知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

65 records (took 0.023 seconds)

    Simulation-in-the-loop Tuning of Robot Parameters for System Modeling and Control
    2.
    发明申请
    Simulation-in-the-loop Tuning of Robot Parameters for System Modeling and Control 有权

    公开(公告)号：US20220305646A1

    公开(公告)日：2022-09-29

    申请号：US17214810

    申请日：2021-03-27

    Applicant: Mitsubishi Electric Research Laboratories, Inc.

    Inventor： Siddarth Jain ,  Jeroen van Baar ,  Radu Ioan Corcodel ,  Alan Sullivan ,  Mouhacine Benosman

    IPC: B25J9/16 ,  B25J13/08

    Abstract: A system for parameter tuning for robotic manipulators is provided. The system includes an interface configured to receive a task specification, a plurality of physical parameters, and a plurality of control parameters, wherein the interface is configured to communicate with a real-world robot via a robot controller. The system further includes a memory to store computer-executable programs including a robot simulation module, a robot controller, and an auto-tuning module a processor, in connection with the memory. In this case, the processor is configured to acquire, in communication with the real-world robot, state values of the real-world robot, state values of the robot simulation module, simultaneously update, by use of a predetermined optimization algorithm with the auto-tuning module, an estimate of one or more of the physical, and said control parameters, and store the updated parameters.

    Apparatus and Method for Controlling a System Having Uncertainties in its Dynamics
    3.
    发明申请
    Apparatus and Method for Controlling a System Having Uncertainties in its Dynamics 有权

    公开(公告)号：US20220121188A1

    公开(公告)日：2022-04-21

    申请号：US17123701

    申请日：2020-12-16

    Applicant: Mitsubishi Electric Research Laboratories, Inc.

    Inventor： Mouhacine Benosman ,  Reazul Russel ,  Jeroen van Baar

    IPC: G05B23/02 ,  G05B17/02

    Abstract: A controller for controlling a system having uncertainties in its dynamics subject to constraints on an operation of the system is provided. The controller is configured to acquire historical data of the operation of the system, and determine, for the system in a current state, a current control action transitioning a state of the system from the current state to a next state. The current control action is determined according to a robust and constraint Markov decision process (RCMDP) that uses the historical data to optimize a performance cost of the operation of the system subject to an optimization of a safety cost enforcing the constraints on the operation, wherein a state transition for each of state and action pairs in the performance cost and the safety cost is represented by a plurality of state transitions capturing the uncertainties of the dynamics of the system.

    System and Method for Robust Optimization for Trajectory-Centric ModelBased Reinforcement Learning
    4.
    发明申请
    System and Method for Robust Optimization for Trajectory-Centric ModelBased Reinforcement Learning 有权

    公开(公告)号：US20210178600A1

    公开(公告)日：2021-06-17

    申请号：US16712329

    申请日：2019-12-12

    Applicant: Mitsubishi Electric Research Laboratories, Inc.

    Inventor： Devesh Jha ,  Patrik Kolaric ,  Arvind Raghunathan ,  Mouhacine Benosman ,  Diego Romeres

    IPC: B25J9/16 ,  G06N20/00 ,  G06N3/04

    Abstract: A controller for optimizing a local control policy of a system for trajectory-centric reinforcement learning is provided. The controller includes performing steps of learning a stochastic predictive model for the system using a set of data collected during trial and error experiments performed using an initial random control policy, estimating mean prediction and uncertainty associated, determining a local set of deviations of the system using the learned stochastic system model, from a nominal system state upon use of a control input at a current time-step, determining a system state with a worst-case deviation, determining a gradient of the robustness constraint, providing and solving a robust policy optimization problem using non-linear programming to obtain system trajectory and stabilizing local policy simultaneously, updating the control data according to the solved optimization problem, and output the updated control data via the interface.

    Semi-Active Feedback Control of Sway of Cables in Elevator System
    7.
    发明申请
    Semi-Active Feedback Control of Sway of Cables in Elevator System 有权
    电梯系统中电缆摆动的半主动反馈控制

    公开(公告)号：US20160272463A1

    公开(公告)日：2016-09-22

    申请号：US14658607

    申请日：2015-03-16

    Applicant: Mitsubishi Electric Research Laboratories, Inc.

    Inventor： Mouhacine Benosman

    IPC: B66B5/02 ,  G06F17/16 ,  B66B7/12 ,  G05B15/02 ,  B66B5/00 ,  B66B9/00

    CPC classification number: G06F17/16 ,  B66B5/0018 ,  B66B7/06

    Abstract: A method controls an operation of an elevator system including an elevator car moving within an elevator shaft and at least one elevator cable connected to the elevator car and the elevator shaft. The method determines, during the operation of the elevator system, a velocity of a sway of the elevator cable and modifies, in response to the determining, a damping coefficient of a semi-active damper actuator connected to the elevator cable according to a function of the velocity of the sway.

    Abstract translation: 一种方法控制包括在电梯井内移动的电梯轿厢和连接到电梯轿厢和电梯井的至少一个电梯电缆的电梯系统的操作。 该方法在电梯系统的操作期间确定升降机电缆的摇摆的速度，并且响应于该确定而修改连接到电梯电缆的半主动阻尼器致动器的阻尼系数，该阻尼系数根据 摇摆的速度。

    Finite time power control for smart-grid distributed system
    9.
    发明授权
    Finite time power control for smart-grid distributed system 有权
    智能电网分布式系统的有限时间功率控制

    公开(公告)号：US09419437B2

    公开(公告)日：2016-08-16

    申请号：US14134075

    申请日：2013-12-19

    Applicant: Mitsubishi Electric Research Laboratories, Inc.

    Inventor： Mouhacine Benosman ,  Evangelos Polymeneas

    IPC: G05B15/02 ,  H02J3/38 ,  H02J3/48 ,  H02J3/50 ,  H02J13/00 ,  G06Q50/06 ,  H02J3/00

    CPC classification number: H02J3/381 ,  G06Q50/06 ,  H02J3/48 ,  H02J3/50 ,  H02J13/0006 ,  H02J2003/003 ,  Y02E10/763 ,  Y02E40/72 ,  Y02E40/76 ,  Y04S10/12 ,  Y04S10/54 ,  Y04S10/545

    Abstract: A distributed energy resource (DER) exchanges with each neighboring DER portions of the total demand for power accumulated by the DER and each neighboring DER and portions of a total capability of the network to generate the total power accumulated by the DER and each neighboring DER before each communication step. The DER updates the portion of the total demand for power and total capability accumulated by the DER using the portions of the total demand and the portions of the total capability received from the neighboring DERs. After the fixed number of communication steps, the DER accumulates the total demand for power and the total capability of the network and generates an amount of the power as a product of the total demand for the power and a ratio of a maximum capability of the DER to generate the power and the total capability of the network.

    Abstract translation: 分布式能源（DER）与由DER和每个相邻DER所累积的总功率需求的每个相邻DER部分交换，以及网络的总能力的部分，以产生由DER和每个相邻DER累积的总功率 每个沟通步骤。 DER使用总需求的部分和从相邻DER接收到的总能力的部分来更新DER所累积的功率和总能力的总需求的部分。 在固定数量的通信步骤之后，DER累积了对电力的总需求和网络的总能力，并且产生作为电力的总需求和DER的最大能力的比率的乘积的功率量 以产生电力和网络的总体能力。

    Controlling Sway of Elevator Rope Using Movement of Elevator Car
    10.
    发明申请
    Controlling Sway of Elevator Rope Using Movement of Elevator Car 有权
    使用电梯车的运动控制电梯绳的摇摆

    公开(公告)号：US20150008075A1

    公开(公告)日：2015-01-08

    申请号：US13933290

    申请日：2013-07-02

    Applicant: Mitsubishi Electric Corporation ,  Mitsubishi Electric Research Laboratories, Inc.

    Inventor： Mouhacine Benosman ,  Daiki Fukui ,  Seiji Watanabe ,  Daisuke Nakazawa

    IPC: B66B5/02

    CPC classification number: B66B7/06

    Abstract: A method reduces a sway of an elevator rope supporting an elevator car within an elevator system using an elevator sheave. The method controls, using a movement of the elevator sheave, a tension of the elevator rope according to a control law of the tension of the elevator rope between a first point and a second point. The first point is associated with a contact of the elevator rope with the elevator sheave. The second point is associated with a contact of the elevator rope with the elevator car or a counterweight of the elevator car. The control law is a function of one or combination of a relative position, a relative velocity and a relative acceleration between the first and the second points.

    Abstract translation: 一种方法减少了使用电梯滑轮在电梯系统内支撑电梯轿厢的电梯绳索的摆动。 该方法根据电梯绳索在第一点和第二点之间的张力的控制规律来控制电梯滑轮的运动，电梯绳索的张​​力。 第一点与电梯绳索与电梯滑轮的接触有关。 第二点与电梯绳索与电梯轿厢或电梯轿厢的配重的接触相关联。 控制律是第一和第二点之间的相对位置，相对速度和相对加速度之一或组合的函数。

Patent Agency Ranking