公开(公告)号：US20110178669A1

公开(公告)日：2011-07-21

申请号：US13121995

申请日：2009-08-25

Applicant: Shoji Tanaka ,  Tsuyoshi Nakano

Inventor： Shoji Tanaka ,  Tsuyoshi Nakano

IPC: G05D1/02

CPC classification number: G05D1/0088 ,  G05D1/024 ,  G05D1/0272 ,  G05D1/0274 ,  G05D2201/0207

Abstract: An electronic controller defining an autonomous mobile device a self-location estimation unit to estimate a self-location based on a local map that is created according to distance/angle information relative to an object in the vicinity and the travel distance of an omni wheel, an environmental map creation unit to create an environmental map of a mobile area based on the self-location and the local map during the guided travel with using a joystick, a registration switch to register the self-location of the autonomous mobile device as the position coordinate of the setting point when the autonomous mobile device reaches a predetermined setting point during the guided travel, a storage unit to store the environmental map and the setting point, a route planning unit to plan the travel route by using the setting point on the environmental map stored in the storage unit, and a travel control unit to control the autonomous mobile device to autonomously travel along the travel route.

Abstract translation: 一种定义自主移动设备的自动定位估计单元的电子控制器，用于基于根据距离/角度信息相对于所述附近的物体和全方向行驶距离而产生的局部地图来估计自身位置， 环境地图创建单元，用于使用操纵杆在导航行进期间基于自身位置和局部地图创建移动区域的环境地图;登记开关，用于将自主移动设备的自身位置注册为位置 在自动移动装置在导航行驶期间到达预定设定点时的设定点的坐标，存储环境地图和设定点的存储单元，通过使用环境设定点来规划行驶路线的路线规划单元 映射存储在存储单元中，以及行驶控制单元，用于控制自主移动设备沿着行进路线自主行进。

公开(公告)号：US07912633B1

公开(公告)日：2011-03-22

申请号：US11606775

申请日：2006-11-30

Applicant: Jeanne Dietsch ,  William Kennedy ,  Matthew LaFary

Inventor： Jeanne Dietsch ,  William Kennedy ,  Matthew LaFary

IPC: G06G7/78

CPC classification number: G01C21/20 ,  G05D1/024 ,  G05D1/0261 ,  G05D1/0272 ,  G05D1/0274 ,  G05D1/0278 ,  G05D2201/0207

Abstract: A method for mobile autonomous updating of GIS maps is provided. In the method, an autonomous mobile data collecting platform is provided with a map identifying one or more GIS features. The platform has at least one data collecting sensor for collecting data for at least one of the GIS features and patrols at least a portion of a region included in the map while updating its GIS position as it patrols. The autonomous mobile data collecting platform applies the at least one data collecting sensor during patrolling to collect data for at least one of the GIS features and updates the GIS map to reflect differential data collected for at least one GIS feature.

Abstract translation: 提供了一种移动自动更新GIS地图的方法。 在该方法中，自主移动数据收集平台具有识别一个或多个GIS特征的地图。 该平台具有至少一个数据收集传感器，用于收集GIS特征中的至少一个的数据，并且在巡视时更新其GIS位置的同时巡视包含在地图中的区域的至少一部分。 自主移动数据收集平台在巡逻期间应用至少一个数据收集传感器以收集至少一个GIS特征的数据，并更新GIS地图以反映为至少一个GIS特征收集的差分数据。

公开(公告)号：US20110004366A1

公开(公告)日：2011-01-06

申请号：US12497160

申请日：2009-07-02

Applicant: Jan Becker ,  Soeren Kammel ,  Benjamin Pitzer

Inventor： Jan Becker ,  Soeren Kammel ,  Benjamin Pitzer

IPC: G05D1/00

CPC classification number: G05D1/0246 ,  G05D1/0274 ,  G05D2201/0207

Abstract: In one embodiment, an autonomously navigated mobile platform includes a support frame, a projector supported by the frame, a sensor supported by the frame, a memory including a plurality of program instructions stored therein for generating an encoded signal using a phase shifting algorithm, emitting the encoded signal with the projector, detecting the emitted signal with the sensor after the emitted signal is reflected by a detected body, associating the detected signal with the emitted signal, identifying an x-axis dimension, a y-axis dimension, and a z-axis dimension of the detected body, and one or more of a range and a bearing to the detected body, based upon the associated signal, identifying a present location of the mobile platform, navigating the mobile platform based upon the identified location, and a processor operably connected to the memory, to the sensor, and to the projector for executing the program instructions.

Abstract translation: 在一个实施例中，自主导航的移动平台包括支撑框架，由框架支撑的投影仪，由框架支撑的传感器，包含存储在其中的多个程序指令的存储器，用于使用相移算法产生编码信号，发射 在发射信号被检测到的身体反射之后，用投影仪检测发射信号与传感器的发射信号，将检测到的信号与发射信号相关联，识别x轴尺寸，y轴尺寸和z 基于相关联的信号，识别移动平台的当前位置，基于所识别的位置导航移动平台，以及检测到的身体的一个或多个范围和方位;以及 处理器可操作地连接到存储器，传感器和投影仪，用于执行程序指令。

公开(公告)号：US20100280754A1

公开(公告)日：2010-11-04

申请号：US12839793

申请日：2010-07-20

Applicant: Luis Filipe Domingues Goncalves ,  Enrico Di Bernardo ,  Paolo Pirjanian ,  L. Niklas Karlsson

Inventor： Luis Filipe Domingues Goncalves ,  Enrico Di Bernardo ,  Paolo Pirjanian ,  L. Niklas Karlsson

IPC: G01C21/00 ,  G01C21/12

CPC classification number: G05D1/0246 ,  G01C21/12 ,  G05D1/0231 ,  G05D1/0234 ,  G05D1/024 ,  G05D1/0242 ,  G05D1/0248 ,  G05D1/0272 ,  G05D1/0274 ,  G05D1/0278 ,  G05D2201/0207 ,  G05D2201/0215 ,  G06T7/55 ,  G06T7/70 ,  G06T7/74 ,  G06T2207/30204 ,  Y10S901/01 ,  Y10S901/46 ,  Y10S901/47 ,  Y10S901/50

Abstract: The invention is related to methods and apparatus that use a visual sensor and dead reckoning sensors to process Simultaneous Localization and Mapping (SLAM). These techniques can be used in robot navigation. Advantageously, such visual techniques can be used to autonomously generate and update a map. Unlike with laser rangefinders, the visual techniques are economically practical in a wide range of applications and can be used in relatively dynamic environments, such as environments in which people move. One embodiment further advantageously uses multiple particles to maintain multiple hypotheses with respect to localization and mapping. Further advantageously, one embodiment maintains the particles in a relatively computationally-efficient manner, thereby permitting the SLAM processes to be performed in software using relatively inexpensive microprocessor-based computer systems.

Abstract translation: 本发明涉及使用视觉传感器和航位推算传感器来处理同时定位和映射（SLAM）的方法和装置。 这些技术可用于机器人导航。 有利地，可以使用这种可视化技术来自主地生成和更新地图。 与激光测距仪不同，视觉技术在广泛的应用中在经济上是实用的，并且可以在诸如人们移动的环境的相对动态的环境中使用。 一个实施例进一步有利地使用多个粒子来维持关于定位和映射的多个假设。 进一步有利的是，一个实施例以相对计算效率的方式维护颗粒，从而允许使用相对便宜的基于微处理器的计算机系统在软件中执行SLAM处理。

公开(公告)号：US07822266B2

公开(公告)日：2010-10-26

申请号：US11446089

申请日：2006-06-02

Applicant: Carl K. Wellington ,  Aaron C. Courville ,  Anthony J. Stentz

Inventor： Carl K. Wellington ,  Aaron C. Courville ,  Anthony J. Stentz

IPC: G06K9/00

CPC classification number: G06K9/00201 ,  G05D1/024 ,  G05D1/0242 ,  G05D1/0251 ,  G05D1/0274 ,  G05D2201/0201 ,  G05D2201/0207 ,  G05D2201/021 ,  G06K9/00664 ,  G06K9/00697 ,  G06K9/4638 ,  G06T17/05

Abstract: The disclosed terrain model is a generative, probabilistic approach to modeling terrain that exploits the 3D spatial structure inherent in outdoor domains and an array of noisy but abundant sensor data to simultaneously estimate ground height, vegetation height and classify obstacles and other areas of interest, even in dense non-penetrable vegetation. Joint inference of ground height, class height and class identity over the whole model results in more accurate estimation of each quantity. Vertical spatial constraints are imposed on voxels within a column via a hidden semi-Markov model. Horizontal spatial constraints are enforced on neighboring columns of voxels via two interacting Markov random fields and a latent variable. Because of the rules governing abstracts, this abstract should not be used to construe the claims.

Abstract translation: 所公开的地形模型是一种生成性的概率方法，它利用户外域内固有的3D空间结构和一系列噪声丰富的传感器数据来模拟地形，同时估计地面高度，植被高度，分类障碍物和其他感兴趣的领域，甚至 密集不可渗透的植被。 对整个模型的地面高度，班级身高和班级身份的联合推断可以更准确地估算每个数量。 垂直空间约束通过隐藏的半马尔可夫模型施加在列内的体素上。 水平空间约束通过两个相互作用的马尔科夫随机场和潜在变量在相邻列的体素上实现。 由于管理摘要的规则，本摘要不应用于解释索赔。

公开(公告)号：US20100265327A1

公开(公告)日：2010-10-21

申请号：US12677636

申请日：2008-08-25

Applicant: Wolfgang Niem ,  Henning Von Zitzewitz ,  Ulrich-Lorenz Benzler ,  Wolfgang Niehsen ,  Anke Svensson ,  Jochen Wingbermuehle

Inventor： Wolfgang Niem ,  Henning Von Zitzewitz ,  Ulrich-Lorenz Benzler ,  Wolfgang Niehsen ,  Anke Svensson ,  Jochen Wingbermuehle

IPC: H04N7/18 ,  G01S19/39

CPC classification number: G05D1/0253 ,  G05D1/0259 ,  G05D1/0274 ,  G05D1/0278 ,  G05D2201/0207

Abstract: A system and method to record the surroundings for a movable device. The system has at least one sensor for the visual recording of the surroundings, as well as respectively at least one sensor for recording the direction of motion and the orientation of the device, the system being developed to process information provided by the sensors.

Abstract translation: 记录可移动装置的环境的系统和方法。 该系统具有用于视觉记录周围环境的至少一个传感器，以及分别用于记录运动方向和装置的取向的至少一个传感器，该系统被开发以处理由传感器提供的信息。

公开(公告)号：US07774158B2

公开(公告)日：2010-08-10

申请号：US10739935

申请日：2003-12-17

Applicant: Luis Filipe Domingues Goncalves ,  Enrico Di Bernardo ,  Paolo Pirjanian ,  L. Niklas Karlsson

Inventor： Luis Filipe Domingues Goncalves ,  Enrico Di Bernardo ,  Paolo Pirjanian ,  L. Niklas Karlsson

IPC: G01C21/00

CPC classification number: G05D1/0246 ,  G01C21/12 ,  G05D1/0231 ,  G05D1/0234 ,  G05D1/024 ,  G05D1/0242 ,  G05D1/0248 ,  G05D1/0272 ,  G05D1/0274 ,  G05D1/0278 ,  G05D2201/0207 ,  G05D2201/0215 ,  G06T7/55 ,  G06T7/70 ,  G06T7/74 ,  G06T2207/30204 ,  Y10S901/01 ,  Y10S901/46 ,  Y10S901/47 ,  Y10S901/50

Abstract: The invention is related to methods and apparatus that use a visual sensor and dead reckoning sensors to process Simultaneous Localization and Mapping (SLAM). These techniques can be used in robot navigation. Advantageously, such visual techniques can be used to autonomously generate and update a map. Unlike with laser rangefinders, the visual techniques are economically practical in a wide range of applications and can be used in relatively dynamic environments, such as environments in which people move. One embodiment further advantageously uses multiple particles to maintain multiple hypotheses with respect to localization and mapping. Further advantageously, one embodiment maintains the particles in a relatively computationally-efficient manner, thereby permitting the SLAM processes to be performed in software using relatively inexpensive microprocessor-based computer systems.

Abstract translation: 本发明涉及使用视觉传感器和航位推算传感器来处理同时定位和映射（SLAM）的方法和装置。 这些技术可用于机器人导航。 有利地，可以使用这种可视化技术来自主地生成和更新地图。 与激光测距仪不同，视觉技术在广泛的应用中在经济上是实用的，并且可以在诸如人们移动的环境的相对动态的环境中使用。 一个实施例进一步有利地使用多个粒子来维持关于定位和映射的多个假设。 进一步有利的是，一个实施例以相对计算效率的方式维护颗粒，从而允许使用相对便宜的基于微处理器的计算机系统在软件中执行SLAM处理。

公开(公告)号：US07640076B2

公开(公告)日：2009-12-29

申请号：US10977745

申请日：2004-10-29

Applicant: Bradley Darrel Olson

Inventor： Bradley Darrel Olson

IPC: G06F19/00

CPC classification number: G05D1/0038 ,  B25J5/007 ,  B25J15/0206 ,  B25J19/022 ,  G05B2219/37572 ,  G05B2219/40298 ,  G05D2201/0207

Abstract: A remotely controlled roving vehicle comprises a claw assembly and a video camera. The claw assembly includes a main body and a plurality of grasping member. A first end of each one of the grasping members is movably mounted on the main body for enabling a second end of each one of the grasping members to be moved between an open position and a closed position. The video camera includes an image-receiving portion that is mounted on the main body. A second end of each one of the grasping members is within a field of view of the video camera. A lens of the video camera is centrally located with respect to the first ends of the grasping members. The first end of each one of the grasping members is pivotally mounted on the main body. The main body is rotatable about a longitudinal axis thereof.

Abstract translation: 远程控制的粗纱车包括爪组件和摄像机。 爪组件包括主体和多个抓握构件。 每个抓握构件的第一端可移动地安装在主体上，以使得每个抓握构件的第二端能够在打开位置和关闭位置之间移动。 摄像机包括安装在主体上的图像接收部分。 每个抓握构件的第二端在摄像机的视场内。 摄像机的镜头相对于抓握构件的第一端位于中心位置。 每个抓持构件的第一端枢转地安装在主体上。 主体可绕其纵向轴线旋转。

公开(公告)号：US07606416B2

公开(公告)日：2009-10-20

申请号：US10989401

申请日：2004-11-17

Applicant: Woo-Sup Han ,  Kyung-shik Roh ,  Woong Kwon ,  Young-bo Shim ,  Yeon-taek Oh ,  Ki-cheol Park

Inventor： Woo-Sup Han ,  Kyung-shik Roh ,  Woong Kwon ,  Young-bo Shim ,  Yeon-taek Oh ,  Ki-cheol Park

IPC: G06K9/34

CPC classification number: G06K9/00664 ,  G05D1/0246 ,  G05D2201/0207 ,  G06K9/4652 ,  G06K9/4671 ,  G06K9/6212

Abstract: A landmark detection apparatus and method, the apparatus including a first detection unit that generates N first sample blocks in a first sampling region using a first weighted sampling method according to a first degree of dispersion, and that performs a first landmark detection by comparing a feature of each first sample block a feature of a landmark model, where the first sample region is set to the entirety of a current frame image; and a second detection unit that generates N second sample blocks in a second sampling region using a second weighted sampling method according to a second degree of dispersion, and that performs a second landmark detection by comparing a feature of each second sample block the feature of the landmark model, where the second sampling region is set to an area less than the entirety of the current frame image.

Abstract translation: 一种地标检测装置和方法，所述装置包括：第一检测单元，其使用第一分散度的第一加权采样方法在第一采样区域中生成N个第一采样块，并且通过比较特征 每个第一采样块的地标模型的特征，其中第一采样区域被设置为当前帧图像的整体; 以及第二检测单元，其使用根据第二分散度的第二加权采样方法在第二采样区域中生成N个第二采样块，并且通过将每个第二采样块的特征进行比较来执行第二地标检测， 其中第二采样区域被设置为小于当前帧图像的整体的区域。

公开(公告)号：US20090093907A1

公开(公告)日：2009-04-09

申请号：US12180755

申请日：2008-07-28

Applicant: Ryoso Masaki ,  Toshio Moriya ,  Kosei Matsumoto ,  Junichi Tamamoto ,  Motoya Taniguchi

Inventor： Ryoso Masaki ,  Toshio Moriya ,  Kosei Matsumoto ,  Junichi Tamamoto ,  Motoya Taniguchi

IPC: G06F17/00

CPC classification number: G05D1/024 ,  G05D1/0272 ,  G05D1/0274 ,  G05D1/028 ,  G05D1/0297 ,  G05D2201/0206 ,  G05D2201/0207 ,  G05D2201/0216

Abstract: In a robot system constructed by a superior controller and a robot, it is necessary to carry out a high-speed computation in a system which simultaneously generate a map together with identifying a posture of the robot, there is a problem that the robot system becomes expensive because a computing load becomes enlarged, and it is an object to reduce the computing load. In order to achieve the object, there is provided a robot system constructed by a controller having a map data and a mobile robot, in which the robot is provided with a distance sensor measuring a plurality of distances with respect to a peripheral object, and an identifying apparatus identifying a position and an angle of the robot by collating with the map data, and the controller is provided with a map generating apparatus generating or updating the map data on the basis of the position and the angle of the robot, and the measured distance with respect to the object. Accordingly, it is possible to reduce the computing load of the controller and the robot, and it is possible to achieve a comparatively inexpensive robot system.

Abstract translation: 在由上级控制器和机器人构成的机器人系统中，需要在同时生成地图并识别机器人的姿势的系统中进行高速计算，存在机器人系统变为 因为计算负载变大，所以这是降低计算负荷的对象。 为了实现该目的，提供了一种由具有地图数据和移动机器人的控制器构成的机器人系统，其中机器人设置有相对于周边物体测量多个距离的距离传感器，以及 通过与地图数据对照来识别机器人的位置和角度的识别装置，并且控制器设置有基于机器人的位置和角度生成或更新地图数据的地图生成装置，并且测量 相对于物体的距离。 因此，可以减少控制器和机器人的计算负担，并且可以实现相对便宜的机器人系统。