IP Library Granted Patent US 12686123
Granted Patent B2
US 12686123 · App. 18/965,506 · Granted Jul 21, 2026

Method and system for estimating posture of robot

Inventors: Jung Won Lee (Suwon-Si, KR); Dong Yeon Yoo (Suwon-Si, KR); Dong-Hee Yun (Suwon-Si, KR)
Assignee: AJOU UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION
B25J9/1653B25J9/1664
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 12686123
App. No.
18/965,506
Granted
Jul 21, 2026
Kind
B2
Abstract

A method of estimating a posture of a robot is disclosed. The posture estimation method of the robot according to the present disclosure includes: generating a first marker and at least one second marker and attaching them to the robot; collecting an image including the first marker and at least one of the plurality of second markers; estimating position information and rotation information of the first marker and each of the second markers; deriving the position information and the rotation information of the first marker depending on a relative positional relationship between the first marker and each of the second markers when the first marker is not identified; and estimating a posture of the robot based on the position information and the rotation information of the first marker.

Claims (21)

1 . A method of estimating a posture of a robot executed by one or more processors of a computer device, the method comprising:

generating a first marker and one or more second markers and attaching them to the robot;

collecting an image including the first marker and at least one of the one or more second markers;

estimating position information and rotation information of the first marker and each of the one or more second markers in the image;

deriving the position information and the rotation information of the first marker depending on a relative positional relationship between the first marker and each of the one or more second markers in the image when the first marker is not identified; and

estimating a posture of the robot based on the position information and the rotation information of the first marker.

2 . The method of claim 1 , wherein the first marker is attached to an end-effector of the robot.

3 . The method of claim 1 , further comprising:

setting the positional relationship between the first marker and each of the one or more second markers attached to the robot,

wherein the positional relationship between the first marker and a specific second marker is derived by analyzing an image generated by simultaneously photographing the first marker and the specific second marker.

4 . The method of claim 1 , wherein there are a plurality of second markers and state information of the first marker is derived in plural depending on the positional relationship between the first marker and each of the plurality of second markers in the image, and

the method further comprising:

selecting one of the state information of the first marker derived in plural.

5 . The method of claim 1 , wherein the posture of the robot is estimated by a machine learning module in which a relationship between the state information of the first marker and the posture of the robot is previously learned.

6 . A system for estimating a posture of a robot, the system comprising:

a first marker and one or more second markers attached to the robot;

a sensor configured to collect an image including the first marker and at least one of the one or more second markers; and

a processor configured to:

estimate position information and rotation information of the first marker and each of the one or more second markers in the image,

derive the position information and the rotation information of the first marker depending on a relative positional relationship between the first marker and each of the one or more second markers in the image when the first marker is not identified, and

estimate a posture of the robot based on the position information and the rotation information of the first marker.