公开(公告)号：US09043198B1

公开(公告)日：2015-05-26

申请号：US13782976

申请日：2013-03-01

Applicant: GOOGLE INC.

Inventor： David Black ,  Ryan Hickman

IPC: G06F17/27 ,  G06F17/21

CPC classification number: G06F17/276 ,  G06F17/273 ,  G06F17/277

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automatic text suggestion are described. One of the methods includes receiving a text item including one or more terms; determining a plurality of text strings, each text string including a matching portion and one or more suffixes, wherein the matching portion matches the text item, and the one or more suffixes are located after the matching portion; ranking the one or more suffixes based on a credibility score and a frequency score of each suffix, the credibility score indicating an estimated credibility of a source of the text string including the suffix, the frequency score indicating an estimated frequency of appearance of the suffix; and providing a group of the one or more suffixes that includes a highest ranking suffix for display as a suggestion for completing a sentence starting from the text item.

公开(公告)号：US09030501B2

公开(公告)日：2015-05-12

申请号：US14459437

申请日：2014-08-14

Applicant: Google Inc.

Inventor： Munjal Desai ,  Ryan Hickman ,  Thor Lewis ,  Damon Kohler

IPC: G09G5/00 ,  G06T3/00 ,  G01C3/08

CPC classification number: G06T3/0006 ,  G01C3/08 ,  G06T2211/428 ,  G09G5/00 ,  H04N7/185 ,  Y10S901/01

Abstract: Methods and systems for modifying a display of a field of view of a robotic device to include zoomed-in and zoomed-out views are provided. In examples, the robotic device may include a camera to capture images in a field of view of a robotic device, and distance sensors which can provide outputs that may be used to determine a distance of the robotic device to an object in the field of view of the robotic device. A display of the field of view of the robotic device can be generated, and as the distance decreases, the display can be modified to include a zoomed-in view of the object. As the distance increases, the display can be modified to include a zoomed-out view of the object. An amount of zoom of the object may be inversely proportional to the distance.

Abstract translation: 提供了用于修改机器人设备的视野的显示以包括放大和缩小视图的方法和系统。 在示例中，机器人装置可以包括用于在机器人装置的视野中捕获图像的相机以及距离传感器，所述距离传感器可以提供可用于确定机器人装置在视场中的对象的距离的输出 的机器人装置。 可以生成机器人装置的视野的显示，并且随着距离减小，可以修改显示以包括对象的放大视图。 随着距离的增加，可以对显示进行修改，以包括对象的缩小视图。 物体的变焦量可能与距离成反比。

公开(公告)号：US20140350890A1

公开(公告)日：2014-11-27

申请号：US14454655

申请日：2014-08-07

Applicant: Google Inc.

Inventor： Arshan Poursohi ,  Ryan Hickman

IPC: G01N33/00

CPC classification number: G08B21/182 ,  B25J9/161 ,  B25J9/1671 ,  G01N33/00 ,  G05B15/02 ,  G05B2219/2642 ,  G05B2219/39168 ,  G06N3/008 ,  G08B13/00 ,  G08B17/00 ,  G08B21/12

Abstract: Methods and devices are disclosed for monitoring environmental conditions in one or more environments. In one embodiment, the method includes maintaining a plurality of environmental-condition thresholds, each of which corresponds to an environmental condition and is predetermined based on data corresponding to the environmental condition that is received from a plurality of robots. The method further includes receiving from a first robot first data corresponding to a first environmental condition in a first environment. The method may still further include making a first comparison of the first data and a first environmental-condition threshold corresponding to the first environmental condition and, based on the first comparison, triggering a notification. Triggering the notification may comprise transmitting to the robot instructions to transmit the notification to at least one of a call center and a remote device.

公开(公告)号：US08848201B1

公开(公告)日：2014-09-30

申请号：US13793071

申请日：2013-03-11

Applicant: Google Inc.

Inventor： James R. Bruce ,  Ryan Hickman ,  Arshan Poursohi

IPC: G01B11/24

CPC classification number: G01B11/24 ,  G01B21/047

Abstract: Methods and systems for multi-modal three-dimensional (3D) scanning of objects are described. An example method may include receiving, from a scanning system, 3D information associated with an object having a first resolution. A region of interest of the object may be determined by a processor based on the 3D information associated with the object. Additionally, instructions for operating the scanning system to determine additional information associated with the region of interest of the object may be determined. The additional information associated with the region of interest may have a second resolution that is higher than the first resolution. The instructions may be provided to the scanning system to determine the additional information associated with the region of interest of the object.

Abstract translation: 描述了用于多模态三维（3D）扫描对象的方法和系统。 示例性方法可以包括从扫描系统接收与具有第一分辨率的对象相关联的3D信息。 对象的感兴趣区域可以由处理器基于与对象相关联的3D信息来确定。 此外，可以确定用于操作扫描系统以确定与对象的感兴趣区域相关联的附加信息的指令。 与感兴趣区域相关联的附加信息可以具有高于第一分辨率的第二分辨率。 可以向扫描系统提供指令以确定与对象的感兴趣区域相关联的附加信息。

公开(公告)号：US20130262511A1

公开(公告)日：2013-10-03

申请号：US13791182

申请日：2013-03-08

Applicant: GOOGLE INC.

Inventor： James J. Kuffner, JR. ,  James R. Bruce ,  Arshan Poursohi ,  Ryan Hickman

IPC: G06F17/30

CPC classification number: G06F17/30047 ,  G06F17/30259 ,  G06F17/30268 ,  G06T15/50 ,  G06T2215/16

Abstract: Methods and systems are provided for determining and transmitting applicable lighting information, applicable viewing perspective, and a 3D model for an object in response to a search query. An example method includes receiving, at a server, a search query regarding an object. A 3D model for the object is determined. The 3D model includes three-dimensional shape information about the object. The method also includes determining, based on a plurality of stored images of the object, at least one applicable light field and at least one applicable viewing perspective. A search query result is transmitted from the server. The search query result may include the 3D model, the applicable light field(s), and the applicable viewing perspective(s). A server and a non-transitory computer readable medium are also disclosed that could perform a similar method.

Abstract translation: 提供了用于响应于搜索查询来确定和传送可应用的照明信息，适用的观看透视图和用于对象的3D模型的方法和系统。 一种示例性方法包括在服务器处接收关于对象的搜索查询。 确定对象的3D模型。 3D模型包括关于对象的三维形状信息。 该方法还包括基于对象的多个存储的图像来确定至少一个可应用的光场和至少一个适用的观看透视图。 从服务器发送搜索查询结果。 搜索查询结果可以包括3D模型，可应用的光场和适用的观看透视图。 还公开了可以执行类似方法的服务器和非暂时计算机可读介质。

公开(公告)号：US09870435B1

公开(公告)日：2018-01-16

申请号：US14195475

申请日：2014-03-03

Applicant: Google Inc.

Inventor： Ryan Hickman ,  Arshan Poursohi ,  Thor Lewis

IPC: G06F17/50

CPC classification number: G06F17/50 ,  G01B11/2545 ,  G06F7/60 ,  G06T17/00 ,  G06T19/20 ,  G06T2210/16 ,  G06T2219/2021

Abstract: Disclosed are methods and systems for determining and displaying a simulated deformation of a 3D object data model. In one aspect, a method is disclosed that includes causing a force to be applied to an object to cause a deformation of the object and causing a plurality of reference scans of the object to be captured. The method further includes, based on the plurality of reference scans, generating a 3D object data model representing the object and, further based on the plurality of reference scans, identifying a constraint point of the 3D object data model, where the constraint point represents a point of minimum deformation of the object. The method still further includes selecting a predefined deformation model, where the predefined deformation model defines a simulated deformation, and where the simulated deformation simulates at least a portion of the deformation of the object proximate to the point of minimum deformation.

公开(公告)号：US09836483B1

公开(公告)日：2017-12-05

申请号：US14010642

申请日：2013-08-27

Applicant: Google Inc.

Inventor： Ryan Hickman ,  James J. Kuffner, Jr. ,  James R. Bruce ,  Anthony G. Francis, Jr. ,  Arshan Poursohi ,  Chaitanya Gharpure

IPC: G06F17/30

CPC classification number: G06F17/30259

Abstract: Methods and systems for comparing a 3D model of a target object to a shape-search database are provided. An example method includes using a mobile device to acquire a plurality of images of a target object, determining a 3D model based on the images, transmitting a search query that includes the 3D model, and receiving a search query result. In another example method, a server could receive a search query that includes a 3D model of an object, compare the 3D model to a shape-search database, generate a search query result based on the comparison, and transmit the search query result. The search query result could include one or more of: information regarding the target object, information regarding one or more objects similar to the target object, and a suggestion for acquiring additional images of the target object.

公开(公告)号：US09445015B2

公开(公告)日：2016-09-13

申请号：US14185477

申请日：2014-02-20

Applicant: Google Inc.

Inventor： Joel Hesch ,  Ryan Hickman ,  Johnny Lee

IPC: H04N5/262 ,  H04N5/232 ,  H04N5/225 ,  G06T15/20 ,  H04W4/02

CPC classification number: H04N5/2628 ,  G06T15/205 ,  H04N5/2258 ,  H04N5/23229 ,  H04N5/23293 ,  H04N5/2621 ,  H04N2209/047 ,  H04W4/026 ,  H04W4/027

Abstract: Example methods and systems for adjusting sensor viewpoint to a virtual viewpoint are provided. An example method may involve receiving data from a first camera; receiving data from a second camera; transforming, from the first viewpoint to a virtual viewpoint within the device, frames in a first plurality of frames based on an offset from the first camera to the virtual viewpoint; determining, in a second plurality of frames, one or more features and a movement, relative to the second viewpoint, of the one or more features; and transforming, from the second viewpoint to the virtual viewpoint, the movement of the one or more features based on an offset from the second camera to the virtual viewpoint; adjusting the transformed frames of the virtual viewpoint by an amount that is proportional to the transformed movement; and providing for display the adjusted and transformed frames of the first plurality of frames.

Abstract translation: 提供了将传感器视点调整到虚拟视点的示例性方法和系统。 示例性方法可以涉及从第一相机接收数据; 从第二相机接收数据; 基于从第一摄像机到虚拟视点的偏移，从设备内的第一视点到虚拟视点转换第一多个帧中的帧; 在第二多个帧中确定所述一个或多个特征的一个或多个特征和相对于所述第二视点的运动; 并且从第二观点向虚拟视点将基于从第二照相机的偏移到所述虚拟视点的所述一个或多个特征的移动; 将所述虚拟视点的变换帧调整与所述变换的运动成比例的量; 以及提供用于显示所述第一多个帧的已调整和变换的帧。

公开(公告)号：US09417185B1

公开(公告)日：2016-08-16

申请号：US14058949

申请日：2013-10-21

Applicant: Google Inc.

Inventor： James R. Bruce ,  Ryan Hickman ,  James J. Kuffner, Jr. ,  Arshan Poursohi

IPC: G01N21/55 ,  G06T15/04 ,  G06T15/00 ,  G06T7/40

CPC classification number: G01N21/55 ,  G01N2021/559 ,  G06T7/40 ,  G06T15/00 ,  G06T15/04

Abstract: Methods and systems for controlling light arrays to determine properties of an object are described. An example method includes causing illumination of a surface of an object from multiple illumination positions using a programmable array of lights, and receiving images from an image-capture device while the surface of the object is illuminated. For example, the programmable array of lights may be modulated to cause illumination of a portion of the surface of the object from first and second illumination positions, and a first and second image of the surface of the object captured during illumination from the first and second illumination positions respectively may be received. Subsequently, a processor may determine material information for the object based on an amount of specular reflectivity for the surface of the object and reference to a database of known amounts of specular reflectivity for a plurality of materials.

Abstract translation: 描述了用于控制光阵列以确定对象的属性的方法和系统。 示例性方法包括：使用可编程阵列阵列从多个照明位置照射物体的表面，并且在物体的表面被照亮的同时从图像捕获装置接收图像。 例如，可编程阵列的光可以被调制以使得来自第一和第二照明位置的物体表面的一部分的照明，以及在照明期间从第一和第二照明位置捕获的物体的表面的第一和第二图像 可以分别接收照明位置。 随后，处理器可以基于物体表面的镜面反射率的量并且参考多个材料的已知量的镜面反射率的数据库来确定物体的材料信息。

公开(公告)号：US20160207200A1

公开(公告)日：2016-07-21

申请号：US15085239

申请日：2016-03-30

Applicant: Google Inc.

Inventor： James J. Kuffner, JR. ,  Ryan Hickman

IPC: B25J9/16 ,  H04L29/08

CPC classification number: B25J9/1692 ,  B25J5/005 ,  B25J9/1674 ,  B62D55/075 ,  G05B2219/39413 ,  G06F9/5072 ,  H04L67/12

Abstract: Methods and systems for determining a status of a component of a device are provided. An example method includes triggering an action of a component of a device, and responsively receiving information associated with the action of the component from a sensor. The method further includes a computing system having a processor and a memory comparing the information with calibration data and determining a status of the component based on the comparison. In some examples, the calibration data may include information derived from data received from a pool of one or more devices utilizing same or similar components as the component. The determined status may include information associated with a performance of the component with respect to performances of same or similar components of the pool of devices. In one example, the device may self-calibrate the component based on the status.