公开(公告)号：US20210181747A1

公开(公告)日：2021-06-17

申请号：US17113132

申请日：2020-12-07

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Shuping Hu ,  Jun Cheng ,  Jingtao Zhang ,  Miaochen Guo ,  Dong Wang ,  Jianxin Pang ,  Youjun Xiong

IPC: G05D1/02 ,  G06T1/00 ,  G06T7/13 ,  G06T7/73 ,  B62D57/02

Abstract: A robot climbing control method is disclosed. A gravity direction vector in a gravity direction in a camera coordinate system of a robot is obtained. A stair edge of stairs in a scene image is obtained and an edge direction vector of the stair edge in the camera coordinate system is determined. A position parameter of the robot relative to the stairs is determined according to the gravity direction vector and the edge direction vector. Poses of the robot are adjusted according to the position parameter to control the robot to climb the stairs.

公开(公告)号：US20210146538A1

公开(公告)日：2021-05-20

申请号：US16734393

申请日：2020-01-05

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Zecai Lin ,  Zhaohui An ,  Zheng Xie ,  Yizhang Liu ,  Youjun Xiong ,  Jianxin Pang

IPC: B25J9/16 ,  B25J13/08

Abstract: A method for controlling an arm of a robot to imitate a human arm, includes: acquiring first pose information of key points of a human arm to be imitated; converting the first pose information into second pose information of key points of an arm of a robot; determining an angle value of each joint of the arm according to inverse kinematics of the arm based on the second pose information; and controlling the arm to move according to the angle values.

公开(公告)号：US20210107577A1

公开(公告)日：2021-04-15

申请号：US16724413

申请日：2019-12-23

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Chunyu Chen ,  Yizhang Liu ,  Ligang Ge ,  Xianwei Su ,  Zheng Xie ,  Youjun Xiong ,  Jianxin Pang

IPC: B62D57/02 ,  G01L5/16

Abstract: The present disclosure provides a zero moment point jitter processing method as well as an apparatus and a robot using the same. The method includes: obtaining left foot force information and right foot force information collected by sensors; calculating a first zero moment point and a second zero moment point of soles of two feet of a robot based on the left foot force information and the right foot force information; calculating a third zero moment point of the robot according to the first zero moment point and the second zero moment point; calculating a jitter amplitude of the third zero moment point within a preset period; and adjusting a position of the third zero moment point in response to the jitter amplitude being not larger than a predetermined jitter amplitude threshold. In this manner, the robot can eliminate zero moment point jitters within a certain amplitude.

公开(公告)号：US20200206945A1

公开(公告)日：2020-07-02

申请号：US16556233

申请日：2019-08-30

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Youjun Xiong ,  Jianxin Pang ,  Wanli Zhang ,  Jingtao Zhang

IPC: B25J13/08 ,  B25J19/02 ,  B25J9/16

Abstract: The present disclosure relates to robot technology, which provides a robot pose estimation method as well as an apparatus and a robot using the same. The method includes: obtaining, through an inertial measurement unit, initial 6DoF pose data; performing a first correction on the initial 6DoF pose data based on pose data obtained through an auxiliary sensor to obtain corrected 6DoF pose data; obtaining, through a 2D lidar sensor disposed on a stable platform, 3DoF pose data; and performing a second correction on the corrected 6DoF pose data based on the 3DoF pose data to obtain target 6DoF pose data. In this manner, the accuracy of the pose data of the robot is improved, and the accurate pose estimation of the robot is realized.

公开(公告)号：US20200206914A1

公开(公告)日：2020-07-02

申请号：US16671164

申请日：2019-10-31

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Yongping Zeng ,  Youjun Xiong ,  Zhongliang Wang ,  Dong Liu ,  Jianxin Pang

IPC: B25J9/16 ,  B25J9/10 ,  G05F1/10

Abstract: The present disclosure is provides a servo control method as well as an apparatus and a robot using the same. The method includes: obtaining a teeth force reduction multiple of a gear of a servo; creating a voltage queue based on the teeth force reduction multiple; calculating a target loading voltage corresponding to a current moment based on a voltage queue; and applying the target loading voltage on a motor of the servo, wherein the target loading voltage is for driving the motor of the servo to rotate. Through the above-mentioned method, the loading voltage can be effectively reduced when the servo is started, thereby protecting teeth of the gear of the servo and increasing the service life of the servo.

公开(公告)号：US20200206898A1

公开(公告)日：2020-07-02

申请号：US16572637

申请日：2019-09-17

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： YOUJUN XIONG ,  Ligang Ge ,  Yizhang Liu ,  Chunyu Chen ,  Zheng Xie ,  Jianxin Pang

IPC: B25J9/00 ,  B25J13/08 ,  B25J9/16

Abstract: There are a biped robot gait control method and a biped robot, where the method includes: obtaining six-dimensional force information, and determining a motion state of two legs of the biped robot; calculating a ZMP position of each of two legs of the biped robot; determining a ZMP expected value of each of the two legs in real time; obtaining a compensation angle of an ankle joint of each of the two legs of the biped robot by inputting the ZMP position, a change rate of the ZMP position, the ZMP expected value, and a change rate of the ZMP expected value to an ankle joint smoothing controller so as to perform a close-loop ZMP tracking control on each of the two legs; adjusting a current angle of the ankle joint of each of the two legs of the biped robot in real time; and repeating the forgoing steps.

公开(公告)号：US20200184682A1

公开(公告)日：2020-06-11

申请号：US16548868

申请日：2019-08-23

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： YOUJUN XIONG ,  Wanli Zhang ,  Jianxin Pang

IPC: G06T7/73 ,  G06T7/246 ,  G06T7/90

Abstract: The present disclosure relates to robot technology, which provides an object pose tracking method and apparatus. The method includes: obtaining an initial pose of the object, and determining a first viewing angle of an object with respect to a camera based on the initial pose; searching for a first 3D model corresponding to the first viewing angle; calculating a projected contour of an initial pose using the searched first 3D model, and obtaining feature point(s) of the projected contour; calculating a pose change amount based on the feature point(s) of the projected contour and feature point(s) of a real contour; and performing an iterative calculation on the pose change amount to obtain a pose correction amount, and obtaining a corrected pose of the object based on the pose correction amount. In the calculation process, the 3D model can be selected to improve the calculation speed by fewer feature points.

公开(公告)号：US20240193929A1

公开(公告)日：2024-06-13

申请号：US18536287

申请日：2023-12-12

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： KAN WANG ,  Jianxin Pang ,  Huan Tan

IPC: G06V10/82 ,  G06V10/77

CPC classification number: G06V10/82 ,  G06V10/7715 ,  G06V2201/07

Abstract: A target identification method includes: obtaining an image containing a target to be identified; performing feature extraction on the image to obtain image features in the image; and inputting the image features into a target identification network model to obtain an identification result that determines a class to which the target to be identified belongs. The target identification network model includes a loss function that is based on intra-class constraints and inter-class constraints. The intra-class constraints are to constrain an intra-class distance between sample image features of a sample target and a class center of a class to which the sample target belongs, and the inter-class constraints are to constrain inter-class distances between class centers of different classes, and/or inter-class angles between the class centers of different classes.

公开(公告)号：US20240135579A1

公开(公告)日：2024-04-25

申请号：US18380086

申请日：2023-10-13

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Kan WANG ,  Shuping Hu ,  Jianxin Pang ,  Huan Tan

IPC: G06T7/73 ,  G06V10/77 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V40/10

CPC classification number: G06T7/74 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V40/10 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06V20/52

Abstract: A method for obtaining a feature extraction model, a method for human fall detection and a terminal device are provided. The method for human fall detection includes: inputting a human body image into a feature extraction model for feature extraction to obtain a target image feature; in response to a distance between the target image feature and a pre-stored mean value of standing category image features being greater than or equal to a preset distance threshold, determining that the human body image is a human falling image; and in response to the distance being less than the preset distance threshold, determining that the human body image is a human standing image. The feature extraction model is obtained based on constraint training to aggregate standing category image features and separate falling category image features from the standing category image features.

公开(公告)号：US11940774B2

公开(公告)日：2024-03-26

申请号：US17115735

申请日：2020-12-08

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Miaochen Guo ,  Jingtao Zhang ,  Dong Wang ,  Shuping Hu ,  Jianxin Pang ,  Youjun Xiong

IPC: G05B19/408 ,  G05B19/4155 ,  G06F18/214 ,  G06F18/22 ,  G06N3/08 ,  G06V10/764 ,  G06V20/10 ,  G06V20/64 ,  G06V40/20

CPC classification number: G05B19/4086 ,  G05B19/4155 ,  G06F18/214 ,  G06F18/22 ,  G06N3/08 ,  G06V10/764 ,  G06V20/10 ,  G06V20/647 ,  G06V40/20 ,  G05B2219/33027 ,  G05B2219/50391

Abstract: The present disclosure provides action imitation method as well as a robot and a computer readable storage medium using the same. The method includes: collecting at least a two-dimensional image of a to-be-imitated object; obtaining two-dimensional coordinates of each key point of the to-be-imitated object in the two-dimensional image and a pairing relationship between the key points of the to-be-imitated object; converting the two-dimensional coordinates of the key points of the to-be-imitated object in the two-dimensional image into space three-dimensional coordinates corresponding to the key points of the to-be-imitated object through a pre-trained first neural network model, and generating an action control instruction of a robot based on the space three-dimensional coordinates corresponding to the key points of the to-be-imitated object and the pairing relationship between the key points, where the action control instruction is for controlling the robot to imitate an action of the to-be-imitated object.