Robotic system with object identification and handling mechanism and method of operation thereof

    公开(公告)号:US10583560B1

    公开(公告)日:2020-03-10

    申请号:US16374617

    申请日:2019-04-03

    Applicant: Mujin, Inc.

    Abstract: A robotic system includes: a control unit configured to: receive an object set including one or more object entries, wherein: the object entries correspond to source objects of an object source, each of the object entries are described by one or more object entry properties; receive sensor information representing one or more detectable object properties for detectable source objects of an object source; calculate an object match probability between the detectable source objects and the object entries based on a property correlation between the detectable object properties of the detectable source objects and the object entry properties of the object entries; generate an object identity approximation for each of the detectable source objects based on a comparison between the object match probability for each of the detectable source objects corresponding to a particular instance of the object entries; select a target object from the detectable source objects; generate an object handling strategy, for implementation by an object handling unit, to transfer the target object from the object source based on the object entry properties of the object entries corresponding to the object identity approximation; update the object set to indicate that the target object corresponding to a specific instance of the object entries has been removed from the object source; and a storage unit 204, coupled to the control unit, configured to store the object set.

    System and method of object detection based on image data

    公开(公告)号:US11288814B2

    公开(公告)日:2022-03-29

    申请号:US16909709

    申请日:2020-06-23

    Applicant: Mujin, Inc.

    Abstract: A system and method of detecting objects are provided. The method includes generating first edge information from first image data representing an object based on a first mode of image capture, generating second edge information from second image data representing the object based on a second mode of image capture, the second mode being different from the first mode, fusing the first edge information with the second edge information to generate fused edge information, generating an object detection hypothesis based on the fused edge information, and validating the object detection hypothesis based on the fused edge information, the first edge information, and/or the second edge information.

    METHOD AND COMPUTING SYSTEM FOR PROCESSING CANDIDATE EDGES

    公开(公告)号:US20210256705A1

    公开(公告)日:2021-08-19

    申请号:US16791024

    申请日:2020-02-14

    Applicant: MUJIN, INC.

    Abstract: A system and method for processing candidate edges are presented. The method may be performed when spatial structure information and 2D image information are stored. The method may include identifying, based on the spatial structure information, a 3D location that represents a corner of an object structure; identifying, based on the spatial structure information, a 3D vector that extends from the 3D location and is parallel with an edge; determining a 2D location within the 2D image information that corresponds to the 3D location; determining a 2D vector within the 2D image information that corresponds to the 3D vector; determining an edge detection region; identifying a cluster of candidate edges within the edge detection region that does not represent any object edge; identifying, as a 2D object edge, a candidate edge that is not part of the identified cluster; and performing segmentation based on the 2D object edge.

Patent Agency Ranking