利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

44 条记录 (耗时 0.206 秒)

    Trainable modular robotic apparatus and methods
    1.
    发明授权
    Trainable modular robotic apparatus and methods 有权
    可训练的模块化机器人装置和方法

    公开(公告)号：US09533413B2

    公开(公告)日：2017-01-03

    申请号：US14209826

    申请日：2014-03-13

    申请人： Brain Corporation

    发明人： Eugene Izhikevich ,  Dimitry Fisher ,  Jean-Baptiste Passot ,  Heathcliff Hatcher ,  Vadim Polonichko

    IPC分类号： B25J9/16 ,  G06N99/00 ,  G06N3/00 ,  B25J13/08 ,  A63H3/20 ,  G06N3/04

    CPC分类号： B25J9/163 ,  A63H3/20 ,  B25J9/1694 ,  B25J13/08 ,  G06N3/008 ,  G06N3/049 ,  G06N99/005 ,  Y10S901/02 ,  Y10S901/04 ,  Y10S901/09 ,  Y10S901/50

    摘要： Apparatus and methods for a modular robotic device with artificial intelligence that is receptive to training controls. In one implementation, modular robotic device architecture may be used to provide all or most high cost components in an autonomy module that is separate from the robotic body. The autonomy module may comprise controller, power, actuators that may be connected to controllable elements of the robotic body. The controller may position limbs of the toy in a target position. A user may utilize haptic training approach in order to enable the robotic toy to perform target action(s). Modular configuration of the disclosure enables users to replace one toy body (e.g., the bear) with another (e.g., a giraffe) while using hardware provided by the autonomy module. Modular architecture may enable users to purchase a single AM for use with multiple robotic bodies, thereby reducing the overall cost of ownership.

    摘要翻译： 具有接受训练控制的人造智能的模块化机器人装置的装置和方法。 在一个实现中，模块化机器人设备架构可以用于在与机器人主体分离的自主模块中提供全部或最高成本的组件。 自主模块可以包括可以连接到机器人身体的可控元件的控制器，电源，致动器。 控制器可将玩具的四肢定位在目标位置。 用户可以利用触觉训练方法，以使机器人玩具能够执行目标动作。 本公开的模块化配置使得用户可以在使用由自主模块提供的硬件的同时，用另一个（例如，长颈鹿）来替换一个玩具体（例如熊）。 模块化架构可以使用户能够购买单个AM以用于多个机器人体，从而降低总拥有成本。

    Apparatus and methods for backward propagation of errors in a spiking neuron network
    2.
    发明授权
    Apparatus and methods for backward propagation of errors in a spiking neuron network 有权
    尖峰神经元网络误差反向传播的装置和方法

    公开(公告)号：US09489623B1

    公开(公告)日：2016-11-08

    申请号：US14054366

    申请日：2013-10-15

    申请人： Brain Corporation

    发明人： Oleg Sinyavskiy ,  Vadim Polonichko

    IPC分类号： G06N3/08 ,  B25J9/16

    CPC分类号： G06N3/084 ,  B25J9/163 ,  G06N3/008 ,  G06N3/0445 ,  G06N3/049 ,  G06N3/063 ,  Y10S901/50

    摘要： Apparatus and methods for developing robotic controllers comprising parallel networks. In some implementations, a parallel network may comprise at least first and second neuron layers. The second layer may be configured to determine a measure of discrepancy (error) between a target network output and actual network output. The network output may comprise control signal configured to cause a task execution by the robot. The error may be communicated back to the first neuron layer in order to adjust efficacy of input connections into the first layer. The error may be encoded into spike latency using linear or nonlinear encoding. Error communication and control signal provision may be time multiplexed so as to enable target action execution. Efficacy associated with forward and backward/reverse connections may be stored in individual arrays. A synchronization mechanism may be employed to match forward/reverse efficacy in order to implement plasticity.

    摘要翻译： 用于开发包括并联网络的机器人控制器的装置和方法。 在一些实现中，并行网络可以包括至少第一和第二神经元层。 第二层可以被配置为确定目标网络输出和实际网络输出之间的差异（误差）的度量。 网络输出可以包括被配置为导致机器人执行任务的控制信号。 该误差可以被传送回第一神经元层，以便调节输入连接到第一层的功效。 可以使用线性或非线性编码将误差编码为尖峰等待时间。 错误通信和控制信号提供可以被时分复用以便能够执行目标动作执行。 与前向和后向/反向连接相关联的功效可以存储在单独的阵列中。 为了实现可塑性，可以采用同步机制来匹配正向/反向效能。

    Trainable modular robotic methods
    3.
    发明授权
    Trainable modular robotic methods 有权
    可训练的模块化机器人方法

    公开(公告)号：US09364950B2

    公开(公告)日：2016-06-14

    申请号：US14209578

    申请日：2014-03-13

    申请人： Brain Corporation

    发明人： Eugene Izhikevich ,  Dimitry Fisher ,  Jean-Baptiste Passot ,  Heathcliff Hatcher ,  Vadim Polonichko

    IPC分类号： G05B19/18 ,  B25J9/00 ,  G06N99/00 ,  B25J13/00 ,  B25J9/10 ,  A63H29/22 ,  A63H30/04

    CPC分类号： B25J9/0081 ,  A63H29/22 ,  A63H30/04 ,  B25J9/104 ,  B25J13/00 ,  G06N99/005 ,  Y10T74/20305 ,  Y10T74/20311 ,  Y10T74/20317

    摘要： Apparatus and methods for a modular robotic device with artificial intelligence that is receptive to training controls. In one implementation, modular robotic device architecture may be used to provide all or most high cost components in an autonomy module that is separate from the robotic body. The autonomy module may comprise controller, power, actuators that may be connected to controllable elements of the robotic body. The controller may position limbs of the toy in a target position. A user may utilize haptic training approach in order to enable the robotic toy to perform target action(s). Modular configuration of the disclosure enables users to replace one toy body (e.g., the bear) with another (e.g., a giraffe) while using hardware provided by the autonomy module. Modular architecture may enable users to purchase a single AM for use with multiple robotic bodies, thereby reducing the overall cost of ownership.

    摘要翻译： 具有接受训练控制的人造智能的模块化机器人装置的装置和方法。 在一个实现中，模块化机器人设备架构可以用于在与机器人主体分离的自主模块中提供全部或最高成本的组件。 自主模块可以包括可以连接到机器人身体的可控元件的控制器，电源，致动器。 控制器可将玩具的四肢定位在目标位置。 用户可以利用触觉训练方法，以使机器人玩具能够执行目标动作。 本公开的模块化配置使得用户可以在使用由自主模块提供的硬件的同时，用另一个（例如，长颈鹿）来替换一个玩具体（例如熊）。 模块化架构可以使用户能够购买单个AM以用于多个机器人体，从而降低总拥有成本。

    SPOOFING REMOTE CONTROL APPARATUS AND METHODS
    4.
    发明申请
    SPOOFING REMOTE CONTROL APPARATUS AND METHODS 有权
    SPOOFING远程控制装置和方法

    公开(公告)号：US20150283701A1

    公开(公告)日：2015-10-08

    申请号：US14244892

    申请日：2014-04-03

    申请人： BRAIN CORPORATION

    发明人： Eugene M. Izhikevich ,  Patryk Laurent ,  Vadim Polonichko

    IPC分类号： B25J9/16

    CPC分类号： G06N3/008 ,  G05D1/0022 ,  G05D1/0088 ,  G05D1/0246 ,  G05D2201/02 ,  G06N3/049 ,  G06N99/005 ,  Y10S901/01 ,  Y10S901/47

    摘要： Robotic devices may be operated by users remotely. A learning controller apparatus may detect remote transmissions comprising user control instructions. The learning apparatus may receive sensory input conveying information about robot's state and environment (context). The learning apparatus may monitor one or more wavelength (infrared light, radio channel) and detect transmissions from user remote control device to the robot during its operation by the user. The learning apparatus may be configured to develop associations between the detected user remote control instructions and actions of the robot for given context. When a given sensory context occurs, the learning controller may automatically provide control instructions to the robot that may be associates with the given context. The provision of control instructions to the robot by the learning controller may obviate the need for user remote control of the robot thereby enabling autonomous operation by the robot.

    摘要翻译： 机器人设备可以由用户远程操作。 学习控制器装置可以检测包括用户控制指令的远程传输。 学习装置可以接收关于机器人的状态和环境（上下文）的感官输入。 学习装置可以监视一个或多个波长（红外光，无线电信道），并且在用户操作期间检测从用户遥控装置到机器人的传输。 学习装置可以被配置为在给定的上下文之间发展检测到的用户远程控制指令和机器人的动作之间的关联。 当发生给定的感觉上下文时，学习控制器可以自动向可能与给定上下文相关联的机器人提供控制指令。 通过学习控制器向机器人提供控制指令可以避免用户对机器人的远程控制的需要，从而实现机器人的自主操作。

    Apparatus and methods for distance estimation using multiple image sensors
    5.
    发明授权
    Apparatus and methods for distance estimation using multiple image sensors 有权

    公开(公告)号：US10989521B2

    公开(公告)日：2021-04-27

    申请号：US16214730

    申请日：2018-12-10

    申请人： Brain Corporation

    发明人： Micah Richert ,  Marius Buibas ,  Vadim Polonichko

    IPC分类号： G01B11/14 ,  G06T7/593 ,  H04N19/51

    摘要： Data streams from multiple image sensors may be combined in order to form, for example, an interleaved video stream, which can be used to determine distance to an object. The video stream may be encoded using a motion estimation encoder. Output of the video encoder may be processed (e.g., parsed) in order to extract motion information present in the encoded video. The motion information may be utilized in order to determine a depth of visual scene, such as by using binocular disparity between two or more images by an adaptive controller in order to detect one or more objects salient to a given task. In one variant, depth information is utilized during control and operation of mobile robotic devices.

    APPARATUS AND METHODS FOR PROGRAMMING AND TRAINING OF ROBOTIC HOUSEHOLD APPLIANCES
    6.
    发明申请
    APPARATUS AND METHODS FOR PROGRAMMING AND TRAINING OF ROBOTIC HOUSEHOLD APPLIANCES 审中-公开

    公开(公告)号：US20190380551A1

    公开(公告)日：2019-12-19

    申请号：US16454199

    申请日：2019-06-27

    申请人： Brain Corporation

    发明人： Botond Szatmary ,  Vadim Polonichko

    IPC分类号： A47L9/28 ,  G06N3/00 ,  G05D1/02 ,  A47L9/00

    摘要： Apparatus and methods for training and operating of robotic appliances. Robotic appliance may be operable to clean user premises. The user may train the appliance to perform cleaning operations in constrained areas. The appliance may be configured to clean other area of the premises automatically. The appliance may perform premises exploration and/or determine map of the premises. The appliance may be provided priority information associated with areas of the premises. The appliance may perform cleaning operations in order of the priority. Robotic vacuum cleaner appliance may be configured for safe cable operation wherein the controller may determine one or more potential obstructions (e.g., a cable) along operating trajectory. Upon approaching the cable, the controller may temporarily disable brushing mechanism in order to prevent cable damage.