Device and method for monitoring a system

    公开(公告)号:US11900223B2

    公开(公告)日:2024-02-13

    申请号:US16722845

    申请日:2019-12-20

    CPC classification number: G06N20/00 G05B19/425 G05B23/0221 G06N5/04 G01M13/045

    Abstract: A portable real-time system monitoring device is advantageously capable of autonomously learning the normal behavior of any system and of alerting the user or taking other action when the system becomes unpredictable or otherwise undesirable. No prior knowledge about the system is needed by the device. This is because the device uses a combination of machine learning and statistical process control to autonomously develop its own model of the monitored system and then autonomously monitor the system for unexpected behavior. Therefore, without any prior analysis or model creation, it can be deployed on any system, and it can be reused on any other system after it has been reset. The advantageous device of the disclosed and claimed concept performs this function in either real time or near real-time.

    Automatic path generation device
    5.
    发明授权

    公开(公告)号:US11433537B2

    公开(公告)日:2022-09-06

    申请号:US16458193

    申请日:2019-07-01

    Abstract: An automatic path generation device includes a preprocessing unit creating teacher data based on a temporary motion path which is a motion path between a plurality of motion points where a robot moves and which is automatically generated with a motion planning algorithm and an actual motion path which is a motion path between the motion points and which is created by a skilled worker and a motion path learning unit generating a learned model which has learned a difference between the temporary motion path and the actual motion path with teacher data created by the preprocessing unit.

    Systems, apparatus, and methods for robot swarm coordination

    公开(公告)号:US11137746B2

    公开(公告)日:2021-10-05

    申请号:US16703290

    申请日:2019-12-04

    Abstract: Systems, apparatus, and methods to coordinate a robot swarm include an analyzer to create a planning message based on data associated with a first bot and a second bot. The planning message is communicated to the swarm from a first source. In addition, a scheduler issues a first assignment of a first operation slot and a first role to the first bot based on the planning message, issues a second assignment of a second operation slot and a second role to the second bot based on the planning message, and creates a decision message including the first assignment and the second assignment. The decision message is communicated to the swarm from a second source different than the first source.

    Robot, robot system, and method for setting coordinate system of robot

    公开(公告)号:US10935968B2

    公开(公告)日:2021-03-02

    申请号:US16168172

    申请日:2018-10-23

    Abstract: A robot includes a robot control unit configured to control an operation of a robot, wherein the robot control unit is configured to set a coordinate system of the robot installed on a reference flat surface using measurement results of at least position coordinates in a vertical direction of three or more measurement points on the reference flat surface on which the robot is installed and measurement results of position coordinates of a plurality of reference reflection portions provided on a base portion of the robot.

    Controller and machine learning device
    10.
    发明授权

    公开(公告)号:US10668619B2

    公开(公告)日:2020-06-02

    申请号:US15995384

    申请日:2018-06-01

    Inventor: Tetsuji Ueda

    Abstract: A machine learning device of a controller observes, as state variables expressing a current state of an environment, teaching position compensation amount data indicating a compensation amount of a teaching position in control of a robot according to the teaching position and data indicating a disturbance value of each of the motors of the robot in the control of the robot, and acquires determination data indicating an appropriateness determination result of the disturbance value of each of the motors of the robot in the control of the robot. Then, the machine learning device learns the compensation amount of the teaching position of the robot in association with the motor disturbance value data by using the observed state variables and the determination data.

Patent Agency Ranking