Database for a coordinate system of an aircraft

    公开(公告)号:US11995056B2

    公开(公告)日:2024-05-28

    申请号:US18447300

    申请日:2023-08-09

    IPC分类号: G06F16/00 G06F16/22 B64F5/40

    CPC分类号: G06F16/22 B64F5/40

    摘要: Techniques are described herein for generating a database. A method can include receiving a first value associated with a physical element of a target object and obtained during a performance of a first stage of a robot task, and a second value associated with the physical element and obtained during a second stage, wherein the first and second value describe a same characteristic of the physical element and are represented in a target object coordinate system. A third value associated with a tool of a robot and obtained during a third stage can be received, wherein the third value is represented in the robot coordinate system. A first data structure can be generated, wherein the first data structure comprises the first, second, and third value. The first data structure can be associated with a second data structure, wherein the second data structure comprises a fourth value identifying the target object.

    DATABASE FOR A COORDINATE SYSTEM OF AN AIRCRAFT

    公开(公告)号:US20240054116A1

    公开(公告)日:2024-02-15

    申请号:US18447300

    申请日:2023-08-09

    IPC分类号: G06F16/22

    CPC分类号: G06F16/22 B64F5/40

    摘要: Techniques are described herein for generating a database. A method can include receiving a first value associated with a physical element of a target object and obtained during a performance of a first stage of a robot task, and a second value associated with the physical element and obtained during a second stage, wherein the first and second value describe a same characteristic of the physical element and are represented in a target object coordinate system. A third value associated with a tool of a robot and obtained during a third stage can be received, wherein the third value is represented in the robot coordinate system. A first data structure can be generated, wherein the first data structure comprises the first, second, and third value. The first data structure can be associated with a second data structure, wherein the second data structure comprises a fourth value identifying the target object.

    Auto-locating and autonomous operation data storage

    公开(公告)号:US11807400B1

    公开(公告)日:2023-11-07

    申请号:US18339199

    申请日:2023-06-21

    IPC分类号: B64F5/40 G07C5/00 G07C5/08

    CPC分类号: B64F5/40 G07C5/008 G07C5/085

    摘要: Techniques for auto-locating and autonomous operation data storage are disclosed. An example method can include storing a representation of an aircraft in a data storage of the computing system. The representation and instructions for performing a first operation on the aircraft can be transmitted to a first robot. The first robot can be configured to identify the aircraft based on a first feature of the representation. The method can further include receiving sensor data. The method can further include transmitting the sensor data to an analysis service to identify a state of a part of the aircraft. The method can further include storing the analysis in the data storage. The method can further include generating second instructions for performing a second operation on the aircraft based on the analysis and the representation stored in the data storage.

    Movable gantry system configured to interface with jigs of different sizes

    公开(公告)号:US12013677B2

    公开(公告)日:2024-06-18

    申请号:US18351447

    申请日:2023-07-12

    发明人: William Wilder

    IPC分类号: G05B19/19

    CPC分类号: G05B19/19 G05B2219/40293

    摘要: A movable gantry system is configured to interface with jigs of different types or sizes and/or with different positions of a same jig and/or to perform operations on different parts mounted in such jigs. To do so, the movable gantry system includes an end effector, a gantry, and a computing system. The end effector is mounted within the gantry and provides at least rotational movement to perform operations on a part. The gantry is movable and interfaces with a jig holding the part. Further, the gantry provides translational movement to the end effector. The computing system identifies the gantry and the part and controls the gantry and the end effector, thereby facilitating the operations on the part. The computing system stores, in a data store, information about an operation upon performed by the end effector after a datuming process based translational data and on rotational data.

    AUTOMATICALLY IDENTIFYING LOCATIONS TO APPLY SEALANT AND APPLYING SEALANT TO A TARGET OBJECT

    公开(公告)号:US20240116181A1

    公开(公告)日:2024-04-11

    申请号:US18478881

    申请日:2023-09-29

    IPC分类号: B25J9/16 B25J15/00

    摘要: Aspects of the disclosure are directed towards generating a trajectory for use by a robot to perform an operation on a target object. A method includes a robot instructed to traverse a surface of the target object from the starting position and obtain sensor input from a sensor system of the robot using a first trajectory specified by a CAD file for the target object. Sensor input that includes a first height to the target object, a width of the seam, and a depth of the seam may be received. A second trajectory may be generated for traversing the surface of the target object and that modifies the first trajectory based on the sensor input. The robot may be instructed to move to the starting position and traverse the surface of the target object using the second trajectory and apply a sealant to the seam.

    Training of artificial intelligence model

    公开(公告)号:US11911921B1

    公开(公告)日:2024-02-27

    申请号:US18447244

    申请日:2023-08-09

    IPC分类号: B25J9/16 G06T7/70

    摘要: Aspects of the disclosure are directed towards artificial intelligence-based modeling of target objects, such as aircraft parts. In an example, a system initially trains a machine learning (ML) model based on synthetic images generated based on multi-dimensional representation of target objects. The same system or a different system subsequently further trains the ML model based on actual images generated by cameras positioned by robots relative to target objects. The ML model can be used to process an image generated by a camera positioned by a robot relative to a target object based on a multi-dimensional representation of the target object. The output of the ML model can indicate, for a detected target, position data, a target type, and/or a visual inspection property. This output can then be used to update the multi-dimensional representation, which is then used to perform robotics operations on the target object.

    TRAINING OF ARTIFICIAL INTELLIGENCE MODEL
    9.
    发明公开

    公开(公告)号:US20240051149A1

    公开(公告)日:2024-02-15

    申请号:US18447244

    申请日:2023-08-09

    IPC分类号: B25J9/16

    摘要: Aspects of the disclosure are directed towards artificial intelligence-based modeling of target objects, such as aircraft parts. In an example, a system initially trains a machine learning (ML) model based on synthetic images generated based on multi-dimensional representation of target objects. The same system or a different system subsequently further trains the ML model based on actual images generated by cameras positioned by robots relative to target objects. The ML model can be used to process an image generated by a camera positioned by a robot relative to a target object based on a multi-dimensional representation of the target object. The output of the ML model can indicate, for a detected target, position data, a target type, and/or a visual inspection property. This output can then be used to update the multi-dimensional representation, which is then used to perform robotics operations on the target object.