Robot, method, and manipulating system

Patent metadata

Field	Value
Publication number	US-11833682-B2
Application number	US-201916710656-A
Country	US
Kind code	B2
Filing date	Dec 11, 2019
Priority date	Dec 14, 2018
Publication date	Dec 5, 2023
Grant date	Dec 5, 2023

Abstract

A robot including a manipulator includes: an image-pickup acquisition unit configured to acquire an image of an environmental space including a target object to be grasped; and a control unit configured to control a motion performed by the robot, in which the control unit causes the robot to acquire, by the image-pickup acquisition unit, a plurality of information pieces of the target object to be grasped while it moves the robot so that the robot approaches the target object to be grasped, calculates, for each of the information pieces, a grasping position of the target object to be grasped and an index of certainty of the grasping position by using a learned model, and attempts to grasp, by moving the manipulator, the target object to be grasped at a grasping position selected based on a result of the calculation.

First claim

What is claimed is:

1. A robot comprising a manipulator, the robot further comprising:
an image-pickup acquisition unit configured to acquire an image-pickup image of an environmental space including a target object to be grasped; and
a control unit configured to control a motion performed by the robot, wherein
the control unit
causes the robot to acquire, by the image-pickup acquisition unit, a plurality of image-pickup images of the target object to be grasped while it moves the robot so that the robot approaches the target object to be grasped,
calculates, for information acquired from the image-pickup images, a plurality of grasping positions of the target object to be grasped and indices of certainty of the grasping positions by using a learned model, the learned model receiving the information acquired from the image-pickup images and outputting the plurality of grasping positions of the target object to be grasped and indices of certainty of the grasping positions,
attempts to grasp, by moving the manipulator, the target object to be grasped at a grasping position selected among the plurality of grasping positions based on a result of the calculation, and
determines whether there are remaining grasping positions on the target object at which an attempt to grasp has not been made,

wherein the grasping positions are on the target object where the target object is to be grasped.

2. The robot according to claim 1 , wherein the control unit preferentially selects the grasping position corresponding to a relatively high index and attempts to grasp the target object to be grasped at the selected grasping position.

3. The robot according to claim 1 , wherein the control unit attempts to grasp the target object to be grasped by moving the manipulator when at least one of the indices higher than a predetermined threshold has been obtained.

4. The robot according to claim 1 , wherein the image-pickup acquisition unit is disposed at a tip of the manipulator.

5. The robot according to claim 1 , wherein the information is image data on a 3D image created by compositing a plurality of image-pickup images of the target object to be grasped acquired by the image-pickup acquisition unit.

6. A method for controlling a robot comprising an image-pickup acquisition unit configured to acquire an image-pickup image of an environmental space including a target object to be grasped, and a manipulator, the method comprising:
causing the robot to acquire, by the image-pickup acquisition unit, a plurality of image-pickup images of the target object to be grasped while the robot is moved so as to approach the target object to be grasped;
calculating, for information acquired from the image-pickup images, a plurality of grasping positions of the target object to be grasped and indices of certainty of the grasping positions by using a learned model, the learned model receiving the information acquired from the image-pickup images and outputting the plurality of grasping positions of the target object to be grasped and indices of certainty of the grasping positions;
attempting to grasp, by moving the manipulator, the target object to be grasped at a grasping position selected among the plurality of grasping positions based on a result of the calculation; and
determining whether there are remaining grasping positions on the target object at which an attempt to grasp has not been made,
wherein the grasping positions are on the target object where the target object is to be grasped.

7. A manipulating system comprising a manipulator, the manipulating system further comprising:
an image-pickup acquisition unit configured to acquire an image-pickup image of an environmental space including a target object to be grasped; and
a control unit configured to control a motion performed by the manipulating system, wherein
the control unit
causes the manipulating system to acquire, by the image-pickup acquisition unit, a plurality of image-pickup images of the target object to be grasped while it moves the manipulating system so that the manipulating system approaches the target object to be grasped,
calculates, for information acquired from the image-pickup images, a plurality of grasping positions of the target object to be grasped and indices of certainty of the grasping positions by using a learned model, the learned model receiving the information acquired from the image-pickup images and outputting the plurality of grasping positions of the target object to be grasped and indices of certainty of the grasping positions,
attempts to grasp, by moving the manipulator, the target object to be grasped at a grasping position selected among the plurality of grasping positions based on a result of the calculation, and
determines whether there are remaining grasping positions on the target object at which an attempt to grasp has not been made,

wherein the grasping positions are on the target object where the target object is to be grasped.

8. The robot according to claim 1 , wherein the control unit determines that there are remaining grasping positions on the target object where an attempt to grasp has not been made, and determines a next grasping position on the target object to be grasped among the remaining grasping positions when the target object is not successfully grasped at the grasping position.

9. The robot according to claim 1 , wherein the control unit determines a predetermined time elapses when the target object is not successfully grasped at the grasping position, and determines remaining grasping positions on the target object when the predetermined time elapses.

Assignees

• Toyota Motor Co Ltd

Inventors

• Ikeda Takuya
• Terada Koji

Classifications

• B25J9/1612 Primary

  characterised by the hand, wrist, grip control · CPC title

• B25J9/163

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

• B25J9/1669

  characterised by special application, e.g. multi-arm co-operation, assembly, grasping · CPC title

• B25J9/1697 Primary

  Vision controlled systems · CPC title

• B25J19/021

  Optical sensing devices · CPC title