INDUSTRIEROBOTER MIT MINDESTENS ZWEI BILDERFASSUNGSEINRICHTUNGEN
    91.
    发明申请
    INDUSTRIEROBOTER MIT MINDESTENS ZWEI BILDERFASSUNGSEINRICHTUNGEN 审中-公开
    具有至少两个成像装置的工业机器人

    公开(公告)号:WO2017153180A1

    公开(公告)日:2017-09-14

    申请号:PCT/EP2017/054240

    申请日:2017-02-23

    Inventor: STEIDL, Dietmar

    Abstract: Die Erfindung betrifft einen Industrieroboter (1) aufweisend einen Roboterarm (2) mit mehreren Gliedern (12), die über Gelenke (11) verbunden sind, sowie aufweisend eine Robotersteuerung (13), die ausgebildet ist, die Glieder (12) des Roboterarms (2) gemäß eines Roboterprogramms automatisch oder in einem Handfahrbetrieb gegeneinander zu verstellen, wobei wenigstens eines der mehreren Glieder (12) mindestens zwei Bilderfassungseinrichtungen (K1, K2) aufweist, von denen jede Bilderfassungseinrichtung (K1, K2) hinsichtlich ihrer räumlichen Position und Orientierung bezüglich des Glieds (12), an dem die Bilderfassungseinrichtung (K1, K2) befestigt ist, eingemessen ist.

    Abstract translation:

    本发明涉及一种工业机器人(1),其包含(2),其具有多个部件(12)OVER关节的机器人臂(11)连接,并包括机器人控制器(13)形成 是机器人手臂(2)的成员(12)根据。 以自动地或彼此抵靠手动驱动方式中,调整的机器人程序,其中具有至少两个图像获取装置(K1,K2),其中的每一个图像捕获装置(K1,K2)相对于它们的R&AUML所述多个部件(12)中的至少一个; umlichen位置和方向刻导航使用类似于 (12)的图像检测装置(K1,K2)连接到其上。

    ACTIVE CAMERA MOVEMENT DETERMINATION FOR OBJECT POSITION AND EXTENT IN THREE-DIMENSIONAL SPACE
    95.
    发明申请
    ACTIVE CAMERA MOVEMENT DETERMINATION FOR OBJECT POSITION AND EXTENT IN THREE-DIMENSIONAL SPACE 审中-公开
    三维空间中物体位置和外观的主动摄像机运动确定

    公开(公告)号:WO2017095580A1

    公开(公告)日:2017-06-08

    申请号:PCT/US2016/060079

    申请日:2016-11-02

    Abstract: A method of motion planning includes observing an object from a first pose of an agent having a controllable camera. The method also includes determining one or more subsequent control inputs to move the agent and the camera to observe the object from at least one subsequent pose. The subsequent control input(s) are determined so as to minimize an expected enclosing measure of the object based on visual data collected from the camera. The method further includes controlling the agent and the camera based on the subsequent control input(s).

    Abstract translation: 运动计划的方法包括从具有可控照相机的座席的第一姿势观察物体。 该方法还包括确定一个或多个后续控制输入以移动代理和照相机以从至少一个后续姿态观察物体。 确定随后的控制输入,以基于从相机收集的视觉数据使对象的预期封闭度量最小化。 该方法还包括基于随后的控制输入来控制代理和相机。

    TEACHING POINT CORRECTING METHOD, PROGRAM, RECORDING MEDIUM, ROBOT APPARATUS, IMAGING POINT CREATING METHOD, AND IMAGING POINT CREATING APPARATUS
    99.
    发明申请
    TEACHING POINT CORRECTING METHOD, PROGRAM, RECORDING MEDIUM, ROBOT APPARATUS, IMAGING POINT CREATING METHOD, AND IMAGING POINT CREATING APPARATUS 审中-公开
    教导点校正方法,程序,记录介质,机器人装置,成像点创建方法和成像点创建装置

    公开(公告)号:WO2017068930A1

    公开(公告)日:2017-04-27

    申请号:PCT/JP2016/078965

    申请日:2016-09-23

    CPC classification number: B25J9/1697

    Abstract: Indicators are set on a marker positioned on a working stage in conformity with a target teaching point. A stereo camera images the indicator in a state of being positioned on a robot hand, and measures the three-dimensional position of the marker. In robot arm controlling, the robot hand is positioned at the correction teaching point for off-line that is offset from an off-line teaching point in the depth of field direction of the stereo camera. In imaging, while the robot hand is positioned at the correction teaching point for off-line, the indicators are imaged by the stereo camera. In correcting, based on an imaging result of the indicator, the on-line teaching point is corrected toward the target teaching point to obtain the on-line teaching point.

    Abstract translation:

    根据目标教导点,在位于工作台上的标记上设置指示符。 立体照相机使指示器成像在机器人手上,并测量标记的三维位置。 在机器人手臂控制中,机器人手位于离线的校正示教点,该立体相机的景深方向偏离离线示教点。 在成像中,当机器人手放置在离线校正示教点时,指示器由立体相机成像。 在根据指标的成像结果进行校正时,朝向目标教导点校正在线教导点以获得在线教导点。

    USING SENSOR-BASED OBSERVATIONS OF AGENTS IN AN ENVIRONMENT TO ESTIMATE THE POSE OF AN OBJECT IN THE ENVIRONMENT AND TO ESTIMATE AN UNCERTAINTY MEASURE FOR THE POSE
    100.
    发明申请
    USING SENSOR-BASED OBSERVATIONS OF AGENTS IN AN ENVIRONMENT TO ESTIMATE THE POSE OF AN OBJECT IN THE ENVIRONMENT AND TO ESTIMATE AN UNCERTAINTY MEASURE FOR THE POSE 审中-公开
    使用基于传感器的环境中的代理观察来估计对象在环境中的位置并估计不确定度的位置

    公开(公告)号:WO2017059267A1

    公开(公告)日:2017-04-06

    申请号:PCT/US2016/054817

    申请日:2016-09-30

    Abstract: Methods, apparatus, systems, and computer-readable media are provided for using sensor-based observations from multiple agents (e.g., mobile robots and/or fixed sensors) in an environment to estimate the pose of an object in the environment at a target time and to estimate an uncertainty measure for that pose. Various implementations generate a multigraph based on a group of observations from multiple agents, where the multigraph includes a reference frame node, object nodes, and a plurality edges connecting the nodes. In some implementations, a composite pose and composite uncertainty measure are generated for each of a plurality of simple paths along the edges of the multigraph that connect the reference frame node to a given object node - and a pose and uncertainty measure for an object identifier associated with the given object node is generated based on the composite poses and the composite uncertainty measures.

    Abstract translation: 提供方法,装置,系统和计算机可读介质,用于在环境中使用来自多个代理(例如,移动机器人和/或固定传感器)的基于传感器的观察来估计在目标时间的环境中的物体的姿态 并估计该姿势的不确定性度量。 各种实施方式基于来自多个代理的观察组生成多个图像,其中多个图形包括参考帧节点,对象节点和连接节点的多个边缘。 在一些实施方式中,针对连接参考帧节点与给定对象节点的多个图形的边缘的多个简单路径中的每一个生成复合姿态和复合不确定性度量以及相关联的对象标识符的姿态和不确定性度量 基于复合姿势和复合不确定性度量产生给定对象节点。

Patent Agency Ranking