Method and apparatus for pose planar constraining on the basis of planar feature extraction

    公开(公告)号:US11182644B2

    公开(公告)日:2021-11-23

    申请号:US16725357

    申请日:2019-12-23

    Abstract: The present application provides a method and apparatus for pose planar constraining on the basis of planar feature extraction, wherein the method includes: inputting the acquired RGB color image and point cloud image into spatial transformation network to obtain two-dimensional and three-dimensional affine transformation matrixes; extracting the planar features of the transformed two-dimensional affine transformation matrix and three-dimensional affine transformation matrix; inputting the acquired planar features into the decoder and obtain the pixel classification of the planar features; clustering the vectors corresponding to the planar pixels to obtain the segmentation result of the planar sample; using planar fitted by the segmentation result to make planar constraint to the pose calculated by vision algorithm. The application combines RGB-D information to perform plane extraction, and designs a new spatial transformation network to transform two-dimensional color image and three-dimensional point cloud image.

    Waist joint of humanoid robot and humanoid robot

    公开(公告)号:US11364642B2

    公开(公告)日:2022-06-21

    申请号:US16856010

    申请日:2020-04-22

    Abstract: The present disclosure provides a waist joint of humanoid robot and a humanoid robot. The waist joint comprise: tile-shaped structural members, connection members, and substrates. The first end of the first connection member is slidably connected with the first end of the first tile-shaped structural member, and the first end of the second connection member is slidably connected with the second end of the first tile-shaped structural member; one side surface of the first substrate is slidably connected with the first end of the second tile-shaped structural member, and one side surface of the second substrate is slidably connected with the second end of the second tile-shaped structural member; the second end of the first connection member is connected with the third end of the second tile-shaped structural member, and the second end of the second connection member is connected with the fourth end of the second tile-shaped structural member.

    Joint support structure of a robot and a robot having the same

    公开(公告)号:US11364627B2

    公开(公告)日:2022-06-21

    申请号:US16848634

    申请日:2020-04-14

    Abstract: The present disclosure provides a joint support structure of a robot and a robot having the same. The joint support structure comprises: a drive motor; a reducing transmission mechanism; a motor side casing; a transmission side casing; and a knee joint sleeve disposed on outer peripheries of the motor side casing and of the transmission side casing and connected to the reducing transmission mechanism; the motor side casing has a first annular groove; the transmission side casing has a second annular groove; the knee joint sleeve is provided with an annular connector circumferentially surrounding the motor side casing, and the annular connector has a third annular groove matched with the first annular groove to form a first ball track for accommodating first balls; the knee joint sleeve has a fourth annular groove is matched with the second annular groove to form a second ball track.

    Method and Apparatus for Pose Planar Constraining on the Basis of Planar Feature Extraction

    公开(公告)号:US20210192271A1

    公开(公告)日:2021-06-24

    申请号:US16725357

    申请日:2019-12-23

    Abstract: The present application provides a method and apparatus for pose planar constraining on the basis of planar feature extraction, wherein the method includes: inputting the acquired RGB color image and point cloud image into spatial transformation network to obtain two-dimensional and three-dimensional affine transformation matrixes; extracting the planar features of the transformed two-dimensional affine transformation matrix and three-dimensional affine transformation matrix; inputting the acquired planar features into the decoder and obtain the pixel classification of the planar features; clustering the vectors corresponding to the planar pixels to obtain the segmentation result of the planar sample; using planar fitted by the segmentation result to make planar constraint to the pose calculated by vision algorithm. The application combines RGB-D information to perform plane extraction, and designs a new spatial transformation network to transform two-dimensional color image and three-dimensional point cloud image.

Patent Agency Ranking