公开(公告)号：US20240331173A1

公开(公告)日：2024-10-03

申请号：US18603100

申请日：2024-03-12

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： BAIYU PAN ,  Jianxin Pang

IPC: G06T7/50 ,  G06V10/77 ,  G06V10/82

CPC classification number: G06T7/50 ,  G06V10/7715 ,  G06V10/82 ,  G06T2207/20228

Abstract: A method for binocular depth estimation is provided, including: obtaining binocular images and performing feature extraction on the binocular images to obtain left and right feature mappings; performing disparity construction by using the left and right feature mappings to obtain a disparity cost volume with a reduced dimension; performing attention feature learning on the disparity cost volume to obtain an attention feature vector and performing feature weighting on the disparity cost volume by using the attention feature vector to obtain a weighted cost volume; performing disparity regression on the weighted cost volume based on a two-dimensional convolution to obtain a prediction disparity map; and performing disparity depth conversion on the prediction disparity map to obtain a depth map of the binocular images.

公开(公告)号：US11850747B2

公开(公告)日：2023-12-26

申请号：US17112569

申请日：2020-12-04

Applicant: UBTECH ROBOTICS CORP LTD

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

IPC: B25J9/16 ,  B25J19/02 ,  G06N3/08

CPC classification number: B25J9/161 ,  B25J9/1697 ,  B25J19/023 ,  G06N3/08

Abstract: The present disclosure provides an action imitation method as well as a robot and a computer readable storage medium using the same. The method includes: collecting a plurality of action images of a to-be-imitated object; processing the action images through a pre-trained convolutional neural network to obtain a position coordinate set of position coordinates of a plurality of key points of each of the action images; calculating a rotational angle of each of the linkages of the to-be-imitated object based on the position coordinate sets of the action images; and controlling a robot to move according to the rotational angle of each of the linkages of the to-be-imitated object. In the above-mentioned manner, the rotational angle of each linkage of the to-be-imitated object can be obtained by just analyzing and processing the images collected by an ordinary camera without the help of high-precision depth camera.

公开(公告)号：US20230386244A1

公开(公告)日：2023-11-30

申请号：US18078027

申请日：2022-12-08

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： SHUPING HU ,  Kan Wang ,  Huan Tan ,  Jianxin Pang

IPC: G06V40/10 ,  G06V10/776 ,  G06V10/74

CPC classification number: G06V40/103 ,  G06V10/776 ,  G06V10/761

Abstract: A person re-identification method, a storage medium, and a terminal device are provided. In the method, a preset ratio-based triplet loss function is used as a loss function during training The ratio-based triplet loss function limits a ratio of a positive sample feature distance to a negative sample feature distance to be less than a preset ratio threshold. The positive sample feature distance is a distance between a reference image feature and a positive sample image feature, and the negative sample feature distance is a distance between the reference image feature and a negative sample image feature. Compared with the existing absolute distance-based triplet loss function, in the case of small inter-class differences and large intra-class differences, the ratio-based triplet loss function can effectively improve the stability of model training, the features extracted by the trained model are more discriminative and robust, thereby improving the accuracy of person re-identification results.

公开(公告)号：US11693430B2

公开(公告)日：2023-07-04

申请号：US17114526

申请日：2020-12-08

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Jie Bai ,  Ligang Ge ,  Yizhang Liu ,  Hongge Wang ,  Jianxin Pang ,  Youjun Xiong

IPC: G05D1/02 ,  G05D1/08 ,  B62D57/02 ,  G05B19/4155

CPC classification number: G05D1/0891 ,  B62D57/02 ,  G05B19/4155 ,  G05D1/0212 ,  G05B2219/40233

Abstract: A computer-implemented gait planning method includes: determining a pitch angle between a foot of the robot and a support surface where the robot stands; determining a support point on a sole of the foot according to the pitch angle; calculating an ankle-foot position vector according to the support point, wherein the ankle-foot position vector is a position vector from an ankle of the robot to a support point on a sole of the foot; calculating a magnitude of change of an ankle position according to the pitch angle and the ankle-foot position vector; and obtaining a compensated ankle position by compensating the ankle position according to the magnitude of change of the ankle position.

公开(公告)号：US11631192B2

公开(公告)日：2023-04-18

申请号：US17107860

申请日：2020-11-30

Applicant: UBTECH ROBOTICS CORP LTD

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

IPC: G06T7/73 ,  G06T7/12 ,  G06T7/50 ,  B25J9/16

Abstract: A robot climbing control method is disclosed. The method obtains an RGB color image and a depth image of stairs, extracts an outline of a target object of a target step on the stairs from the RGB color image, determines relative position information of the robot and the target step according to the depth image and the outline of the target object, and controls the robot to climb the target step according to the relative position information. The embodiment of the present disclosure allows the robot to effectively adjust postures and forward directions on any size of and non-standardized stairs and avoids the deviation of the walking direction, thereby improving the effectiveness and safety of the stair climbing of the robot.

公开(公告)号：US11602848B2

公开(公告)日：2023-03-14

申请号：US17120229

申请日：2020-12-13

Applicant: UBTECH ROBOTICS CORP LTD

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

IPC: B25J9/16 ,  B25J13/08

Abstract: A robot control method includes: obtaining force information associated with feet of the robot; calculating a zero moment point of a COM of a body of the robot based on the force information; updating a position trajectory of the robot according to the zero moment point of the COM of the body to obtain an updated position of the COM of the body; obtaining posture information of the robot; updating a posture trajectory of the robot according to the posture information to obtain an updated pose angle; performing inverse kinematics analysis on the updated position of the COM of the body and the updated pose angle to obtain joint angles of legs of the robot; and controlling the robot to move according to the joint angles.

公开(公告)号：US11593974B2

公开(公告)日：2023-02-28

申请号：US17075727

申请日：2020-10-21

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Rui Guo ,  Zhichao Liu ,  Jianxin Pang ,  Youjun Xiong

IPC: G06T11/00 ,  G06T7/13 ,  G06T7/90 ,  G06T7/70 ,  G06T3/00 ,  G01C21/00

Abstract: A method for building a map includes: acquiring an original grayscale map, preprocessing the original grayscale map to obtain a preprocessed map, binarizing the preprocessed map to obtain a binarized map, performing a boundary filling to the preprocessed map and the binarized map to obtain a boundary-filled preprocessed map and a boundary-filled binarized map, performing a boundary thinning to the boundary-filled binarized map to obtain a thinned binarized map, and performing a boundary thinning to the boundary-filled preprocessed map, according to the thinned binarized map, to obtain a thinned preprocessed map.

公开(公告)号：US20220375106A1

公开(公告)日：2022-11-24

申请号：US17866574

申请日：2022-07-18

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Shuping Hu ,  Jun Cheng ,  Jingtao Zhang ,  Miaochen Guo ,  Dong Wang ,  Zaiwang Gu ,  Jianxin Pang

IPC: G06T7/246 ,  G06T7/73

Abstract: A method includes: performing target detection on a current image to obtain detection information of a plurality of detected targets; obtaining position prediction information of each of a plurality of tracked targets and a number of times of tracking losses of targets from tracking information of each of the tracked targets, and determining a first matching threshold for each of the tracked targets according to the number of times of tracking losses of targets; calculating a motion matching degree between each of the tracked targets and each of the detected targets according to the position detection information and the position prediction information; for each of the tracked targets, obtaining a motion matching result according to the motion matching degree and the first matching threshold corresponding to the tracked target; and matching the detected targets and the tracked targets according to the motion matching results to obtain a tracking result.

公开(公告)号：US11416719B2

公开(公告)日：2022-08-16

申请号：US17012016

申请日：2020-09-03

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Chenchen Jiang ,  Zhichao Liu ,  Yongsheng Zhao ,  Yu Tang ,  Jianxin Pang ,  Youjun Xiong

IPC: G06K9/62 ,  G01S19/47 ,  G01S19/48 ,  G01S19/49

Abstract: The present disclosure provides a localization method as well as a helmet and a computer readable storage medium using the same. The method includes: extracting first feature points from a target image; obtaining inertial information of the carrier, and screening the first feature points based on the inertial information to obtain second feature points; triangulating the second feature points of the target image to generate corresponding initial three-dimensional map points, if the target image is a key frame image; performing a localization error loopback calibration on the initial three-dimensional map points according to at least a predetermined constraint condition to obtain target three-dimensional map points; and determining a positional point of the specific carrier according to the target three-dimensional map points. In this manner, the accuracy of the localization of a dynamic object such as a person when moving can be improved.

公开(公告)号：US11331806B2

公开(公告)日：2022-05-17

申请号：US16843921

申请日：2020-04-09

Applicant: UBTECH ROBOTICS CORP LTD

Inventor： Zecai Lin ,  Miaochen Guo ,  Yizhang Liu ,  Youjun Xiong ,  Jianxin Pang

IPC: G05B19/42 ,  B25J9/16 ,  B25J9/04 ,  B25J9/06 ,  B25J9/00 ,  B25J17/02 ,  B25J13/08 ,  B25J19/04 ,  B25J9/12

Abstract: The present disclosure discloses a robot control method as well as an apparatus, and a robot using the same. The method includes: obtaining a human pose image; obtaining pixel information of key points in the human pose image; obtaining three-dimensional positional information of key points of a human arm according to the pixel information of the preset key points; obtaining a robotic arm kinematics model of a robot; obtaining an angle of each joint in the robotic arm kinematics model according to the three-dimensional positional information of the key points of the human arm and the robotic arm kinematics model; and controlling an arm of the robot to perform a corresponding action according to the angle of each joint. The control method does not require a three-dimensional stereo camera to collect three-dimensional coordinates of a human body, which reduces the cost to a certain extent.