COMPUTER-IMPLEMENTED METHOD FOR REPEATEDLY COMPUTING CONTROL INPUT FOR CONTROL OF SYSTEM ACCORDING TO OBJECTIVES

    公开(公告)号:US20240329612A1

    公开(公告)日:2024-10-03

    申请号:US18616107

    申请日:2024-03-25

    IPC分类号: G05B13/04

    CPC分类号: G05B13/048

    摘要: The present invention provides a computer-implemented method for repeatedly computing a control input for a control of a system according to objectives. The method comprises computing, at a current time step, the control input according to the objectives using one or more Pareto fronts that were generated for computing, at one or more respective time steps before the current time step, the control input according to the objectives. The present invention further provides a data processing apparatus comprising means for carrying out the aforementioned method; and a computer-readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the aforementioned method.

    Method and system for verifying vehicle usage data

    公开(公告)号:US12094262B2

    公开(公告)日:2024-09-17

    申请号:US16942911

    申请日:2020-07-30

    摘要: A vehicle transmits vehicle data to an observer entity when the vehicle and the observer entity are in proximity. The vehicle data includes unique vehicle identification information; proximity is defined by an upper threshold for a distance between the vehicle and the observer entity. The observer entity adds data to the vehicle data, the added data including an indication of a position of the observer entity and a time stamp indicating a time of reception of the vehicle data to generate joint data. The joint data is transmitted to an external database and the aforementioned steps are repeated. From the added data a usage estimation value is calculated which is a measure for usage of the vehicle and which is compared with the vehicle usage data retrieved from the vehicle. Information on validity of the vehicle usage data based on the comparison result is generated and output.

    ENERGY MANAGEMENT SYSTEM FOR AUTONOMOUS WORK ROBOTS

    公开(公告)号:US20240262228A1

    公开(公告)日:2024-08-08

    申请号:US18427744

    申请日:2024-01-30

    发明人: Nils Einecke

    IPC分类号: B60L53/36

    CPC分类号: B60L53/36

    摘要: The present invention relates to a method for determining a schedule for charging an energy storage device (13) of an autonomous work robot (1). The method comprises a step (S1) of acquiring a work schedule of the autonomous work robot and a step (S3) of determining the charging schedule based on the work schedule in order to improve a cost function that is optimal when an optimal amount of work time within the work schedule is achieved.

    WEED CONTROL SYSTEM
    5.
    发明公开
    WEED CONTROL SYSTEM 审中-公开

    公开(公告)号:US20240206456A1

    公开(公告)日:2024-06-27

    申请号:US18515198

    申请日:2023-11-20

    IPC分类号: A01M21/02 A01D43/14

    摘要: A weed control system includes an autonomous work device, and the autonomous work device includes driving means configured to move the autonomous work device, sensor means configured acquire a sensor signal from the environment of the autonomous device, and a control circuit configured to control the driving means to navigate the autonomous work device in the environment. The weed control system includes at least one disposable releasable shading plate arranged on a release mechanism of the autonomous work device. The control circuit is configured to detect plants in the environment based on the acquired sensor signal, to determine whether a detected plant is a target plant, and in case a detected plant is a target plant, to control the release mechanism to release the releasable shading plate onto the location of the detected target plant.

    Social interaction opportunity detection method and system

    公开(公告)号:US11784961B2

    公开(公告)日:2023-10-10

    申请号:US17084648

    申请日:2020-10-30

    摘要: A method and corresponding system for improving an interaction process in a social network for a user with at least one other person is provided. The method comprises a step of, in a training phase, acquiring sensor data on at least a user state and interaction data on a social interaction of a human person with the at least one other person. The acquired sensor data and the interaction data is then analyzed in order to generate classifier data from the acquired sensor data and the acquired interaction data. In a subsequent application phase, the method acquires current sensor data on at least the user state of the at least one other person, predicts an interaction score for the user based on the acquired current sensor data and the classifier data, and generates an interaction identifier for the user for an interaction with the at least one other person in the social network based on the predicted interaction score.

    Simulating task performance of virtual characters

    公开(公告)号:US11752623B2

    公开(公告)日:2023-09-12

    申请号:US17216702

    申请日:2021-03-30

    发明人: Michael Gienger

    IPC分类号: B25J9/16 G05B17/02

    摘要: A method and simulation system for controlling at least one effector trajectory for solving a predefined task by at least one virtual effector. The method includes acquiring a sequence of postures to modify at least one of a contact constraint topology and an object constraint topology, generating a set of constraint equations based on at least one of the modified contact constraint topology and the modified object constraint topology, performing constraint relaxation on the generated set of constraint equations to generate a task description including the relaxed set of constraint equations, generating the effector trajectory by applying a trajectory generation algorithm on the generated task description, performing an inverse kinematics algorithm on the generated effector trajectory for generating a control signal, outputting the control signal to an output device, and generating, by the output device, image information displaying the effector trajectory of the virtual effector based on the control signal.

    CONTROLLING AN AUTONOMOUS WORKING DEVICE BASED ON PHYSICAL INTERACTION

    公开(公告)号:US20220184801A1

    公开(公告)日:2022-06-16

    申请号:US17120283

    申请日:2020-12-14

    摘要: An autonomous working device comprises at least one sensor configured to generate a sensor signal based on a physical interaction of the autonomous working device with a physical entity, at least one actuator configured to perform a working task, and a controller configured to generate a control signal for controlling the actuator. The controller is configured to evaluate the sensor signal, to determine a pattern of a physical interaction of the autonomous working device with a person and to generate the control signal based on the determined pattern of a physical interaction.

    INTERACTIVE REMINDER COMPANION
    10.
    发明申请

    公开(公告)号:US20220139200A1

    公开(公告)日:2022-05-05

    申请号:US17084651

    申请日:2020-10-30

    摘要: The present disclosure relates to a system for reminding a person to perform an activity. The system comprise a robot configured to carry out different behaviors, wherein the activity and its corresponding trigger condition are set by a user and the system selects, from the different behaviors, a first behavior assigned to the activity, senses the person, determines, based on the sensors information, whether or not the activity is performed by the person in accordance with the trigger condition. The robot carries out the selected behavior if the activity is not performed by the person in accordance with the trigger condition, wherein after or during the selected behavior is carried out, an activity of the person is determined based on the information derived from the sensors to select a second behavior from the different behaviors.