中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

30 records (took 0.018 seconds)

    SELECTIVELY DOWNLOADING TARGETED OBJECT RECOGNITION MODULES
    13.
    发明申请
    SELECTIVELY DOWNLOADING TARGETED OBJECT RECOGNITION MODULES 审中-公开

    公开(公告)号：US20180039835A1

    公开(公告)日：2018-02-08

    申请号：US15230412

    申请日：2016-08-06

    Applicant: X DEVELOPMENT LLC

    Inventor： Nareshkumar Rajkumar ,  Stefan Hinterstoisser ,  Max Bajracharya

    IPC: G06K9/00 ,  B25J9/16 ,  G06T1/00

    CPC classification number: G06K9/00664 ,  B25J9/1697 ,  G06K9/00979 ,  G06K9/00993 ,  G06K9/628 ,  G06T1/0014 ,  H04W4/025 ,  H04W4/60 ,  H04W4/80 ,  Y10S901/47

    Abstract: Methods, apparatus, systems, and computer-readable media are provided for downloading targeted object recognition modules that are selected from a library of candidate targeted object recognition modules based on various signals. In some implementations, an object recognition client may be operated to facilitate object recognition for a robot. It may download targeted object recognition module(s). Each targeted object recognition module may facilitate inference of an object type or pose of an observed object. The targeted object module(s) may be selected from a library of targeted object recognition modules based on various signals, such as a task to be performed by the robot. The object recognition client may obtain vision data capturing at least a portion of an environment in which the robot operates. The object recognition client may determine, based on the vision data and the downloaded object recognition module(s), information about an observed object in the environment.

    Methods and apparatus for determining the pose of an object based on point cloud data
    14.
    发明授权
    Methods and apparatus for determining the pose of an object based on point cloud data 有权

    公开(公告)号：US09868212B1

    公开(公告)日：2018-01-16

    申请号：US15046870

    申请日：2016-02-18

    Applicant: X Development LLC

    Inventor： Stefan Hinterstoisser

    IPC: G06F19/00 ,  B25J9/16 ,  G06F17/50

    CPC classification number: B25J9/1671 ,  G05B2219/40564 ,  G06F17/50 ,  G06T1/0014

    Abstract: Methods, apparatus, and computer readable media that are related to 3D object detection and pose determination and that may optionally increase the robustness and/or efficiency of the 3D object recognition and pose determination. Some implementations are generally directed to techniques for generating an object model of an object based on model point cloud data of the object. Some implementations of the present disclosure are additionally and/or alternatively directed to techniques for application of acquired 3D scene point cloud data to a stored object model of an object to detect the object and/or determine the pose of the object.

    DELEGATION OF OBJECT AND POSE DETECTION
    16.
    发明申请
    DELEGATION OF OBJECT AND POSE DETECTION 审中-公开

    公开(公告)号：US20200151447A1

    公开(公告)日：2020-05-14

    申请号：US16742526

    申请日：2020-01-14

    Applicant: X Development LLC

    Inventor： Nareshkumar Rajkumar ,  Stefan Hinterstoisser

    IPC: G06K9/00 ,  G06T7/33 ,  G06T7/73 ,  G06K9/62

    Abstract: Methods, apparatus, systems, and computer-readable media are provided for delegating object type and/or pose detection to a plurality of “targeted object recognition modules.” In some implementations, a method may be provided that includes: operating an object recognition client to facilitate object recognition for a robot; receiving, by the object recognition client, sensor data indicative of an observed object in an environment; providing, by the object recognition client, to each of a plurality of remotely-hosted targeted object recognition modules, data indicative of the observed object; receiving, by the object recognition client, from one or more of the plurality of targeted object recognition modules, one or more inferences about an object type or pose of the observed object; and determining, by the object recognition client, information about the observed object, such as its object type and/or pose, based on the one or more inferences.

    Delegation of object and pose detection
    17.
    发明授权
    Delegation of object and pose detection 有权

    公开(公告)号：US10579874B2

    公开(公告)日：2020-03-03

    申请号：US16014311

    申请日：2018-06-21

    Applicant: X Development LLC

    Inventor： Nareshkumar Rajkumar ,  Stefan Hinterstoisser

    IPC: G06K9/00 ,  G06K9/62 ,  G06T7/73 ,  G06T7/33

    Abstract: Methods, apparatus, systems, and computer-readable media are provided for delegating object type and/or pose detection to a plurality of “targeted object recognition modules.” In some implementations, a method may be provided that includes: operating an object recognition client to facilitate object recognition for a robot; receiving, by the object recognition client, sensor data indicative of an observed object in an environment; providing, by the object recognition client, to each of a plurality of remotely-hosted targeted object recognition modules, data indicative of the observed object; receiving, by the object recognition client, from one or more of the plurality of targeted object recognition modules, one or more inferences about an object type or pose of the observed object; and determining, by the object recognition client, information about the observed object, such as its object type and/or pose, based on the one or more inferences.

    SELECTIVELY DOWNLOADING TARGETED OBJECT RECOGNITION MODULES
    18.
    发明申请
    SELECTIVELY DOWNLOADING TARGETED OBJECT RECOGNITION MODULES 审中-公开

    公开(公告)号：US20190171881A1

    公开(公告)日：2019-06-06

    申请号：US16269183

    申请日：2019-02-06

    Applicant: X DEVELOPMENT LLC

    Inventor： Nareshkumar Rajkumar ,  Stefan Hinterstoisser ,  Max Bajracharya

    IPC: G06K9/00 ,  G06T1/00 ,  B25J9/16 ,  G06K9/62

    Abstract: Methods, apparatus, systems, and computer-readable media are provided for downloading targeted object recognition modules that are selected from a library of candidate targeted object recognition modules based on various signals. In some implementations, an object recognition client may be operated to facilitate object recognition for a robot. It may download targeted object recognition module(s). Each targeted object recognition module may facilitate inference of an object type or pose of an observed object. The targeted object module(s) may be selected from a library of targeted object recognition modules based on various signals, such as a task to be performed by the robot. The object recognition client may obtain vision data capturing at least a portion of an environment in which the robot operates. The object recognition client may determine, based on the vision data and the downloaded object recognition module(s), information about an observed object in the environment.

    Selectively downloading targeted object recognition modules
    19.
    发明授权
    Selectively downloading targeted object recognition modules 有权

    公开(公告)号：US10229317B2

    公开(公告)日：2019-03-12

    申请号：US15230412

    申请日：2016-08-06

    Applicant: X DEVELOPMENT LLC

    Inventor： Nareshkumar Rajkumar ,  Stefan Hinterstoisser ,  Max Bajracharya

    IPC: G06K9/00 ,  B25J9/16 ,  G06T1/00 ,  G06K9/62 ,  H04W4/60 ,  H04W4/02 ,  H04W4/80

    Abstract: Methods, apparatus, systems, and computer-readable media are provided for downloading targeted object recognition modules that are selected from a library of candidate targeted object recognition modules based on various signals. In some implementations, an object recognition client may be operated to facilitate object recognition for a robot. It may download targeted object recognition module(s). Each targeted object recognition module may facilitate inference of an object type or pose of an observed object. The targeted object module(s) may be selected from a library of targeted object recognition modules based on various signals, such as a task to be performed by the robot. The object recognition client may obtain vision data capturing at least a portion of an environment in which the robot operates. The object recognition client may determine, based on the vision data and the downloaded object recognition module(s), information about an observed object in the environment.

Patent Agency Ranking