利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

5 条记录 (耗时 0.022 秒)

    Hierarchical spatial representation for multimodal sensory data
    1.
    发明授权
    Hierarchical spatial representation for multimodal sensory data 有权
    多模态感觉数据的分层空间表示

    公开(公告)号：US08693729B1

    公开(公告)日：2014-04-08

    申请号：US13585356

    申请日：2012-08-14

    申请人： Paul Alex Dow ,  Deepak Khosla ,  David J Huber

    发明人： Paul Alex Dow ,  Deepak Khosla ,  David J Huber

    IPC分类号： G06T7/00 ,  B25J9/16

    CPC分类号： G06K9/00 ,  G06T7/74 ,  G06T2207/20081

    摘要： The present invention creates and stores target representations in several coordinate representations based on biologically inspired models of the human vision system. By using biologically inspired target representations a computer can be programmed for robot control without using kinematics to relate a target position in camera eyes to a target position in body or head coordinates. The robot sensors and appendages are open loop controlled to focus on the target. In addition, the invention herein teaches a scenario and method to learn the mappings between coordinate representations using existing machine learning techniques such as Locally Weighted Projection Regression.

    摘要翻译： 本发明基于人类视觉系统的生物学启发模型创建并存储几个坐标表示中的目标表示。 通过使用生物启发的目标表示，计算机可以被编程用于机器人控制，而不使用运动学来将相机眼睛中的目标位置与身体或头部坐标中的目标位置相关联。 机器人传感器和附件是开环控制的，专注于目标。 另外，本发明教导了使用现有机器学习技术（例如局部加权投影回归）来学习坐标表示之间的映射的情景和方法。

    Hierarchical spatial representation for multimodal sensory data
    2.
    发明授权
    Hierarchical spatial representation for multimodal sensory data 有权
    多模态感觉数据的分层空间表示

    公开(公告)号：US08311317B1

    公开(公告)日：2012-11-13

    申请号：US12192918

    申请日：2008-08-15

    申请人： Paul Alex Dow ,  Deepak Khosla ,  David J Huber

    发明人： Paul Alex Dow ,  Deepak Khosla ,  David J Huber

    IPC分类号： G06K9/00

    CPC分类号： G06K9/00 ,  G06T7/74 ,  G06T2207/20081

    摘要： The present invention creates and stores target representations in several coordinate representations based on biologically inspired models of the human vision system. By using biologically inspired target representations a computer can be programmed for robot control without using kinematics to relate a target position in camera eyes to a target position in body or head coordinates. The robot sensors and appendages are open loop controlled to focus on the target. In addition, the invention herein teaches a scenario and method to learn the mappings between coordinate representations using existing machine learning techniques such as Locally Weighted Projection Regression.

    摘要翻译： 本发明基于人类视觉系统的生物学启发模型创建并存储几个坐标表示中的目标表示。 通过使用生物启发的目标表示，计算机可以被编程用于机器人控制，而不使用运动学来将相机眼睛中的目标位置与身体或头部坐标中的目标位置相关联。 机器人传感器和附件是开环控制的，专注于目标。 另外，本发明教导了使用现有机器学习技术（例如局部加权投影回归）来学习坐标表示之间的映射的情景和方法。

    Method and system for computing fused saliency maps from multi-modal sensory inputs
    3.
    发明授权
    Method and system for computing fused saliency maps from multi-modal sensory inputs 有权
    用于计算多模式感觉输入的融合显着图的方法和系统

    公开(公告)号：US08396282B1

    公开(公告)日：2013-03-12

    申请号：US12262548

    申请日：2008-10-31

    申请人： David J Huber ,  Deepak Khosla ,  Paul Alex Dow

    发明人： David J Huber ,  Deepak Khosla ,  Paul Alex Dow

    IPC分类号： G06K9/00 ,  G05B15/00

    CPC分类号： G06K9/4623 ,  G06K9/629

    摘要： The present disclosure describes a fused saliency map from visual and auditory saliency maps. The saliency maps are in azimuth and elevation coordinates. The auditory saliency map is based on intensity, frequency and temporal conspicuity maps. Once the auditory saliency map is determined, the map is converted into azimuth and elevation coordinates by processing selected snippets of sound from each of four microphones arranged on a robot head to detect the location of the sound source generating the saliencies.

    摘要翻译： 本公开描述了来自视觉和听觉显着图的融合显着图。 显着图是方位角和高程坐标。 听觉显着图基于强度，频率和时间显着性图。 一旦听觉显着性图被确定，通过处理布置在机器人头上的四个麦克风中的每一个的选定的声音片段来检测产生出色的声源的位置，将地图转换成方位角和仰角坐标。

    Small gas turbine engine with unmixed exhaust
    5.
    发明授权
    Small gas turbine engine with unmixed exhaust 失效
    小型燃气涡轮发动机采用非混合排气

    公开(公告)号：US07740441B1

    公开(公告)日：2010-06-22

    申请号：US12184729

    申请日：2008-08-01

    申请人： David J Huber ,  Cheryl A Schopf ,  Jack W Wilson, Jr.

    发明人： David J Huber ,  Cheryl A Schopf ,  Jack W Wilson, Jr.

    IPC分类号： F01D25/16 ,  F04D29/049

    CPC分类号： F01D5/026 ,  F16C3/023 ,  F16C2360/23 ,  Y02T50/671 ,  Y10S29/013 ,  Y10T29/4932

    摘要： A small twin spool gas turbine engine with a bearing support arrangement in which the bearings are dampened by O-rings secured between the bearing races and the support structure, the bearings are arranged in series so that a cooling air can be passed through the bearings to prevent overheating, and the bearings are dry lubricated. The aft end of the engine includes high speed and low speed ball bearings supported with preload springs to add additional damping capability. The end bearing support assemblies form a cooling air path for the cooling fluid to flow through a passage within one of the guide vanes, through the bearings and a hole in the low pressure turbine rotor disk and out the exhaust of the engine. A snorkel tube extends into the bypass air channel drawing air for the bearings, and has a slanted opening preventing dirt particulates from entering the bearing cooling passage.

    摘要翻译： 一种具有轴承支撑装置的小型双阀芯燃气涡轮发动机，其中轴承被固定在轴承座和支撑结构之间的O形环夯实，轴承被串联布置，使得冷却空气可以穿过轴承到 防止过热，轴承进行干式润滑。 发动机的后端包括用预加载弹簧支撑的高速和低速球轴承，以增加额外的阻尼能力。 端部轴承支撑组件形成冷却空气路径，用于冷却流体流过导叶之一内的通道，通过轴承和低压涡轮转子盘中的孔并排出发动机的排气。 浮潜管延伸到用于轴承的旁路空气通道抽吸空气中，并且具有防止污物颗粒进入轴承冷却通道的倾斜开口。