知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

75 条记录 (耗时 0.03 秒)

    Replicating the Remote Environment of a Proxy Robot
    1.
    发明申请
    Replicating the Remote Environment of a Proxy Robot 审中-公开

    公开(公告)号：US20170129105A1

    公开(公告)日：2017-05-11

    申请号：US15384321

    申请日：2016-12-20

    申请人： Kenneth Dean Stephens, Jr.

    发明人： Kenneth Dean Stephens, Jr.

    IPC分类号： B25J9/16 ,  B25J3/04

    CPC分类号： B25J9/1689 ,  B25J3/04 ,  B25J11/00 ,  B64G4/00 ,  B64G2001/1064 ,  B64G2004/005 ,  G05B2219/40116 ,  G05B2219/40191 ,  G06N3/004 ,  G06N3/008 ,  Y10S901/09 ,  Y10S901/47

    摘要： A method and system for exploring a remote environment from an environment simulator or terrain replicator at a local base on Earth is disclosed. The system includes: at least one proxy robot in the remote environment with a near-field video camera and a high resolution 360-degree far field video camera; at least one additional surveillance means at the remote environment to capture images and data pertaining to the remote environment; an aggregator means to aggregate video from the cameras on the at least one proxy robot with the images and data from the at least one additional surveillance means; a transmitter means at the remote environment to transmit the aggregated video and data signals over a path to the local base; a receiver means at the local base to receive the aggregated video and data signals from the remote environment; a terrain analysis computer at the local base to receive and process the aggregated video and data signals to generate therefrom a 360-degree approximated real time (ART) video field precisely representing a terrain surrounding the at least one proxy robot in the remote environment; a display means in the environment simulator or the terrain replicator at the local base to receive and display the ART video field for at least one user; a full body motion capture suit means in the environment simulator or the terrain replicator marked to a plurality of dimensions of the at least one user, wherein activities performed virtually in the environment simulator or the terrain replicator represent the identical activities to be performed by the proxy robot in the terrain of the remote environment; a plurality of motion capture video cameras to capture video signals representing each move or position change in the full body motion capture suit; a follow-me data computer to receive the video signals from the plurality of motion capture video cameras, wherein the follow-me data computer processes the motion capture video signals into a follow-me data train for transmission to a follow-me data translator at the remote environment, and wherein the follow-me data computer further generates and directs data representing changes in the full body motion capture suit back to the terrain analysis computer for continuous updating of the ART video for the display means in the environment simulator or the terrain replicator to reflect position changes from the full body motion capture suit; a follow-me data translator at the remote environment to translate the follow-me data train into data code addressable to each electro-mechanical hinge, motor and synthetic muscle in the at least one proxy robot and cause the proxy robot to move through the remote environment by emulating every move and position change in the full body motion capture suit at the local base.

    Reconfigurable robotic system
    2.
    发明授权
    Reconfigurable robotic system 有权
    可重构机器人系统

    公开(公告)号：US09592603B2

    公开(公告)日：2017-03-14

    申请号：US14802971

    申请日：2015-07-17

    申请人： SPIN MASTER INC.

    发明人： Christopher John Hardouin ,  Romeo Andres Garza ,  Felipe Jose Garza

    IPC分类号： G06F19/00 ,  B25J9/08 ,  B25J9/00 ,  B25J9/16

    CPC分类号： B25J9/08 ,  B25J5/007 ,  B25J9/0003 ,  B25J9/1602 ,  B25J9/1617 ,  B25J13/003 ,  G05B2219/40116 ,  G05B2219/40264 ,  G05B2219/40302 ,  G05B2219/40304 ,  G05D2201/0214

    摘要： A system includes digital servo modules and building blocks that are assemblable in several permutations to construct robotic figures. A central controller communicates with the modules via communication channels, each subdivided into sub-channels. The system utilizes a discovery process wherein the central controller periodically transmits a discovery signal in each sub-channel until a newly attached module transmits a reply to the discovery signal. The central controller transmits position commands to the recognized servo modules and receives position feedback from the recognized modules. The system enables someone to easily program a robotic figure via: a learned motion mode, wherein joints are manipulated and the central controller records a trajectory for each servo module; a user motion capture mode, wherein user motions are captured via camera to generate servo trajectories; and an animation builder mode, wherein a virtual representation of the robotic figure can be manipulated on screen to generate servo trajectories.

    摘要翻译： 一个系统包括数字伺服模块和可以组合在几个排列中构建机器人图形的构建模块。 中央控制器通过通信通道与模块进行通信，每个通道分为子通道。 该系统利用发现过程，其中中央控制器周期性地发送每个子信道中的发现信号，直到新连接的模块向发现信号发送回复。 中央控制器将位置命令发送到识别的伺服模块，并从识别的模块接收位置反馈。 该系统使得人们能够通过以下方式轻松地编程机器人图：学习的运动模式，其中关节被操纵并且中央控制器记录每个伺服模块的轨迹; 用户运动捕捉模式，其中通过照相机捕获用户运动以产生伺服轨迹; 以及动画构建器模式，其中可以在屏幕上操纵机器人图形的虚拟表示以产生伺服轨迹。

    Robot and method for controlling a robot
    3.
    发明授权
    Robot and method for controlling a robot 有权
    用于控制机器人的机器人和方法

    公开(公告)号：US09579793B2

    公开(公告)日：2017-02-28

    申请号：US13060847

    申请日：2009-08-19

    申请人： Dirk Jacob ,  Tobias Ortmaier

    发明人： Dirk Jacob ,  Tobias Ortmaier

    IPC分类号： B25J9/16 ,  A61B34/30 ,  A61B17/00

    CPC分类号： B25J9/1643 ,  A61B34/30 ,  A61B2017/00207 ,  A61B2090/0427 ,  A61B2090/061 ,  B25J9/1676 ,  B25J9/1689 ,  G05B2219/39211 ,  G05B2219/40116 ,  G05B2219/40202 ,  G05B2219/40617

    摘要： The invention relates to a robot and a method for controlling a robot. The distance between an object and the robot and/or the derivative thereof or a first motion of the object is detected by means of a non-contact distance sensor arranged in or on a robot arm of the robot and/or on or in an end effector fastened on the robot arm. The robot arm is moved based on the first motion detected by means of the distance sensor, a target force or a target torque to be applied by the robot is determined based on the distance detected between the object and the robot, and/or a function of the robot or a parameterization of a function of the robot is triggered based on the first motion detected and/or a target distance between the object and the robot and/or the derivative thereof detected by means of the distance sensor.

    摘要翻译： 本发明涉及一种机器人和一种用于控制机器人的方法。 物体与机器人之间的距离和/或其衍生物或物体的第一运动通过布置在机器人的机器人手臂中或之上的非接触式距离传感器和/或一端 执行器固定在机器人手臂上。 基于通过距离传感器检测到的第一动作来移动机器人手臂，基于被检体和机器人之间的距离，确定由机器人施加的目标力或目标力矩，和/或功能 基于通过距离传感器检测的第一运动和/或物体与机器人之间的目标距离和/或其导数来触发机器人的功能的参数化。

    Robotic process automation
    4.
    发明授权
    Robotic process automation 有权
    机器人过程自动化

    公开(公告)号：US09555544B2

    公开(公告)日：2017-01-31

    申请号：US15094063

    申请日：2016-04-08

    申请人： Accenture Global Solutions Limited

    发明人： Cyrille Bataller ,  Adrien Jacquot ,  Sergio Raúl Torres

    IPC分类号： G05B19/00 ,  B25J9/16 ,  G06T1/00 ,  G06F3/0484

    CPC分类号： B25J9/163 ,  B25J9/1679 ,  B25J9/1697 ,  G05B19/0423 ,  G05B2219/36184 ,  G05B2219/40116 ,  G06F3/0484 ,  G06T1/0014

    摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automating a manual process. The methods, systems, and apparatus include actions of identifying a process that (i) is manually performed by a user interacting with a computer, and (ii) is to be automated for performance by a robot that is configured to interact with another computer. Additional actions include obtaining one or more images taken of a display of the computer while the user is interacting with the computer in manually performing the process and applying a computer vision technique to identify one or more activities associated with the process. Further actions include, for each of the one or more identified activities, generating activity information associated with the activity and generating a process definition for use in causing the robot to automatically perform the process.

    摘要翻译： 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于自动化手动过程。 方法，系统和装置包括识别（i）由与计算机交互的用户手动执行的过程的动作，以及（ii）被配置为与另一计算机交互的机器人的自动执行。 附加动作包括在用户正在与计算机进行交互以手动执行该过程并应用计算机视觉技术来识别与该过程相关联的一个或多个活动时，获取所获取的计算机显示的一个或多个图像。 对于一个或多个识别的活动中的每一个，进一步的动作包括生成与活动相关联的活动信息，并且生成用于使机器人自动执行该过程的过程定义。

    TELEPRESENCE BASED INVENTORY PICK AND PLACE OPERATIONS THROUGH ROBOTIC ARMS AFFIXED TO EACH ROW OF A SHELF
    5.
    发明申请
    TELEPRESENCE BASED INVENTORY PICK AND PLACE OPERATIONS THROUGH ROBOTIC ARMS AFFIXED TO EACH ROW OF A SHELF 审中-公开
    基于TELEPRESENCE的存货和通过机器人操作的地位操作完成了每一条货架

    公开(公告)号：US20160297611A1

    公开(公告)日：2016-10-13

    申请号：US15077931

    申请日：2016-03-23

    申请人： Jeff Williams ,  Ravi Bhaskaran ,  Charlie Martin

    发明人： Jeff Williams ,  Ravi Bhaskaran ,  Charlie Martin

    IPC分类号： B65G1/137 ,  B25J9/16 ,  G05D1/00 ,  B25J13/02

    CPC分类号： B65G1/137 ,  B25J3/00 ,  B25J3/04 ,  B25J9/0087 ,  B25J9/1687 ,  B25J9/1689 ,  B25J13/006 ,  B25J13/025 ,  B65G2209/04 ,  G05B2219/39106 ,  G05B2219/40014 ,  G05B2219/40078 ,  G05B2219/40116 ,  G05B2219/40192 ,  G05D1/005 ,  G05D2201/0216

    摘要： Disclosed are a system and/or a method of telepresence based inventory pick and place operations through actuator controlled robotic arms affixed to each row of a shelf. A method includes mounting a robotic arm at an end of a row of a shelf of inventory on a set of rails affixed to the row of a shelf. The robotic arm is permitted to move horizontally along the row of the shelf. The robotic arm is repositioned along the three axes using a set of actuators. A haptic motion of a human user is mirrored that is remotely using a positioning device (e.g., human may feel the feedback of the remote arm as it touches the objects). An item is placed on a counting platform in front of the robotic arm. The items are placed automatically in the designated location down through a transport means when a pick operation is completed.

    摘要翻译： 公开了一种通过致动器控制的机器人手臂固定到搁架的每一行的基于远程呈现的库存拾取和放置操作的系统和/或方法。 一种方法包括将机架手臂放置在一列存放在货架上的一端的固定在货架行上的一组导轨上。 允许机器人手臂沿着货架的行水平移动。 使用一组致动器沿着三个轴重新定位机器臂。 人类用户的触觉运动被镜像，远程使用定位设备（例如，人可能感觉到远程臂在触摸物体时的反馈）。 一个物品放置在机器臂前面的计数平台上。 当拾取操作完成时，物品通过传送装置自动放置在指定位置。

    APPARATUS AND METHODS FOR CONTROL OF ROBOT ACTIONS BASED ON CORRECTIVE USER INPUTS
    7.
    发明申请
    APPARATUS AND METHODS FOR CONTROL OF ROBOT ACTIONS BASED ON CORRECTIVE USER INPUTS 有权
    基于正确的用户输入控制机器人动作的装置和方法

    公开(公告)号：US20150217449A1

    公开(公告)日：2015-08-06

    申请号：US14171762

    申请日：2014-02-03

    申请人： Brain Corporation

    发明人： Philip Meier ,  Jean-Baptiste Passot ,  Borja Ibarz Gabardos ,  Patryk Laurent ,  Oleg Sinyavskiy ,  Peter O'Connor ,  Eugene Izhikevich

    IPC分类号： B25J9/16 ,  G06N5/04 ,  G06N99/00

    CPC分类号： B25J9/163 ,  B25J9/1602 ,  B25J9/161 ,  B25J9/1656 ,  G05B2219/40116 ,  G05D1/0033 ,  G05D1/0088 ,  G05D2201/02 ,  G06N3/008 ,  G06N99/005 ,  Y10S901/01 ,  Y10S901/46

    摘要： Robots have the capacity to perform a broad range of useful tasks, such as factory automation, cleaning, delivery, assistive care, environmental monitoring and entertainment. Enabling a robot to perform a new task in a new environment typically requires a large amount of new software to be written, often by a team of experts. It would be valuable if future technology could empower people, who may have limited or no understanding of software coding, to train robots to perform custom tasks. Some implementations of the present invention provide methods and systems that respond to users' corrective commands to generate and refine a policy for determining appropriate actions based on sensor-data input. Upon completion of learning, the system can generate control commands by deriving them from the sensory data. Using the learned control policy, the robot can behave autonomously.

    摘要翻译： 机器人有能力执行广泛的有用任务，如工厂自动化，清洁，交付，辅助护理，环境监测和娱乐。 使机器人在新环境中执行新任务通常需要大量新的软件来编写，通常由专家小组编写。 如果未来的技术可以赋予人们对软件编码有限或不了解的机会来训练机器人来执行定制任务，这将是有价值的。 本发明的一些实施方案提供了响应于用户的校正命令以生成和改进用于基于传感器数据输入确定适当动作的策略的方法和系统。 完成学习后，系统可以通过从感官数据中导出控制命令来生成控制命令。 使用学习的控制策略，机器人可以自主行为。

    APPARATUS AND METHODS FOR CONTROLLING OF ROBOTIC DEVICES
    9.
    发明申请
    APPARATUS AND METHODS FOR CONTROLLING OF ROBOTIC DEVICES 审中-公开
    用于控制机器人装置的装置和方法

    公开(公告)号：US20150032258A1

    公开(公告)日：2015-01-29

    申请号：US13953595

    申请日：2013-07-29

    申请人： BRAIN CORPORATION

    发明人： Jean-Baptiste Passot ,  Patryk Laurent ,  Eugene M. Izhikevich

    IPC分类号： B25J9/16

    CPC分类号： B25J9/1656 ,  G05B2219/35444 ,  G05B2219/40116 ,  G06N3/008 ,  G06N3/049

    摘要： A robot may be trained based on cooperation between an operator and a trainer. During training, the operator may control the robot using a plurality of control instructions. The trainer may observe movements of the robot and generate a plurality of control commands, such as gestures, sound and/or light wave modulation. Control instructions may be combined with the trainer commands via a learning process in order to develop an association between the two. During operation, the learning process may generate one or more control instructions based on one or more gesture by the trainer. One or both the trainer or the operator may comprise a human, and/or computerized entity.

    摘要翻译： 可以基于操作者和训练者之间的协作训练机器人。 在训练期间，操作员可以使用多个控制指令来控制机器人。 训练者可以观察机器人的运动并产生多个控制命令，例如手势，声音和/或光波调制。 控制指令可以通过学习过程与训练器命令组合，以便在两者之间建立关联。 在操作期间，学习过程可以基于训练者的一个或多个手势产生一个或多个控制指令。 训练者或操作员中的一个或两个可以包括人类和/或计算机化的实体。