripper and the arm, and the flexible related observation data comprises at least one of:
force-related sensing data related to a force taken on by the gripper from the object;
at least one of a position, speed, orientation, and angular velocity of a change in orientation of the gripper;
at least one of a relative distance and a relative angle between the gripper and the arm;
force-related sensing data related to a force taken on by the flexible portion; and
data that is based on a captured image of at least one of the object, the gripper, and the flexible portion.

10 . The control apparatus according to claim 4 , wherein
the flexible portion is positioned between the gripper and the arm, and the flexible related observation data comprises at least one of:
force-related sensing data related to a force taken on by the gripper from the object;
at least one of a position, speed, orientation, and angular velocity of a change in orientation of the gripper;
at least one of a relative distance and a relative angle between the gripper and the arm;
force-related sensing data related to a force taken on by the flexible portion; and
data that is based on a captured image of at least one of the object, the gripper, and the flexible portion.

11 . The control apparatus according to claim 5 , wherein
the flexible portion is positioned between the gripper and the arm, and the flexible related observation data comprises at least one of:
force-related sensing data related to a force taken on by the gripper from the object;
at least one of a position, speed, orientation, and angular velocity of a change in orientation of the gripper;
at least one of a relative distance and a relative angle between the gripper and the arm;
force-related sensing data related to a force taken on by the flexible portion; and
data that is based on a captured image of at least one of the object, the gripper, and the flexible portion.

12 . The control apparatus according to claim 6 , wherein
the flexible portion is positioned between the gripper and the arm, and the flexible related observation data comprises at least one of: force-related sensing data related to a force taken on by the gripper from the object;
at least one of a position, speed, orientation, and angular velocity of a change in orientation of the gripper;
at least one of a relative distance and a relative angle between the gripper and the arm;
force-related sensing data related to a force taken on by the flexible portion; and
data that is based on a captured image of at least one of the object, the gripper, and the flexible portion.

13 . A robot system comprising:
a robot comprising:
a gripper configured to grip an object;
an arm configured to move the gripper;
a physically flexible portion provided at least one of an intermediate position of the gripper, a position between the gripper and the arm, and an intermediate position of the arm; and
the control apparatus according to claim 1 .

14 . A robot comprising:
a gripper configured to grip an object; an arm configured to move the gripper; a physically flexible portion provided at least one of an intermediate position of the gripper, a position between the gripper and the arm, and an intermediate position of the arm; and a sensor configured to detect a state of at least one of the flexible portion, a portion of the robot on a side where the object is gripped relative to the flexible portion, and a gripped object.

15 . A control method of controlling a robot,

Assignees

• Omron Tateisi Electronics Co

Inventors

• Ijiri Yoshihisa
• Shibata Yoshiya
• Hamaya Masaya
• Tanaka Kazutoshi
• Vondrigalski Felix
• Saito Chisato

Classifications

• B25J9/1602 Primary

  characterised by the control system, structure, architecture · CPC title

• B25J9/1605

  Simulation of manipulator lay-out, design, modelling of manipulator · CPC title

• B25J9/163 Primary

  learning, adaptive, model based, rule based expert control · CPC title

• B25J13/08 Primary

  by means of sensing devices, e.g. viewing or touching devices · CPC title

• G06N20/00

  Machine learning · CPC title