-
公开(公告)号:US20240375283A1
公开(公告)日:2024-11-14
申请号:US18577832
申请日:2021-09-07
Applicant: ABB SCHWEIZ AG
Abstract: A method, an electronic device, and a computer readable storage medium for calibrating a robot. The method includes obtaining a first set of data related to at least one of position and orientation of at least three calibration objects. The method includes determining a second set of data related to at least one of position and orientation of the at least three calibration objects when the target object is in a second state different from the first state; determining a transformation relationship between the first set of data and the second set of data; determining a calibrated object coordinate system based on the object coordinate system and the transformation relationship; and controlling the robot to process the target object in a predetermined way under the calibrated object coordinate system.
-
公开(公告)号:US20240308078A1
公开(公告)日:2024-09-19
申请号:US18576694
申请日:2021-09-22
Applicant: ABB SCHWEIZ AG
CPC classification number: B25J9/1692 , B25J9/1653 , B25J13/089
Abstract: A method and an electronic device for calibrating a robot. The method includes obtaining at least two sets of positional data of a first reference point in a base coordinate system of the robot, the first reference point fixedly arranged on the external axis, the at least two sets of positional data corresponding to at least two positions of the first reference point during movement of the external axis. The method includes determining a transformation relationship between the base coordinate system and an user coordinate system of the external axis according to the at least two sets of positional data, determining the calibrated user coordinate system based on the base coordinate system and the transformation relationship, and controlling the robot to process an object arranged on the external axis under the calibrated user coordinate system.
-
公开(公告)号:US20240383145A1
公开(公告)日:2024-11-21
申请号:US18576713
申请日:2021-09-10
Applicant: ABB SCHWEIZ AG
Inventor: Kun Chang , Wenyao Shao , Dianfei Xia
IPC: B25J9/16
Abstract: Methods, apparatuses, systems, and computer readable media for managing a tool in a robot system. In a method, a plurality of arm positions of a robot arm of the robot system are obtained when the tool is placed under a posture on a surface of a calibration object for calibrating the tool, where the posture represents rotation parameters of the robot arm. A center of the calibration object is determined based on the plurality of arm positions. A reference position of the robot arm is generated for calibrating the tool based a position of the center and the posture.
-
公开(公告)号:US20240261965A1
公开(公告)日:2024-08-08
申请号:US18639696
申请日:2024-04-18
Applicant: ABB SCHWEIZ AG
Inventor: Dianfei Xia , Kun Chang , Jiacheng Wang
CPC classification number: B25J9/1653 , B25J13/089 , G01B5/008
Abstract: A method and an apparatus for calibrating a crankshaft to be processed. The method includes causing a positioner to rotate to at least three different angles. The positioner is configured to support the crankshaft and drive the crankshaft to rotate. The method also includes causing a probe to touch a plurality of points on a first cylindrical crankpin of the crankshaft respectively to obtain coordinates of the plurality of points in a robot coordinate system; fitting the coordinates of the plurality of points on the first cylindrical crankpin respectively to obtain a respective pose of the first cylindrical crankpin relative to the robot coordinate system; and determining a pose of a rotating axis of the crankshaft relative to the robot coordinate system based on the respective pose of the first cylindrical crankpin.
-
公开(公告)号:US20240087105A1
公开(公告)日:2024-03-14
申请号:US18263009
申请日:2021-01-26
Applicant: ABB Schweiz AG
Inventor: Nevroz Sen , WenLong Li , Amber-FengQin Zhu , Kun Chang
IPC: G06T7/00
CPC classification number: G06T7/0004 , G06T2207/20081 , G06T2207/20084 , G06T2207/30156
Abstract: A method for detecting paint defects on objects is provided. The method comprises: projecting a plurality of patterns on a surface of an object at a plurality of different pattern characteristics; capturing a plurality of images of the object based on projecting the plurality of patterns; inputting the plurality of images of the object into a machine learning model to determine whether the surface of the object includes one or more paint defects; and based on determining, an image, of the plurality of images, includes a paint defect, causing display of the image with the paint defect.
-
-
-
-