JP4413291B2 - Bin picking device with position data calibration function - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a position data calibration function bin picking equipment. Specifically, the present invention provides means for calibrating the positional relationship of each device necessary for the bin picking system and the positional data necessary for component detection.
[0002]
[Prior art]
The bin picking system is a system in which the position and orientation of a target part put in a box is detected by an image measuring device, and the target part is handled by a robot arm based on the information.
In addition, as an image measuring device, feature data having three-dimensional position data obtained by stereo measurement or the like as well as data that approximates features such as contours, unevenness, and patterns of a target object obtained from an input image with straight lines, arcs, etc. And obtaining the three-dimensional position and orientation of the target object by matching with the feature data having the three-dimensional position data of the model of the target object.
[0003]
There is a model-based matching method as a method for detecting the position of a target component, and various proposals are also made as a method for producing a model of a component.
Conventionally, various proposals have been made as a method for obtaining a relative relationship between a robot arm device and an image measuring device, which is necessary for handling.
[0004]
[Problems to be solved by the invention]
In order for the bin picking system to operate correctly, the positional relationship of each device necessary for detecting the position of the target component and calculating the handling data must be known and the positional relationship must be maintained correctly.
[0005]
However, when a camera is replaced due to a camera failure, a life span, or a camera damage due to an accident, the position of the camera and the coordinate system of the image measuring apparatus associated therewith change, so that all of the existing data needs to be recreated.
In addition, when the camera position and orientation are deviated due to the secular change of the camera mounting portion, the detected position and orientation of the target component is different from the actual position and orientation, resulting in a malfunction of the system operation.
[0006]
[Means for Solving the Problems]
Position data calibration function bin picking device according to claim 1 of the present invention, reference object model is set based on the background object position of the belt conveyor or a work bench or the like existing in the camera field of view does not change, the Coordinate transformation T _VV from old vision system Σ _V, which is the previous coordinate system before replacing the camera due to life or damage, etc., to new vision system Σ _{V ′} , which is a newly set coordinate system after replacing the camera _'the new vision system sigma _V' wherein by performing model matching for the background object using the reference object model that is set in the former vision system in, the background object on which to base the new vision system sigma _{V ' Obtained by} the following formula (1) as the inverse transformation T _V'O ^-1 of the position and orientation T _V'O
T _{VV ′} = T _V′O ⁻¹ (1)
A position data calibration unit that performs position data calibration from the old vision system Σ _V to the new vision system Σ _{V ′} using the coordinate transformation T _{VV ′} ;
The position data calibration unit includes:
Based on the coordinate transformation data T _{VV ′} and the coordinate transformation T _RV from the robot system Σ _R which is the coordinate system of the robot arm device to the old vision system Σ _V , the robot system Σ _R to the new vision system Σ _{V ′.} The coordinate transformation T _{RV ′} to is calculated by the following equation (2):
T _{RV ′} = T _RV T _{VV ′} (2)
Further, the coordinate transformation T _VH to ^-1 and the hand system is a coordinate system of the object to be handled by the robotic arm mechanism from the old vision system sigma _V sigma _{H 'inverse} transform T _VV' of the coordinate transformation data T _VV Based on the following equation (3) , a coordinate transformation T _V′H from the new vision system Σ _{V ′} to the hand system Σ _H is obtained,
T _V′H = T _{VV ′} ⁻¹ T _VH (3)
Furthermore, components based on said ^-1 _'inverse transform T _VV' of the coordinate transformation data T _VV, and the point p _V component model data relative to the old vision system sigma _V based on the new vision system sigma _{V '} After performing the position data calibration by obtaining the transformation of the model data to the point p _{V ′} by the following equation (4) ,
p _{V ′} = T _{VV ′} ⁻¹ p _V (4)
It is characterized by performing normal bin picking.
[0007]
Position data calibration function bin picking device according to claim 2 of the present invention, the reference object model based on an easy mark objects identified fixed in the camera field of view is set, replace the camera in life or damage the _'coordinate transformation T _VV' to the front of the now until the coordinate system in which the old vision system Σ new vision system, which is a newly set coordinate system after replacing the camera from _V Σ _V of that, new vision system Σ _V By performing model matching on the background object using the reference object model set in the old vision system in _' , the inverse of the position and orientation T _V'O of the background object based on the new vision system Σ _V' The conversion T _V′O ⁻¹ is obtained by the following equation (1) ,
T _{VV ′} = T _V′O ⁻¹ (1)
A position data calibration unit that performs position data calibration from the old vision system Σ _V to the new vision system Σ _{V ′} using the coordinate transformation T _{VV ′} ;
The position data calibration unit includes:
Based on the coordinate transformation data T _{VV ′} and the coordinate transformation T _RV from the robot system Σ _R which is the coordinate system of the robot arm device to the old vision system Σ _V , the robot system Σ _R to the new vision system Σ _{V ′.} The coordinate transformation T _{RV ′} to is calculated by the following equation (2):
T _{RV ′} = T _RV T _{VV ′} (2)
Further, the coordinate transformation T _VH to ^-1 and the hand system is a coordinate system of the object to be handled by the robotic arm mechanism from the old vision system sigma _V sigma _{H 'inverse} transform T _VV' of the coordinate transformation data T _VV Based on the following equation (3) , a coordinate transformation T _V′H from the new vision system Σ _{V ′} to the hand system Σ _H is obtained,
T _V′H = T _{VV ′} ⁻¹ T _VH (3)
Furthermore, components based on said ^-1 _'inverse transform T _VV' of the coordinate transformation data T _VV, and the point p _V component model data relative to the old vision system sigma _V based on the new vision system sigma _{V '} After performing the position data calibration by obtaining the transformation of the model data to the point p _{V ′} by the following equation (4) ,
p _{V ′} = T _{VV ′} ⁻¹ p _V (4)
It is characterized by performing normal bin picking.
[0008]
Position data calibration function bin picking device according to claim 3 of the present invention, the mark object by a jig which had been prepared was mounted high positional accuracy as the reference object model in the camera view, the camera in life or damage The coordinate system T _{VV ′} from the old vision system Σ _V, which is the previous coordinate system before replacement, to the new vision system Σ _{V ′} , which is the newly set coordinate system after replacing the camera , is converted into the new vision system Σ. _'by performing model matching for the background object using the reference object model the set in the former vision system in the new vision system sigma _{V' V} of the position and orientation T _V'O of the background object that based on The inverse transformation T _V′O ⁻¹ is obtained by the following formula (1) ,
T _{VV ′} = T _V′O ⁻¹ (1)
A position data calibration unit that performs position data calibration from the old vision system Σ _V to the new vision system Σ _{V ′} using the coordinate transformation T _{VV ′} ;
The position data calibration unit includes:
Based on the coordinate transformation data T _{VV ′} and the coordinate transformation T _RV from the robot system Σ _R which is the coordinate system of the robot arm device to the old vision system Σ _V , the robot system Σ _R to the new vision system Σ _{V ′.} The coordinate transformation T _{RV ′} to is calculated by the following equation (2):
T _{RV ′} = T _RV T _{VV ′} (2)
Further, the coordinate transformation T _VH to ^-1 and the hand system is a coordinate system of the object to be handled by the robotic arm mechanism from the old vision system sigma _V sigma _{H 'inverse} transform T _VV' of the coordinate transformation data T _VV Based on the following equation (3) , a coordinate transformation T _V′H from the new vision system Σ _{V ′} to the hand system Σ _H is obtained,
T _V′H = T _{VV ′} ⁻¹ T _VH (3)
Furthermore, components based on said ^-1 _'inverse transform T _VV' of the coordinate transformation data T _VV, and the point p _V component model data relative to the old vision system sigma _V based on the new vision system sigma _{V '} After performing the position data calibration by obtaining the transformation of the model data to the point p _{V ′} by the following equation (4) ,
p _{V ′} = T _{VV ′} ⁻¹ p _V (4)
It is characterized by performing normal bin picking.
[0010]
A bin picking device with a position data calibration function according to a fourth aspect of the present invention is configured such that a reference part for setting a reference object model is appropriately installed on an operator side, and the camera is replaced with a product with a life or damage. the _'coordinate transformation T _{VV to'} up from the old vision system Σ _V is a coordinate system wherein the camera is a newly set coordinate system after replacing the new vision system Σ _V of now, said in the new vision system Σ _{V '} By performing model matching on the background object using the reference object model set in the old vision system, the inverse transformation T _V of the position and orientation T _V′O of the background object based on the new vision system Σ _{V ′ 'O} ^-1 is obtained by the following formula (1) ,
T _{VV ′} = T _V′O ⁻¹ (1)
Comprising a position data calibration unit that performs position data calibration using _'from the old vision system ΣV new vision system sigma _V' the coordinate transformation T _VV to,
The position data calibration unit includes:
Based on the coordinate transformation data T _{VV ′} and the coordinate transformation T _RV from the robot system Σ _R which is the coordinate system of the robot arm device to the old vision system Σ _V , the robot system Σ _R to the new vision system Σ _{V ′.} The coordinate transformation T _{RV ′} to is calculated by the following equation (2):
T _{RV ′} = T _RV T _{VV ′} (2)
Further, the coordinate transformation T _VH to ^-1 and the hand system is a coordinate system of the object to be handled by the robotic arm mechanism from the old vision system sigma _V sigma _{H 'inverse} transform T _VV' of the coordinate transformation data T _VV Based on the following equation (3) , a coordinate transformation T _V′H from the new vision system Σ _{V ′} to the hand system Σ _H is obtained,
T _V′H = T _{VV ′} ⁻¹ T _VH (3)
Furthermore, components based on said ^-1 _'inverse transform T _VV' of the coordinate transformation data T _VV, and the point p _V component model data relative to the old vision system sigma _V based on the new vision system sigma _{V '} After performing the position data calibration by obtaining the transformation of the model data to the point p _{V ′} by the following equation (4) ,
p _{V ′} = T _{VV ′} ⁻¹ p _V (4)
It is characterized by performing normal bin picking.
[0011]
[Action]
The present invention provides positional data and components necessary for the operation of the bin picking system by performing data calibration before bin picking work even when the position and orientation of the camera change due to camera replacement and camera aging. The bin picking apparatus can be operated normally without recreating all the data.
[0012]
DETAILED DESCRIPTION OF THE INVENTION
(1) Basic concept Bin picking device having a function of calibrating as needed the component data necessary for component detection registered in the memory with respect to the positional relationship of each device obtained in the initial setting The bin picking device can be used without recreating all the positional relationship data and parts data necessary for the operation of the bin picking system even when the camera position and orientation change due to camera replacement or camera aging. Can be operated normally.
[0013]
(2) Bin Picking Device with Position Data Calibration Function FIG. 1 shows an example of a bin picking device with position data calibration function according to the present invention.
This apparatus comprises an image measurement unit 1, a robot controller 2, a control unit 3, and a position data calibration unit 4. The camera (image measurement device) 5 detects the position and orientation of a target part put in the box, and the information Based on the above, position data calibration is performed as necessary before the bin picking operation for handling the target part by the robot arm 6, and after the position data calibration, a normal bin picking operation is repeated.
[0014]
(2.1) Image Measurement Unit The image measurement unit 1 performs component detection and position measurement based on an input image from the camera 5.
In the bin picking work, the position data of the camera 5, the coordinate system data of the camera 5, and the parts data of the target part are received from the control unit 3, and the position and orientation of the target part are detected based on the input image from the camera 5.
In the position data calibration operation, data necessary for position data calibration is measured based on the new coordinate system data of the camera 5, and the measurement data is sent to the position data calibration unit 4 in accordance with a command from the control unit 3.
[0015]
(2.2) Robot controller The robot controller 2 controls the overall operation of the robot arm 6.
In the bin picking work, the handling position / posture data is received from the control unit 3, the handling operation of the target component is performed, and the component is installed at a predetermined place according to the determined operation plan.
[0016]
(2.3) Control unit The control unit 3 controls the entire apparatus.
In the bin picking operation, the camera 5 position data, the camera 5 coordinate system data, and the target part data are sent to the image measuring unit 1, and the parts position and orientation data are received from the camera 5.
Further, a handling position / orientation is calculated from the position / orientation data of the part and the positional relationship data of the apparatus, and the data is sent to the robot controller 2 to issue a handling command.
[0017]
In the position data calibration work, a new coordinate system of the camera 5 is set based on the measurement data of the image measurement unit 1, and the coordinate system data and data necessary for measurement are sent to the image measurement unit 1 to perform measurement for position data calibration. Commands the data to be sent to the position data calibration unit 4.
Further, the positional relationship data of each device and the part data of the registered parts are sent to the position data calibration unit 4 to issue a data calibration command.
Thereafter, various data calibrated by the position data calibration unit 4 are received and stored in the memory.
[0018]
(2.4) Position Data Calibration Unit In the position data calibration unit 4, the conventional coordinate system of the camera 5 is based on the measurement data obtained from the image measurement unit 1 and the positional relationship data of the device stored in the control unit 3. The positional relationship with the newly set coordinate system is obtained, and the positional relationship data and the component data stored in the control unit 3 using the positional relationship data are associated with the new coordinate system of the camera 5 as follows. (See Japanese Patent Application No. 10-196965).
[0019]
(2.4.1) Coordinate system of each device and relative relationship Each coordinate system is set as shown in FIG.
Here, each coordinate system is as follows.
Σ _V : Old vision system (previous coordinate system of camera 5)
Σ _{V '} : New vision system (Camera 5's newly set coordinate system)
Σ _R : Robot system (coordinate system of robot arm 6)
Σ _H : Hand system (coordinate system when handling the target object of the hand)
[0020]
The positional relationship between each device is obtained as coordinate conversion data from the coordinate system of the device to the coordinate system of another device.
T _RV : Coordinate transformation from robot system Σ _R to old vision system Σ _V T _VH : Coordinate transformation from old vision system Σ _V to hand system Σ _H T _{RV '} : From robot system Σ _R to new vision system Σ _V' Coordinate transformation T _V′H : coordinate transformation from new vision system Σ _{V ′} to hand system Σ _H T _{VV ′} : coordinate transformation from old vision system Σ _V to new vision system Σ _{V ′}
(2.4.2) Calculation Data of Calibration Coordinate Conversion Data The conversion data necessary for calibration is the coordinate conversion data T _{VV ′} from the old vision system Σ _V to the new vision system Σ _{V ′} . This is obtained by model matching.
When a reference object part model is created in the old vision system Σ _V , the reference object is placed at the model production position, and model matching is performed using the same model in the new vision system Σ _{V ′} , the new vision system Σ The position and orientation T _V′O of the reference object based on _{V ′} can be detected.
[0022]
At this time the reference object is in a position and orientation that does not move at all in the old vision system sigma _V, just the new vision system sigma _{V 'pose} T _V'O reference object detected in the new vision system sigma _V' old vision from The coordinate transformation T _V′V to the system Σ _V is shown.
Therefore, the coordinate conversion data necessary for data calibration is obtained as follows as the coordinate conversion data T _{VV ′} from the old vision system Σ _V to the new vision system Σ _{V ′} .
T _{VV ′} = T _V′O ⁻¹ (1)
[0023]
(2.4.3) The positional relationship between the calibration robot system Σ _R and the new vision system Σ _{V ′ in} the apparatus positional relationship can be calculated as follows from the calibration coordinate conversion data and the previous positional relationship.
T _{RV ′} = T _RV T _{VV ′} (2)
The positional relationship between the new vision system Σ _{V ′} and the hand system Σ _H can be calculated from the calibration coordinate conversion data and the previous positional relationship as follows.
T _V′H = T _{VV ′} ⁻¹ T _VH (3)
[0024]
(2.4.4) Calibration of part model data The three-dimensional shape model of a part is composed of three-dimensional linear features and curved features, and these three-dimensional data are the tertiary of points on the features based on the vision system. Original position data.
Therefore, the calibration of the three-dimensional shape model of the part can be performed by coordinate conversion of the point position data constituting the model from the old vision system Σ _V to the new vision system Σ _{V ′} .
The point p _V based on the old vision system Σ _V is converted to the point p _{V ′} based on the new vision system Σ _{V ′} as follows.
[0025]
p _{V ′} = T _{VV ′} ⁻¹ p _V (4)
By reconstructing the points of the three-dimensional shape model thus converted, the three-dimensional shape model of the part can be calibrated.
If a 3D shape model based on the new vision system Σ _{V ′} is calculated, the 2D shape model on the image, which is the appearance model at the new position and orientation of the camera, is the image plane of the 3D shape model camera. Can be calibrated by perspective transformation into
[0026]
(2.4.5) Setting of reference object model (2.4.5.1) Setting of reference object model by background object When there is an object whose position does not change in the field of view of the camera, such as a belt conveyor or a workbench As shown in FIG. 2, a background object can be used as a reference object, and a reference object model can be set.
[0027]
(2.4.5.2) Setting of reference object model by fixed mark object When a fixed mark object whose position does not change in the camera field of view can be set, the fixed mark object is used as the reference object as shown in FIG. A model can be set.
[0028]
(2.4.5.3) Although the reference mark is not always attached to the setting device of the reference object model by the attachment mark object, if the attachment mark can be set by some jig during the calibration work, the attachment mark object is as shown in FIG. And a reference object model can be set.
[0029]
(2.4.5.4) Setting of reference object model by mark object attached to robot arm When mark object can be attached to robot arm, the mark object is set as the reference object as shown in FIG. A model can be set.
[0030]
(2.4.5.5) Setting of reference object model with reference parts When parts selected as reference parts for calibration work can be installed at the same position using a robot arm or the like, as shown in FIG. A reference object model can be set using a reference part as a reference object.
[0031]
(2.4.6) Position Data Calibration Method (2.4.6.1) Position Data Calibration Method Using Background Object When the position and orientation of the camera changes, the bin picking system is performed according to the following procedure according to the flowchart shown in FIG. Calibrate the position data.
(1) Set a new vision system for the camera 5.
(2) Model matching is performed using the background object model.
(3) Calculate the calibration coordinate conversion data _{TVV '} from the matching result.
{Circle around (4)} The apparatus positional relationship data is calibrated using the calibration coordinate conversion data and the previous apparatus positional relationship data.
(5) The part model data is calibrated using the calibration coordinate conversion data and the part model data so far.
[0032]
(2.4.6.2) Position Data Calibration Method Using Fixed Mark Object When the position and orientation of the camera change, the position data of the bin picking system is calibrated according to the following procedure according to the flowchart shown in FIG.
(1) Set a new vision system for the camera 5.
(2) Model matching is performed using a fixed mark object model.
(3) Calculate the calibration coordinate conversion data _{TVV '} from the matching result.
{Circle around (4)} The apparatus positional relationship data is calibrated using the calibration coordinate conversion data and the previous apparatus positional relationship data.
(5) The part model data is calibrated using the calibration coordinate conversion data and the part model data so far.
[0033]
(2.4.6.3) Position Data Calibration Method Using Attachment Mark Object When the position and orientation of the camera changes, the position data of the bin picking system is calibrated according to the following procedure according to the flowchart shown in FIG.
(1) Set a new vision system for the camera 5.
(2) Model matching is performed using the mounting mark object model.
(3) Calculate the calibration coordinate conversion data _{TVV '} from the matching result.
{Circle around (4)} The apparatus positional relationship data is calibrated using the calibration coordinate conversion data and the previous apparatus positional relationship data.
(5) The part model data is calibrated using the calibration coordinate conversion data and the part model data so far.
[0034]
(2.4.6.4) Position Data Calibration Method Using Mark Object Attached to Robot Arm When the position and orientation of the camera changes, the position data of the bin picking system is calibrated according to the following procedure according to the flowchart shown in FIG. .
(1) Set a new vision system for the camera 5.
(2) Model matching is performed using a mark object model attached to the robot arm 6.
(3) Calculate the calibration coordinate conversion data _{TVV '} from the matching result.
{Circle around (4)} The apparatus positional relationship data is calibrated using the calibration coordinate conversion data and the previous apparatus positional relationship data.
(5) The part model data is calibrated using the calibration coordinate conversion data and the part model data so far.
[0035]
(2.4.6.5) Position Data Calibration Method Using Reference Parts When the position and orientation of the camera changes, the position data of the bin picking system is calibrated according to the following procedure according to the flowchart shown in FIG.
(1) Set a new vision system for the camera 5.
(2) Model matching is performed using a reference part model.
(3) Calculate the calibration coordinate conversion data _{TVV '} from the matching result.
{Circle around (4)} The apparatus positional relationship data is calibrated using the calibration coordinate conversion data and the previous apparatus positional relationship data.
(5) The part model data is calibrated using the calibration coordinate conversion data and the part model data so far.
[0036]
(3) Operation Procedure of Bin Picking Device with Position Data Calibration Function In the present invention, according to the flowchart shown in FIG. 12, position data calibration is performed as follows before bin picking work as necessary.
(1) First, a new coordinate system of the camera 5 is set.
(2) Next, position data calibration is performed as shown in (2.4.1) to (2.4.6), and the positional relationship data and component data are updated to data corresponding to the new coordinate system.
After such a position data calibration procedure, a normal bin picking operation is performed according to the flowchart shown in FIG.
[0037]
(3) The position and orientation of the target part is detected by image measurement based on the part data.
(4) The handling position and orientation are calculated from the positional relationship data and the position and orientation of the part obtained in (3).
(5) The robot controller 2 moves the hand of the robot arm 6 to the handling position / posture.
(6) Handle the target part.
(7) The robot arm 6 is operated to place the handled target part at a predetermined location.
In normal operation, steps (3) to (7) are repeated until the work is completed.
[0038]
【The invention's effect】
As described above in detail based on the embodiments, according to the present invention, the position data necessary for the bin picking system can be obtained even when the camera is replaced due to a camera failure, a life span, a camera damage due to an accident, or the like. Since it can be calibrated, it has the following effects.
(1) It is not necessary to recreate all the data so far.
(2) The working time due to work associated with camera replacement can be greatly reduced.
(3) It is easy to handle a large amount of part model data, and can easily cope with a process that handles a variety of products.
(4) A database of a large amount of part model data created in the past can be handled efficiently.
(5) The work cost associated with camera replacement can be reduced.
(6) It is possible to reduce the burden on the operator due to camera replacement.
(7) Camera replacement work can be easily performed.
(8) By periodically calibrating the position data, the system can continue to operate normally even if there is a slight shift in the position and orientation of the camera due to aging of the camera mounting portion.
(9) Periodic position data calibration improves system reliability.
[Brief description of the drawings]
FIG. 1 is a configuration diagram illustrating a bin picking device with a position data calibration function according to an embodiment of the present invention.
FIG. 2 is an explanatory diagram showing a reference object model based on a background object.
FIG. 3 is an explanatory diagram showing a reference object model using a fixed mark object.
FIG. 4 is an explanatory diagram showing a reference object model based on an attachment mark object.
FIG. 5 is an explanatory diagram showing a reference object model based on a mark object attached to a robot arm.
FIG. 6 is an explanatory diagram showing a reference object model based on reference parts.
FIG. 7 is a flowchart showing a position data calibration method using a background object.
FIG. 8 is a flowchart showing a position data calibration method using a fixed mark object.
FIG. 9 is a flowchart illustrating a position data calibration method using an attachment mark object.
FIG. 10 is a flowchart illustrating a position data calibration method using a mark object attached to a robot arm.
FIG. 11 is a flowchart showing a position data calibration method using a reference part.
FIG. 12 is a flowchart illustrating a bin picking process with a position data calibration function according to an embodiment of the present invention.
FIG. 13 is an explanatory diagram showing a coordinate system used for position data calibration.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 Image system side part 2 Robot controller 3 Control part 4 Position data calibration part 5 Camera (image measuring device)
6 Robotic arm

Claims (4)

This is a conventional coordinate system in which a reference object model is set based on a background object that does not change the position of a belt conveyor or workbench that exists in the field of view of the camera, and before the camera is replaced due to life or damage. The coordinate transformation T _{VV ′} from the old vision system Σ _V to the new vision system Σ _{V ′} , which is a newly set coordinate system after replacing the camera, is set in the new vision system Σ _{V ′} in the old vision system By performing model matching with respect to the background object using the reference object model, the following formula is _obtained as an inverse transformation T _V′O ⁻¹ of the position and orientation T _V′O of the background object based on the new vision system Σ _{V ′.} Obtained by (1)
T _{VV ′} = T _V′O ⁻¹ (1)
A position data calibration unit that performs position data calibration from the old vision system Σ _V to the new vision system Σ _{V ′} using the coordinate transformation T _{VV ′} ;
The position data calibration unit includes:
Based on the coordinate transformation data T _{VV ′} and the coordinate transformation T _RV from the robot system Σ _R which is the coordinate system of the robot arm device to the old vision system Σ _V , the robot system Σ _R to the new vision system Σ _{V ′.} The coordinate transformation T _{RV ′} to is calculated by the following equation (2):
T _{RV ′} = T _RV T _{VV ′} (2)
Further, the coordinate transformation T _VH to ^-1 and the hand system is a coordinate system of the object to be handled by the robotic arm mechanism from the old vision system sigma _V sigma _{H 'inverse} transform T _VV' of the coordinate transformation data T _VV Based on the following equation (3) , a coordinate transformation T _V′H from the new vision system Σ _{V ′} to the hand system Σ _H is obtained,
T _V′H = T _{VV ′} ⁻¹ T _VH (3)
Furthermore, components based on said ^-1 _'inverse transform T _VV' of the coordinate transformation data T _VV, and the point p _V component model data relative to the old vision system sigma _V based on the new vision system sigma _{V '} After performing the position data calibration by obtaining the transformation of the model data to the point p _{V ′} by the following equation (4) ,
p _{V ′} = T _{VV ′} ⁻¹ p _V (4)
A bin picking device with a position data calibration function, wherein normal bin picking is performed. Reference object model based on an easy mark objects identified fixed in the camera field of view is set, the camera from the old vision system sigma _V is a coordinate system of ever before replacing the camera with life or damage Using the reference object model set in the old vision system in the new vision system Σ _{V ′} , the coordinate transformation T _{VV ′} to the new vision system Σ _{V ′} , which is a newly set coordinate system after replacing the by performing model matching for background objects, determined by the following equation (1) as the inverse transformation T _V'O ^-1 of the position and orientation T _V'O of the background objects backed by a new vision system sigma _{V ',}
T _{VV ′} = T _V′O ⁻¹ (1)
A position data calibration unit that performs position data calibration from the old vision system Σ _V to the new vision system Σ _{V ′} using the coordinate transformation T _{VV ′} ;
The position data calibration unit includes:
Based on the coordinate transformation data T _{VV ′} and the coordinate transformation T _RV from the robot system Σ _R which is the coordinate system of the robot arm device to the old vision system Σ _V , the robot system Σ _R to the new vision system Σ _{V ′.} The coordinate transformation T _{RV ′} to is calculated by the following equation (2):
T _{RV ′} = T _RV T _{VV ′} (2)
Further, the coordinate transformation T _VH to ^-1 and the hand system is a coordinate system of the object to be handled by the robotic arm mechanism from the old vision system sigma _V sigma _{H 'inverse} transform T _VV' of the coordinate transformation data T _VV Based on the following equation (3) , a coordinate transformation T _V′H from the new vision system Σ _{V ′} to the hand system Σ _H is obtained,
T _V′H = T _{VV ′} ⁻¹ T _VH (3)
Furthermore, components based on said ^-1 _'inverse transform T _VV' of the coordinate transformation data T _VV, and the point p _V component model data relative to the old vision system sigma _V based on the new vision system sigma _{V '} After performing the position data calibration by obtaining the transformation of the model data to the point p _{V ′} by the following equation (4) ,
p _{V ′} = T _{VV ′} ⁻¹ p _V (4)
A bin picking device with a position data calibration function, wherein normal bin picking is performed. Wherein the mark object by prepared in advance jig mounted high positional accuracy as the reference object model in the camera field of view, from the old vision system sigma _V is a coordinate system before the now replacing the camera with life or damage Using the reference object model set in the old vision system in the new vision system Σ _{V ′} , the coordinate transformation T _{VV ′} to the new vision system Σ _{V ′} , which is a newly set coordinate system after the camera is replaced. wherein by performing model matching for background objects, determined by the following equation (1) as the inverse transformation T _V'O ^-1 of the position and orientation T _V'O of the background objects backed by a new vision system sigma _{V ',}
T _{VV ′} = T _V′O ⁻¹ (1)
A position data calibration unit that performs position data calibration from the old vision system Σ _V to the new vision system Σ _{V ′} using the coordinate transformation T _{VV ′} ;
The position data calibration unit includes:
Based on the coordinate transformation data T _{VV ′} and the coordinate transformation T _RV from the robot system Σ _R which is the coordinate system of the robot arm device to the old vision system Σ _V , the robot system Σ _R to the new vision system Σ _{V ′.} The coordinate transformation T _{RV ′} to is calculated by the following equation (2):
T _{RV ′} = T _RV T _{VV ′} (2)
Further, the coordinate transformation T _VH to ^-1 and the hand system is a coordinate system of the object to be handled by the robotic arm mechanism from the old vision system sigma _V sigma _{H 'inverse} transform T _VV' of the coordinate transformation data T _VV Based on the following equation (3) , a coordinate transformation T _V′H from the new vision system Σ _{V ′} to the hand system Σ _H is obtained,
T _V′H = T _{VV ′} ⁻¹ T _VH (3)
Furthermore, components based on said ^-1 _'inverse transform T _VV' of the coordinate transformation data T _VV, and the point p _V component model data relative to the old vision system sigma _V based on the new vision system sigma _{V '} After performing the position data calibration by obtaining the transformation of the model data to the point p _{V ′} by the following equation (4) ,
p _{V ′} = T _{VV ′} ⁻¹ p _V (4)
A bin picking device with a position data calibration function, wherein normal bin picking is performed. The camera was replaced from the old vision system Σ _V , which was the previous coordinate system in which the reference parts for setting the reference object model were properly installed on the operator side, and the camera was replaced before its lifetime or damage . with respect to the background object using the reference object model to a newly set coordinate system _'coordinate transformation T _VV' to the new vision system sigma _V, set by the old vision system in the new vision system sigma _{V 'after} By performing model matching , the inverse transformation T _V′O ⁻¹ of the position and orientation T _V′O of the background object based on the new vision system Σ _{V ′} is obtained by the following equation (1) :
T _{VV ′} = T _V′O ⁻¹ (1)
Comprising a position data calibration unit that performs position data calibration using _'from the old vision system ΣV new vision system sigma _V' the coordinate transformation T _VV to,
The position data calibration unit includes:
Based on the coordinate transformation data T _{VV ′} and the coordinate transformation T _RV from the robot system Σ _R which is the coordinate system of the robot arm device to the old vision system Σ _V , the robot system Σ _R to the new vision system Σ _{V ′.} The coordinate transformation T _{RV ′} to is calculated by the following equation (2):
T _{RV ′} = T _RV T _{VV ′} (2)
Further, the coordinate transformation T _VH to ^-1 and the hand system is a coordinate system of the object to be handled by the robotic arm mechanism from the old vision system sigma _V sigma _{H 'inverse} transform T _VV' of the coordinate transformation data T _VV Based on the following equation (3) , a coordinate transformation T _V′H from the new vision system Σ _{V ′} to the hand system Σ _H is obtained,
T _V′H = T _{VV ′} ⁻¹ T _VH (3)
Furthermore, components based on said ^-1 _'inverse transform T _VV' of the coordinate transformation data T _VV, and the point p _V component model data relative to the old vision system sigma _V based on the new vision system sigma _{V '} After performing the position data calibration by obtaining the transformation of the model data to the point p _{V ′} by the following equation (4) ,
p _{V ′} = T _{VV ′} ⁻¹ p _V (4)
A bin picking device with a position data calibration function, wherein normal bin picking is performed.

Images