公开(公告)号：WO2019057356A1

公开(公告)日：2019-03-28

申请号：PCT/EP2018/066429

申请日：2018-06-20

Applicant: ABB SCHWEIZ AG

Inventor： DAI, Fan ,  CLEVER, Debora ,  FIEDLER, Boris ,  KLÖPPER, Benjamin ,  SCHLAKE, Jan-Christoph ,  DIX, Marcel ,  SUBBIAH, Subanatarajan

IPC: B25J9/16 ,  G05B23/02

Abstract: A method for anomaly detection in an industrial robot, comprising the steps of a) while executing a predetermined movement, recording (S11) a time series of at least one first operating parameter of the robot; b) applying a machine learning model to the time series obtained in step a), and c) use the machine learning model to score the time series obtained in step a), deciding whether it is an anomaly or not.

公开(公告)号：WO2017036519A1

公开(公告)日：2017-03-09

申请号：PCT/EP2015/069983

申请日：2015-09-02

Applicant: ABB SCHWEIZ AG

Inventor： DAI, Fan ,  WAHRBURG, Arne ,  MATTHIAS, Björn ,  DING, Hao

IPC: B25J9/16 ,  G05B19/409 ,  G05B19/423

CPC classification number: G05B19/423 ,  B25J9/1656 ,  G05B19/409 ,  G05B2219/36451 ,  G05B2219/36453

Abstract: Hand-held position teaching device (12, 42, 82, 104) and a method for teaching a robot a position and an orientation with a Hand-held position teaching device, wherein the teaching device comprises a teaching device-TCP (18, 56), force sensors (32, 50, 52) and inertial sensors (20, 58) and its' coordinate system is calibrated to the robots' coordinate system, and wherein the teaching device is held in the desired position and orientation and transmits the teaching device-TCP position and orientation to the robot controller (116) to be stored. The user (102) may also apply force to a gripper (44, 48, 84, 88) of the teaching device and grip a workpiece (108, 110) in order to teach a gripping function. The robot controller may afterwards use the plurality of stored positions and orientations to control and move the robot. This is significantly easier than moving the whole robot arm with a teaching device mounted thereon or controlled by it. The user interface of the gripper comprises springs.

Abstract translation: 手持位置教学装置（12,42,82,104）以及用于通过手持式位置教学装置向机器人指示位置和姿势的方法，其中所述教学装置包括教学装置-TCP（18,56 ），力传感器（32,50,52）和惯性传感器（20,58），并且其坐标系被校准到机器人的坐标系，并且其中教导装置保持在期望的位置和方向并且传送教导 设备-TCP位置和定向到要存储的机器人控制器（116）。 用户（102）还可以向教导装置的夹持器（44,48,84,88）施加力并且夹紧工件（108,110）以便教导夹紧功能。 机器人控制器可以随后使用多个存储的位置和方向来控制和移动机器人。 这比使用安装在其上或由其控制的教学装置来移动整个机器人手臂显着简单。 夹持器的用户界面包括弹簧。

公开(公告)号：WO2021239210A1

公开(公告)日：2021-12-02

申请号：PCT/EP2020/064453

申请日：2020-05-25

Applicant: ABB SCHWEIZ AG

Inventor： DAI, Fan ,  LI, Nuo ,  BREISCH, Sebastian ,  CLEVER, Debora

IPC: B25J19/00 ,  B25J15/00

Abstract: Robot application development system (10), comprising a robot application unit (20), configured for determining a robot application (A) for an industrial robot processing a work piece, wherein the robot application (A) defines the industrial robot (100) in a robot workspace; an input interface (40), configured for receiving robot application information (IA) characterizing the robot application (A); an object data interface (50), configured for receiving work piece information (IW) characterizing the work piece (120); and a gripper finger design unit (30), configured for determining a gripper finger (110) design (G) of a gripper finger (110) of the industrial robot (100); wherein the robot application unit (20) is configured for determining the robot application (A), using the robot application information (IA); wherein the gripper finger design unit (30) is configured for determining the gripper finger design (G), using the work piece information (IW) and the robot application information (IA).

公开(公告)号：WO2020030272A1

公开(公告)日：2020-02-13

申请号：PCT/EP2018/071631

申请日：2018-08-09

Applicant: ABB SCHWEIZ AG

Inventor： CLEVER, Debora ,  DAI, Fan ,  DING, Hao ,  GROTH, Tomas ,  MATTHIAS, Dr. Björn ,  WAHRBURG, Arne

IPC: B25J9/16

Abstract: The invention is about a method for estimating a wrench acting on a reference point of a robot, comprising the steps of a) measuring at least one, but not all components of the wrench, and b) estimating non-measured components of the wrench based on a dynamical model of the robot while taking the measured components into account

公开(公告)号：WO2016192768A1

公开(公告)日：2016-12-08

申请号：PCT/EP2015/062087

申请日：2015-06-01

Applicant: ABB SCHWEIZ AG

Inventor： DAI, Fan ,  VILACOBA, Diego

IPC: G05B19/418 ,  B25J9/16

CPC classification number: B25J9/1682 ,  G05B19/41825 ,  G05B2219/34391 ,  G05B2219/39105 ,  G05B2219/39362 ,  Y02P90/087

Abstract: The invention is related to a robot system (30) for synchronizing the movement of a robot arm (32) to a master device (40,42,44), wherein the system comprises a master device (40,42,44), a robot arm (32) with a moveable tip (34) and at least two degrees of freedom in movement and a robot controller (36) which controls the movement of the tip (34) of the robot arm (32) along a predetermined movement path (38, 68, 86) between a start- (70) and an end- (72) position. The robot controller (36) comprises input means (50) for a control signal (52, 62) for values between a first (64) and a second (66) limit, wherein the control signal (52, 62)is generated from source means (48) of the master device (40,42,44) and describes consecutive positions of a movement axis (46,90) of the master device (40,42,44). The robot controller (36) assigns each value of the control signal (52, 62) to a related position of the tip (34) of the robot arm (32) along the predetermined movement path (38, 68, 86) and controls the movement of the tip (34) of the robot arm (32) along the predetermined movement path (38, 68, 86) dependent on the respective values of the control signal (52, 62). While synchronizing the movement of the robot arm with an external axis, a sensor or control device is permanently providing the actual position of the axis to be synchronized with the robot controller, which determines, whether there is a deviation from the desired synchronized state or not.

Abstract translation: 本发明涉及一种用于使机器人手臂（32）与主装置（40,42,44）的移动同步的机器人系统（30），其中该系统包括主装置（40,42,44），一 具有可移动尖端（34）和至少两个运动自由度的机器人臂（32）和机器人控制器（36），其控制机器人手臂（32）的尖端（34）沿着预定的移动路径 （70）和端部（72）之间的位置（38,68,86）。 机器人控制器（36）包括用于控制信号（52,62）的输入装置（50），用于在第一（64）和第二（66）限制之间的值，其中控制信号（52,62）从源 主设备（40,42,44）的装置（48）并且描述主设备（40,42,44）的移动轴（46,90）的连续位置。 机器人控制器（36）将控制信号（52,62）的每个值沿着预定的移动路径（38,68,86）分配给机器人手臂（32）的尖端（34）的相关位置，并且控制 取决于控制信号（52,62）的相应值，机器人臂（32）的尖端（34）沿预定移动路径（38,68,86）移动。 在使机器人臂与外部轴​​线的移动同步的同时，传感器或控制装置永久地提供与机器人控制器同步的轴的实际位置，其确定是否存在与期望的同步状态的偏差 。

公开(公告)号：WO2021190769A1

公开(公告)日：2021-09-30

申请号：PCT/EP2020/058868

申请日：2020-03-27

Applicant: ABB SCHWEIZ AG

Inventor： DAI, Fan ,  LI, Nuo ,  DIX, Marcel ,  CAO, Dongliang

IPC: B25J9/16 ,  B25J9/1669 ,  B25J9/1671 ,  B25J9/1687 ,  G05B2219/40032 ,  G05B2219/40033 ,  G05B2219/40099 ,  G05B2219/40111

Abstract: A method for programming a robot comprises the steps of a) providing a 3D representation of workpieces to be handled by the robot, b) providing a 3D representation of a working environment comprising an initial position where each workpiece is to be seized by the robot, and a final position where the workpiece is to be installed by the robot, c) synthesizing and displaying a view of the working environment comprising an image of the workpieces at respective initial positions; d) enabling a user to select one of the displayed workpieces; e) identifying matching features of the selected workpiece and of the working environment which are able to cooperate to hold the workpiece in a final position in the working environment, and a skill by which the matching features can be brought to cooperate; f) based on the skill and on the final position, identifying an intermediate position from where applying the skill to the workpiece moves the work-piece to the final position; g) adding to a motion program for the robot a routine for moving the workpiece from its initial position to the intermediate position and for applying the skill to the workpiece at the intermediate position.

公开(公告)号：WO2021115615A1

公开(公告)日：2021-06-17

申请号：PCT/EP2019/085081

申请日：2019-12-13

Applicant: ABB SCHWEIZ AG

Inventor： DAI, Fan

IPC: G06K9/00 ,  G06K9/68 ,  G06T1/00

Abstract: A method for visually recognizing an object (5) based on an image provided by a camera (7) viewing an object supporting surface (6), comprises the steps of: a) providing (S1) three-dimensional shape data of an object (5), b) selecting (S2) at least one pose of the object (5) in which the object can be stably positioned on a supporting surface; c) calculating (S4), from said shape data and said selected pose, an expected image (10) of at least part of the object (5), and d) deciding (S7) that the object (5) exists in the field of view of the camera (7) if the expected image (10) is found to match at least part of the image provided by the camera (7).

公开(公告)号：WO2018103908A1

公开(公告)日：2018-06-14

申请号：PCT/EP2017/074751

申请日：2017-09-29

Applicant: ABB SCHWEIZ AG

Inventor： DAI, Fan ,  WAHRBURG, Arne ,  MATTHIAS, Björn ,  DING, Hao

IPC: B25J9/16

Abstract: Ein Verfahren zur Minimierung der Belastung mindestens einer Verbindung (3) eines Manipulators (1), der mittels eines Werkzeugs (2) auf ein Arbeitsobjekt oder seine Umgebung eine Kraft und/ oder ein Drehmoment ausüben soll, ist im Hinblick auf die Aufgabe, einen Manipulator so zu betreiben, dass dessen Manipulationsfähigkeit durch seinen individuellen konstruktiven Aufbau und seine individuelle Leistungsfähigkeit möglichst nicht störend beeinträchtigt wird, dadurch gekennzeichnet, dass die nachfolgenden Schritte ausgeführt werden: - Festlegen des Betrags und/ oder der Richtung der Maximalkraft und/ oder des Maximaldrehmoments, mit welcher bzw. mit welchem die mindestens eine Gelenkverbindung maximal belastet werden soll, - Vorgeben des Betrags und/ oder der Richtung der erwarteten Kraft und/ oder des erwarteten Drehmoments, welche bzw. welches das Werkzeug ausüben soll und/ oder auf dieses einwirkt, - Vorgeben mindestens einer ersten räumlichen Orientierung und/ oder räumlichen Position des Werkzeugs, die sich während des Ausübens oder Einwirkens der Kraft und/ oder des Drehmoments nicht ändern soll, und - Ermitteln einer Konfiguration der Gelenkverbindung, welche diese einnimmt, wenn das Werkzeug unter Einhaltung der vorgegebenen ersten räumlichen Orientierung und/ oder räumlichen Position die vorgegebene Kraft und/ oder das vorgegebene Drehmoment ausübt und/ oder erfährt derart, dass der festgelegte Betrag und/ oder die festgelegte Richtung der Maximalkraft und/ oder des Maximaldrehmoments, mit welcher bzw. mit welchem die mindestens eine Gelenkverbindung maximal belastet werden soll, nicht überschritten wird. Ein Manipulator (1) ist nach diesem Verfahren konfiguriert.

公开(公告)号：WO2022028712A1

公开(公告)日：2022-02-10

申请号：PCT/EP2020/072255

申请日：2020-08-07

Applicant: ABB SCHWEIZ AG

Inventor： DAI, Fan

IPC: B25J9/00 ,  B25J13/00 ,  B25J9/16 ,  B25J13/08 ,  G05B19/423 ,  B25J13/081 ,  B25J9/0081 ,  B25J9/1664 ,  G05B2219/36401 ,  G05B2219/36442

Abstract: A steering module for guiding at least one segment of a robot arm is described, wherein the robot arm is configured to be dragged kinesthetically to guide the robot arm by handling an element of the robot arm, and wherein the steering module comprises a scroll wheel configured to generate steering signals to guide the at least one segment of the robot arm by operating the scroll wheel.

公开(公告)号：WO2020098962A1

公开(公告)日：2020-05-22

申请号：PCT/EP2018/084140

申请日：2018-12-10

Applicant: ABB SCHWEIZ AG

Inventor： CLEVER, Debora ,  DAI, Fan ,  DIX, Marcel ,  KLÖPPER, Benjamin ,  KOTRIWALA, Arzam Muzaffar ,  RODRIGUEZ, Pablo

IPC: G05B13/02 ,  G05B17/02 ,  B25J9/16 ,  G06N3/00

Abstract: A method for applying machine learning, in particular state based machine learning, to an application, comprising the steps: a) Generating a candidate policy (P) by a learner (20); b) Executing a program (80) in at least one simulated application (51, 52) based on a set of candidate parameters (PC1, PC2) provided based on the candidate policy (P) and a state (S) of the simulated application (51, 52), the execution of the program providing interim results (R1, R2) of tested sets of candidate parameters (PC1, PC2) based on a measured performance information of the execution of the program (80); c) Collecting a predetermined number of interim results (R1, R2) and providing an end result (R) based on a combination of the candidate parameters (PC) and/or the state (S) with the measured performances information by a trainer (30); and d) Generating a new candidate policy (P) by the learner (20) based on the end result (R).