公开(公告)号：WO2011057153A1

公开(公告)日：2011-05-12

申请号：PCT/US2010/055740

申请日：2010-11-05

Applicant: EVOLUTION ROBOTICS, INC. ,  STOUT, Michael, S. ,  BRISSON, Gabriel, Francis ,  DI BERNARDO, Enrico ,  PIRJANIAN, Paolo ,  GOEL, Dhiraj ,  CASE, James, Philip ,  DOOLEY, Michael, J.

Inventor： STOUT, Michael, S. ,  BRISSON, Gabriel, Francis ,  DI BERNARDO, Enrico ,  PIRJANIAN, Paolo ,  GOEL, Dhiraj ,  CASE, James, Philip ,  DOOLEY, Michael, J.

IPC: G05D1/02

CPC classification number: B25J9/1684 ,  B25J5/00 ,  B25J5/005 ,  B25J5/007 ,  B25J9/163 ,  G05D1/0219 ,  G05D1/0234 ,  G05D1/0238 ,  G05D1/0255 ,  G05D1/0257 ,  G05D1/0263 ,  G05D1/0272 ,  G05D1/0274 ,  G05D2201/0203 ,  G05D2201/0208 ,  G05D2201/0215 ,  Y10S901/01 ,  Y10S901/46

Abstract: A robot configured to navigate a surface, the robot comprising a movement mechanism; a logical map representing data about the surface and associating locations with one or more properties observed during navigation; an initialization module configured to establish an initial pose comprising an initial location and an initial orientation; a region covering module configured to cause the robot to move so as to cover a region; an edge- following module configured to cause the robot to follow unfollowed edges; a control module configured to invoke region covering on a first region defined at least in part based at least part of the initial pose, to invoke region covering on least one additional region, to invoke edge-following, and to invoke region covering cause the mapping module to mark followed edges as followed, and cause a third region covering on regions discovered during edge-following.

Abstract translation: 一种被配置为导航表面的机器人，所述机器人包括移动机构; 表示关于表面的数据和将位置与在导航期间观察到的一个或多个属性相关联的逻辑图; 初始化模块，被配置为建立包括初始位置和初始取向的初始姿势; 区域覆盖模块，被配置为使所述机器人移动以覆盖区域; 边缘跟随模块被配置为使机器人跟随未追随的边缘; 控制模块，被配置为调用覆盖在至少部分地基于初始姿态的至少一部分定义的第一区域上的区域，以调用覆盖至少一个附加区域的区域，以调用边缘跟随，并且调用区域覆盖导致映射 模块来标记跟随的边缘，并且使得覆盖在边缘跟随期间发现的区域的第三区域。

公开(公告)号：WO2005098476A1

公开(公告)日：2005-10-20

申请号：PCT/US2005/010244

申请日：2005-03-25

Applicant: EVOLUTION ROBOTICS, INC. ,  DIBERNARDO, Enrico ,  PIRJANIAN, Paolo

Inventor： DIBERNARDO, Enrico ,  PIRJANIAN, Paolo

IPC: G01S17/06

CPC classification number: G01B11/002 ,  G01C3/06 ,  G01S5/163 ,  G01S17/06 ,  G01S17/48 ,  G05D1/0234

Abstract: The invention is generally related to the estimation of position and orientation of an object (201) with respect to a local or a global coordinate system using reflected light sources (204, 205) . A typical application of the method and apparatus includes estimation and tracking of the position of a mobile autonomous robot. Other applications include estimation and tracking of an object for position-aware, ubiquitous devices. Additional applications include tracking of the positions of people or pets in an indoor environment. The methods and apparatus comprise one or more optical emitters (203) , one or more optical sensors (202) , signal processing circuitry, and signal processing methods to determine the position and orientation of at least one of the optical sensors based at least in part on the detection of the signal of one or more emitted light sources (201, 205) reflected from a surface (206) .

Abstract translation: 本发明通常涉及使用反射光源（204,205）相对于局部或全局坐标系的估计对象（201）的位置和取向。 所述方法和装置的典型应用包括估计和跟踪移动自主机器人的位置。 其他应用包括用于位置感知，普遍存在的设备的对象的估计和跟踪。 其他应用包括追踪人或宠物在室内环境中的位置。 方法和装置包括一个或多个光发射器（203），一个或多个光学传感器（202），信号处理电路和信号处理方法，用于至少部分地确定至少一个光学传感器的位置和取向 检测从表面（206）反射的一个或多个发射光源（201,205）的信号。

公开(公告)号：WO2004063883A2

公开(公告)日：2004-07-29

申请号：PCT/US2004/000413

申请日：2004-01-09

Applicant: EVOLUTION ROBOTICS, INC. ,  PIRJANIAN, Paolo ,  LISTICK, Barton, Elliot

Inventor： PIRJANIAN, Paolo ,  LISTICK, Barton, Elliot

IPC: G06F

CPC classification number: G05B19/0426 ,  B25J9/1656 ,  G05B2219/23363 ,  G05B2219/23367

Abstract: The invention is related to methods and apparatus for programming and/or control of a computer system via a video camera or other imaging device. Objects in the environment, such as printed cards, can be placed within the field of view of the video camera or other imaging device. Indicia on the cards can be recognized and associated with one or more programming instructions or computer commands for control. In one embodiment, a computer system that is programmed and/or is controlled corresponds to a robot, such as a stationary robot or a mobile robot. In one embodiment, a process receives or monitors visual data (102) from a device such as a camera, recognizes indicia (104) from objects such as cards that are observed in the video images, associates the recognized indicia (106) with programming instructions, such as by, for example, reference to a data store, and arranges a computer program (108) based on the associated programming instructions.

Abstract translation: 本发明涉及用于通过摄像机或其他成像装置对计算机系统进行编程和/或控制的方法和装置。 环境中的对象，例如打印卡，可以放置在摄像机或其他成像设备的视野内。 可以识别卡上的标记并与一个或多个编程指令或计算机命令相关联以进行控制。 在一个实施例中，被编程和/或被控制的计算机系统对应于诸如静止机器人或移动机器人的机器人。 在一个实施例中，过程从诸如照相机的设备接收或监视可视数据（102），从视频图像中观察到的对象（例如卡）识别标记（104），将识别的标记（106）与编程指令相关联 ，诸如通过例如引用数据存储器，并且基于相关联的编程指令来布置计算机程序（108）。

公开(公告)号：WO2004063883A3

公开(公告)日：2005-10-06

申请号：PCT/US2004000413

申请日：2004-01-09

Applicant: EVOLUTION ROBOTICS INC ,  PIRJANIAN PAOLO ,  LISTICK BARTON ELLIOT

Inventor： PIRJANIAN PAOLO ,  LISTICK BARTON ELLIOT

IPC: G05B15/00 ,  G05B19/00 ,  G05B19/042 ,  G06F20060101 ,  G06F19/00

CPC classification number: G05B19/0426 ,  B25J9/1656 ,  G05B2219/23363 ,  G05B2219/23367

Abstract: The invention is related to methods and apparatus for programming and/or control of a computer system via a video camera or other imaging device. Objects in the environment, such as printed cards, can be placed within the field of view of the video camera or other imaging device. Indicia on the cards can be recognized and associated with one or more programming instructions or computer commands for control. In one embodiment, a computer system that is programmed and/or is controlled corresponds to a robot, such as a stationary robot or a mobile robot. In one embodiment, a process receives or monitors visual data (102) from a device such as a camera, recognizes indicia (104) from objects such as cards that are observed in the video images, associates the recognized indicia (106) with programming instructions, such as by, for example, reference to a data store, and arranges a computer program (108) based on the associated programming instructions.

Abstract translation: 本发明涉及用于通过摄像机或其他成像装置对计算机系统进行编程和/或控制的方法和装置。 环境中的对象，例如打印卡，可以放置在摄像机或其他成像设备的视野内。 可以识别卡上的标记并与一个或多个编程指令或计算机命令相关联以进行控制。 在一个实施例中，被编程和/或被控制的计算机系统对应于诸如静止机器人或移动机器人的机器人。 在一个实施例中，过程从诸如相机的设备接收或监视可视数据（102），从视频图像中观察到的对象（例如卡）识别标记（104），将识别的标记（106）与编程指令相关联 ，诸如通过例如引用数据存储器，并且基于相关联的编程指令来布置计算机程序（108）。

公开(公告)号：WO2005088569A1

公开(公告)日：2005-09-22

申请号：PCT/US2005/005843

申请日：2005-02-24

Applicant: EVOLUTION ROBOTICS, INC. ,  HUDNUT, Alec ,  SIMONINI, Alex ,  CREMEAN, Michael ,  MORGAN, Howard

Inventor： HUDNUT, Alec ,  SIMONINI, Alex ,  CREMEAN, Michael ,  MORGAN, Howard

IPC: G07G1/00

CPC classification number: G07F7/02 ,  A47F9/046 ,  G06Q20/343 ,  G07G3/003

Abstract: Methods and computer readable media for recognizing and identifying items located on the belt of a counter and/or in a shopping cart of a store environment for the purpose of reducing/preventing bottom-of-the-basket loss, checking out the items automatically, reducing the checkout time, preventing consumer fraud, increasing revenue and replacing a conventional UPC scanning system to enhance the checking out speed. The images of the items taken by visual sensors may be analyzed to extract features using the scale-invariant feature transformation (SIFT) method. Then, the extracted features are compared to those of trained images stored in a database to find a set of matches. Based on the set of matches, the items are recognized and associated with one or more instructions, commands or actions without the need for personnel to visually see the items, such as by having to come out from behind a check out counter or peering over a check out counter.

Abstract translation: 用于识别和识别位于商店环境的柜台和/或购物车的皮带上的物品的方法和计算机可读介质，用于减少/防止篮下损失，自动检查物品， 减少结帐时间，防止消费者欺诈，增加收入，更换常规UPC扫描系统，提升检出速度。 可以分析由视觉传感器拍摄的物品的图像，以使用尺度不变特征变换（SIFT）方法来提取特征。 然后，将所提取的特征与存储在数据库中的训练图像的特征进行比较以找到一组匹配。 基于一组匹配，这些项目被识别并与一个或多个指令，命令或动作相关联，而不需要人员直观地看到物品，例如必须从检出柜台后面出来或者对等 收银台。

公开(公告)号：WO2004016400A3

公开(公告)日：2004-07-29

申请号：PCT/US0325666

申请日：2003-08-15

Applicant: EVOLUTION ROBOTICS INC ,  BURL MICHAEL CHRISTOPHER ,  PIRJANIAN PAOLO

Inventor： BURL MICHAEL CHRISTOPHER ,  PIRJANIAN PAOLO

IPC: B25J20060101 ,  G05D1/02 ,  G06K9/00 ,  G06T7/20

CPC classification number: G05D1/0246 ,  G05D1/0227 ,  G05D1/024 ,  G05D1/0242 ,  G05D1/0253 ,  G05D1/0255 ,  G05D1/0272 ,  G05D1/0274 ,  G05D2201/0215 ,  G06T7/246

Abstract: The invention is related to methods and apparatus that detect motion by monitoring images from a video camera (104) mounted on a mobile robot (100), such as an autonomously navigated mobile robot (104). Examples of such robots include automated vacuum floor sweepers. Advantageously, embodiments of the invention can automatically sense a robot's motional state in a relatively reliable and cost-efficient manner. Many configurations of robots (100) are configured to include at least one video camera (104). Embodiments of the invention permit the use of a video camera (104) onboard a robot (100) to determine a motional state for the robot (100). This can advantageously permit the motional state of a robot to be determined at a fraction of the cost of additional sensors, such as a laser, an infrared, an ultrasonic, or a contact sensor.

Abstract translation: 本发明涉及通过监视来自安装在诸如自主导航的移动机器人（104）的移动机器人（100）上的摄像机（104）的图像来检测运动的方法和装置。 这种机器人的实例包括自动真空地板清扫机。 有利地，本发明的实施例可以以相对可靠和成本有效的方式自动地感测机器人的运动状态。 机器人（100）的许多配置被配置为包括至少一个摄像机（104）。 本发明的实施例允许使用机器人（100）上的摄像机（104）来确定机器人（100）的运动状态。 这可以有利地允许机器人的运动状态以附加传感器（例如激光，红外线，超声波或接触传感器）的成本的一小部分来确定。

公开(公告)号：WO2004016400A2

公开(公告)日：2004-02-26

申请号：PCT/US2003/025666

申请日：2003-08-15

Applicant: EVOLUTION ROBOTICS, INC. ,  BURL, Michael, Christopher ,  PIRJANIAN, Paolo

Inventor： BURL, Michael, Christopher ,  PIRJANIAN, Paolo

IPC: B25J

CPC classification number: G05D1/0246 ,  G05D1/0227 ,  G05D1/024 ,  G05D1/0242 ,  G05D1/0253 ,  G05D1/0255 ,  G05D1/0272 ,  G05D1/0274 ,  G05D2201/0215 ,  G06T7/246

Abstract: The invention is related to methods and apparatus that detect motion by monitoring images from a video camera (104) mounted on a mobile robot (100), such as an autonomously navigated mobile robot (104). Examples of such robots include automated vacuum floor sweepers. Advantageously, embodiments of the invention can automatically sense a robot's motional state in a relatively reliable and cost-efficient manner. Many configurations of robots (100) are configured to include at least one video camera (104). Embodiments of the invention permit the use of a video camera (104) onboard a robot (100) to determine a motional state for the robot (100). This can advantageously permit the motional state of a robot to be determined at a fraction of the cost of additional sensors, such as a laser, an infrared, an ultrasonic, or a contact sensor.

Abstract translation: 本发明涉及通过监视来自安装在移动机器人（100）上的摄像机（104）（诸如自主导航的移动机器人（104））的图像来检测运动的方法和装置。 这种机器人的例子包括自动真空地板清扫机。 有利地，本发明的实施例可以以相对可靠且成本有效的方式自动感测机器人的运动状态。 机器人（100）的许多配置被配置为包括至少一个摄像机（104）。 本发明的实施例允许使用机器人（100）上的摄像机（104）来确定机器人（100）的运动状态。 这可以有利地允许机器人的运动状态以附加传感器（例如激光器，红外线，超声波或接触传感器）的一小部分成本来确定。

公开(公告)号：WO2013071190A1

公开(公告)日：2013-05-16

申请号：PCT/US2012/064553

申请日：2012-11-09

Applicant: EVOLUTION ROBOTICS, INC.

Inventor： GUTMANN, Jens-steffen ,  GOEL, Dhiraj ,  MUNICH, Mario, E. ,  FONG, Philip

IPC: B25J9/16 ,  B25J13/08 ,  G05D1/02

CPC classification number: G01C21/12 ,  G01S17/06 ,  G05D1/0231 ,  G05D1/0234 ,  G05D1/0272 ,  G05D1/0274 ,  G05D1/028 ,  G05D2201/0203 ,  G05D2201/0207 ,  Y10S901/01 ,  Y10S901/47

Abstract: Vector Field SLAM is a method for localizing a mobile robot in an unknown environment from continuous signals such as WiFi or active beacons. Disclosed is a technique for localizing a robot in relatively large and/or disparate areas. This is achieved by using and managing more signal sources for covering the larger area. One feature analyzes the complexity of Vector Field SLAM with respect to area size and number of signals and then describe an approximation that decouples the localization map in order to keep memory and run-time requirements low. A tracking method for re-localizing the robot in the areas already mapped is also disclosed. This allows to resume the robot after is has been paused or kidnapped, such as picked up and moved by a user. Embodiments of the invention can comprise commercial low-cost products including robots for the autonomous cleaning of floors.

Abstract translation: 矢量场SLAM是一种用于在来自诸如WiFi或活动信标之类的连续信号的未知环境中定位移动机器人的方法。 公开了一种用于在相对较大和/或不同的区域中定位机器人的技术。 这是通过使用和管理更多的信号源来覆盖较大的区域来实现的。 一个特征分析了矢量场SLAM相对于面积大小和信号数量的复杂度，然后描述了一个近似值，它将本地化​​图解耦，以保持内存和运行时间要求较低。 还公开了一种用于在已经映射的区域中重新定位机器人的跟踪方法。 这允许在暂停或被绑架之后恢复机器人，例如用户拾取和移动。 本发明的实施例可以包括商业上的低成本产品，包括用于自主清洁地板的机器人。

公开(公告)号：WO2005088570A1

公开(公告)日：2005-09-22

申请号：PCT/US2005/005851

申请日：2005-02-24

Applicant: EVOLUTION ROBOTICS, INC. ,  OSTROWSKI, Jim ,  GONCALVES, Luis ,  HUDNUT, Alec ,  SIMONINI, Alex ,  CREMEAN, Michael

Inventor： OSTROWSKI, Jim ,  GONCALVES, Luis ,  HUDNUT, Alec ,  SIMONINI, Alex ,  CREMEAN, Michael

IPC: G07G1/00

CPC classification number: G07F7/02 ,  A47F9/045 ,  G06Q20/343 ,  G07G1/0036 ,  G07G1/0063 ,  G07G3/00 ,  G07G3/003 ,  G08B13/1961 ,  G08B13/19671

Abstract: Systems and methods for recognizing and identifying items located on the lower shelf of a shopping cart in a checkout lane of a retail store environment for the purpose of reducing or preventing loss or fraud and increasing the efficiency of a checkout process. The system includes one or more visual sensors that can take images of items and a computer system that receives the images from the one or more visual sensors and automatically identifies the items. The system can be trained to recognize the items using images taken of the items. The system relies on matching visual features from training images to match against features extracted from images taken at the checkout lane. Using the scale-invariant feature transformation (SIFT) method, for example, the system can compare the visual features of the images to the features stored in a database to find one or more matches, where the found one or more matches are used to identify the items. PA ILNI 192-0101 PCT SYSTEMS AND METHODS FOR MERCHANDISE CHECKOUT ABSTRACT OF THE DISCLOSURE

Abstract translation: 为了减少或防止丢失或欺诈以及增加结帐过程的效率，识别和识别位于零售商店环境的结帐通道中的购物车的下架上的物品的系统和方法。 该系统包括可以拍摄物品图像的一个或多个视觉传感器和从一个或多个视觉传感器接收图像并自动识别物品的计算机系统。 可以使用拍摄的项目的图像来训练系统来识别物品。 系统依赖于训练图像的匹配视觉特征，以匹配从结帐通道上拍摄的图像提取的特征。 使用比例不变特征变换（SIFT）方法，例如，系统可以将图像的视觉特征与存储在数据库中的特征进行比较，以找到一个或多个匹配，其中发现的一个或多个匹配用于识别 的项目。 PA ILNI 192-0101 PCT商品检验系统和方法披露摘要

公开(公告)号：WO2005084227A2

公开(公告)日：2005-09-15

申请号：PCT/US2005/006079

申请日：2005-02-28

Applicant: EVOLUTION ROBOTICS, INC. ,  OSTROWSKI, Jim ,  MUNICH, Mario ,  WISEMAN, John

Inventor： OSTROWSKI, Jim ,  MUNICH, Mario ,  WISEMAN, John

IPC: A47F9/04 ,  G07G1/00

CPC classification number: G07G1/0054 ,  A47F9/048

Abstract: Systems and methods for automatically checking out items located on a moving conveyor belt for the purpose of increasing the efficiency of a checkout process and revenue at a point-of-sale. The system includes a conveyor subsystem for moving the items, a housing that enclosed a portion of the conveyor subsystem, a lighting subsystem that illuminates an area within the housing, visual sensors that can take images of the items including UPCs, and a checkout system that receives the images from the visual sensors and automatically identifies the items. The system may include a scale subsystem located under the conveyor subsystem to measure the weights of the items, where the weight of each item is used to check if the corresponding item is identified correctly. The system relies on matching visual features from images stored in a database to match against features extracted from images taken by the visual sensors.

Abstract translation: 用于自动检查位于移动的传送带上的物品的系统和方法，以提高结算过程的效率和销售点的收入。 该系统包括用于移动物品的输送机子系统，封闭输送机子系统的一部分的壳体，照亮壳体内的区域的照明子系统，可以拍摄包括UPC的物品的图像的视觉传感器以及检查系统， 从视觉传感器接收图像并自动识别物品。 该系统可以包括位于输送机子系统下面的比例子系统，用于测量物品的重量，其中每个物品的重量用于检查相应物品是否被正确识别。 该系统依赖于存储在数据库中的图像的匹配视觉特征，以匹配从视觉传感器拍摄的图像中提取的特征。