Computer-implemented method for robot fall prediction, and robot

US10821606B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-10821606-B2
Application numberUS-201715856052-A
CountryUS
Kind codeB2
Filing dateDec 27, 2017
Priority dateOct 20, 2017
Publication dateNov 3, 2020
Grant dateNov 3, 2020

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

The present disclosure is applicable to robot technology. A method for robot fall prediction, and a robot are provided. The method includes: searching a weighted value of a center of gravity of the robot corresponding to a posture of the robot, according to a preset first corresponding relationship; correcting an offset of the center of gravity of the robot based on the weighted value of the center of gravity of the robot; correcting an acceleration of the robot based on an offset direction of the center of gravity of the robot; and determining whether the robot will fall based on the corrected offset of the center of gravity, the offset direction of the center of gravity, and the corrected acceleration of the robot. The present disclosure improves the real-time performance and accuracy of the prediction for the fall of a robot through the fusion calculation of various data.

First claim

Opening claim text (preview).

What is claimed is: 1. A computer-implemented method for robot fall prediction, comprising: providing a robot comprising a processor, an acceleration sensor, and a gyroscope, wherein the processor is electronically coupled to the acceleration sensor and the gyroscope; searching, by the processor, a weighted value of a center of gravity of the robot corresponding to a posture of the robot, according to a preset first corresponding relationship, wherein the preset first corresponding relationship comprises correspondence between a plurality of postures of the robot and a plurality of weighted values of the center of gravity of the robot; obtaining, by the gyroscope, an offset direction of the center of gravity of the robot, and an offset of the center of gravity of the robot; correcting, by the processor, the offset of the center of gravity of the robot based on the weighted value of the center of gravity of the robot; obtaining, by the acceleration sensor, an acceleration of the robot; correcting, by the processor, the acceleration of the robot based on the offset direction of the center of gravity of the robot; and determining, by the processor, whether the robot will fall based on the corrected offset of the center of gravity of the robot, the offset direction of the center of gravity of the robot, and the corrected acceleration of the robot. 2. The method of claim 1 , wherein the robot further comprises a plurality of nodes, each of the nodes comprises a servo having a position sensor, the processor is further electronically coupled to the servo of each of the nodes, and the step of searching, by the processor, the weighted value of the center of gravity of the robot corresponding to the posture of the robot, according to the preset first corresponding relationship, comprises: obtaining, by the processor, position parameters of the nodes of the robot used to indicate the posture of the robot, by using the position sensor; and searching, by the processor, the weighted value of the center of gravity of the robot corresponding to the obtained position parameters of the nodes of the robot, according to a preset second corresponding relationship, wherein the preset second corresponding relationship comprises correspondence between a plurality of sets of the position parameters of the nodes of the robot used to indicate the plurality of postures of the robot, and the plurality of weighted values of the center of gravity of the robot. 3. The method of claim 2 , wherein the step of searching, by the processor, the weighted value of the center of gravity of the robot corresponding to the obtained position parameters of the nodes of the robot, according to the preset second corresponding relationship, comprises: performing, by the processor, an interval discrete processing on the obtained position parameters of the nodes of the robot, to obtain position discrete parameters; and searching, by the processor, the weighted value of the center of gravity of the robot corresponding to the obtained position discrete parameters, according to a preset third corresponding relationship, wherein the preset third corresponding relationship comprises correspondence between a plurality of sets of the position discrete parameters used to indicate the plurality of postures of the robot, and the plurality of weighted values of the center of gravity of the robot. 4. The method of claim 1 , wherein the step of correcting, by the processor, the offset of the center of gravity of the robot based on the weighted value of the center of gravity of the robot, comprises: obtaining, by the processor, the corrected offset of the center of gravity of the robot by multiplying the offset of the center of gravity of the robot by the weighted value of the center of gravity of the robot. 5. The method of claim 1 , wherein the acceleration of the robot comprises an acceleration direction and an acceleration value of the robot, and the step of correcting, by the processor, the acceleration of the robot based on the offset direction of the center of gravity of the robot, comprises: calculating, by the processor, a correlation factor between the acceleration direction of the robot and the offset direction of the center of gravity of the robot; and correcting, by the processor, the acceleration direction and the acceleration value of the robot based on the correlation factor. 6. The method of claim 5 , wherein the step of determining, by the processor, whether the robot will fall based on the corrected offset of the center of gravity of the robot, the offset direction of the center of gravity of the robot, and the corrected acceleration of the robot, comprises: determining, by the processor, a probability, a direction, and a determination of the fall of the robot based on the corrected offset of the center of gravity of the robot, the offset direction of the center of gravity of the robot, the corrected acceleration direction of the robot, the corrected acceleration value of the robot, and a decision tree parameter. 7. The method of claim 6 , wherein the step of determining, by the processor, the probability, the direction, and the determination of the fall of the robot based on the corrected offset of the center of gravity of the robot, the offset direction of the center of gravity of the robot, the corrected acceleration direction of the robot, the corrected acceleration value of the robot, and the decision tree parameter, comprises: determining, by the processor, the probability of the fall of the robot based on the corrected offset of the center of gravity of the robot, the corrected acceleration value of the robot, and the decision tree parameter; determining, by the processor, the direction of the fall of the robot based on the offset direction of the center of gravity of the robot, the corrected acceleration direction of the robot, and the decision tree parameter; and determining, by the processor, that the robot is going to fall, in response to the probability of the fall of the robot being greater than or equal to a fall probability threshold, and determining that the robot is not going to fall, in response to the probability of the fall of the robot being smaller than the fall probability threshold. 8. The method of claim 1 , wherein before the step of searching, by the processor, the weighted value of the center of gravity of the robot corresponding to the posture of the robot, according to the preset first corresponding relationship, further comprises: determining, by the processor, whether the offset of the center of gravity of the robot is greater than or equal to a first gravity center offset threshold; and in response to the offset of the center of gravity of the robot being greater than or equal to the first gravity center offset threshold, performing the step of searching, by the processor, the weighted value of the center of gravity of the robot corresponding to the posture of the robot, according to the preset first corresponding relationship. 9. The method of claim 8 , wherein before the step of correcting, by the processor, the acceleration of the robot based on the offset direction of the center of gravity of the robot, further comprises: determining, by the processor, whether the corrected offset of the center of gravity of the robot is greater than or equal to a second gravity center offset threshold; and in response to the corrected offset of the center of gravity of the robot being greater than or equal to the second gravity center offset threshold, performing the step of correcting, by the processor, the acceleration of the robot based on the offset direction of the center of gravity of the robot. 10. The method of c

Assignees

Inventors

Classifications

  • Minimize sum of gravitational torques of some joints · CPC title

  • Determining position of centre of gravity · CPC title

  • characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion · CPC title

  • parameters identification, estimation, stiffness, accuracy, error analysis · CPC title

  • Balancing devices · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US10821606B2 cover?
The present disclosure is applicable to robot technology. A method for robot fall prediction, and a robot are provided. The method includes: searching a weighted value of a center of gravity of the robot corresponding to a posture of the robot, according to a preset first corresponding relationship; correcting an offset of the center of gravity of the robot based on the weighted value of the ce…
Who is the assignee on this patent?
Ubtech Robotics Corp
What technology area does this patent fall under?
Primary CPC classification B25J9/1674. Mapped technology areas include Operations & Transport.
When was this patent published?
Publication date Tue Nov 03 2020 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 2 related publications on this page (citations in our corpus or others sharing the same primary CPC).