Leg mechanism and humanoid robot
    102.
    发明授权

    公开(公告)号:US11713088B2

    公开(公告)日:2023-08-01

    申请号:US17134202

    申请日:2020-12-25

    CPC classification number: B62D57/032 B25J13/085 B25J17/00

    Abstract: A leg mechanism of a humanoid robot includes: an upper leg, a lower leg rotatably coupled to the upper leg, a knee module actuator mounted to the upper leg, a foot rotatably connected to the lower leg, a knee transmission mechanism connected to the knee module actuator and the lower leg and configured to transmit rotary motion from the knee module actuator to the lower leg, at least one ankle module actuator mounted to the upper leg, at least one ankle transmission mechanism connected to the at least one ankle module actuator and the foot and configured to transmit rotary motion from the at least one ankle module actuator to the foot.

    Navigation map updating method and apparatus and robot using the same

    公开(公告)号:US11629964B2

    公开(公告)日:2023-04-18

    申请号:US16843923

    申请日:2020-04-09

    Abstract: The present disclosure discloses a navigation map updating method as well as an apparatus, and a robot using the same. The method includes: controlling a robot to move along a designated path after a successful relocalization of the robot, and recording key frame data of each frame on the designated path and a corresponding pose; creating a new navigation map, and copying information in an original navigation map into the new navigation map; and covering the key frame data of each frame on the designated path onto the new navigation map to obtain an updated navigation map. In this manner, there is no need for the user to manipulate the robot to recreate the map at the environment where the robot is operated, which saves a lot of time and manpower.

    Robot balance control method, computer-readable storage medium and robot

    公开(公告)号:US11604466B2

    公开(公告)日:2023-03-14

    申请号:US17120232

    申请日:2020-12-13

    Abstract: A robot balance control method includes: obtaining force information associated with a left foot and a right foot of the robot; calculating a zero moment point of a center of mass (COM) of a body of the robot based on the force information; calculating a first position offset and a second position offset of the robot according to the zero moment point of the COM of the body; updating a position trajectory of the robot according to the first position offset and the second offset to obtain an updated position of the COM of the body; performing inverse kinematics analysis on the updated position of the COM of the body to obtain joint angles of the left leg and the right leg of the robot; and controlling the robot to move according to the joint angles.

    Method for extracting image of face detection and device thereof

    公开(公告)号:US11475707B2

    公开(公告)日:2022-10-18

    申请号:US17134467

    申请日:2020-12-27

    Abstract: The present disclosure provides a method for extracting a face detection image, wherein the method includes: obtaining a plurality of image frames by an image detector, performing a face detection process on each image frame to extract a face area, performing a clarity analysis on the face area of each image frame to obtain a clarity degree of a face, conducting a posture analysis on the face area of each image frame to obtain a face posture angle, generating a comprehensive evaluation index for each image frame in accordance with the clarity degree of the face and the face posture angle of each image frame, and selecting a key frame from the image frames based on the comprehensive evaluation index. Such that the resource occupancy rate during image data processing may be reduced, and the quality of the face detection process may be improved.

    METHOD AND DEVICE FOR TRAINING MULTI-TASK RECOGNITION MODEL AND COMPUTER-READABLE STORAGE MEDIUM

    公开(公告)号:US20220207913A1

    公开(公告)日:2022-06-30

    申请号:US17562963

    申请日:2021-12-27

    Abstract: A method for training a multi-task recognition model includes: obtaining a number of sample images, wherein some of the sample images are to provide feature-independent facial attributes, some of the sample images are to provide feature-coupled facial attributes, and some of the sample images are to provide facial attributes of face poses; training an initial feature-sharing model based on a first set of sample images to obtain a first feature-sharing model; training the first feature-sharing model based on the first set of sample images and a second set of sample images to obtain a second feature-sharing model with a loss value less than a preset second threshold; obtaining an initial multi-task recognition model by adding a feature decoupling model to the second feature-sharing model; and training the initial multi-task recognition model based on the sample images to obtain a trained multi-task recognition model.

Patent Agency Ranking