CN113814984B - Dynamic image positioning method and system for robot emptying - Google Patents

Dynamic image positioning method and system for robot emptying Download PDF

Info

Publication number
CN113814984B
CN113814984B CN202111223243.8A CN202111223243A CN113814984B CN 113814984 B CN113814984 B CN 113814984B CN 202111223243 A CN202111223243 A CN 202111223243A CN 113814984 B CN113814984 B CN 113814984B
Authority
CN
China
Prior art keywords
detected
standard
mechanical arm
image
deviation value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111223243.8A
Other languages
Chinese (zh)
Other versions
CN113814984A (en
Inventor
杨峥嵘
刘浩东
高志鹏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Universal Scientific Industrial Shanghai Co Ltd
Original Assignee
Universal Scientific Industrial Shanghai Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Universal Scientific Industrial Shanghai Co Ltd filed Critical Universal Scientific Industrial Shanghai Co Ltd
Priority to CN202111223243.8A priority Critical patent/CN113814984B/en
Priority to TW110143433A priority patent/TWI778870B/en
Publication of CN113814984A publication Critical patent/CN113814984A/en
Application granted granted Critical
Publication of CN113814984B publication Critical patent/CN113814984B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J15/00—Gripping heads and other end effectors
    • B25J15/06—Gripping heads and other end effectors with vacuum or magnetic holding means
    • B25J15/0616—Gripping heads and other end effectors with vacuum or magnetic holding means with vacuum
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
    • B25J9/1697—Vision controlled systems

Abstract

The invention provides a dynamic image positioning method and a system for robot discharging, which comprises a mechanical arm reciprocating between a material taking station and a discharging station and a camera device arranged between the material taking station and the discharging station, wherein the method comprises the following steps: controlling a material taking end of the mechanical arm to absorb the material to be measured from the material taking station and move to the material placing station; when the material taking end of the mechanical arm moves to the visual field range of the camera device, controlling the camera device to take a picture to obtain an image to be processed; identifying the edge line of the material to be detected on the image to be processed, and further calculating the positioning deviation value of the material to be detected; and moving the material taking end of the mechanical arm to be right above the material placing station, and adjusting the posture of the mechanical arm to place materials according to the positioning deviation value. According to the scheme, the robot does not need to stop moving, and the actual photographing position does not need to be tested repeatedly, so that the positioning and discharging efficiency of the robot is higher, and the cost is lower.

Description

Dynamic image positioning method and system for robot emptying
Technical Field
The invention relates to the technical field of positioning transportation, in particular to a dynamic image positioning method and a dynamic image positioning system for robot emptying.
Background
In recent years, with the increase in the demand for electronic products, the investment in automation equipment for producing electronic products has become more and more widespread.
Aiming at the loading and unloading of a robot, the prior art is that a material to be measured is captured to be placed, a static image capturing and positioning mode is adopted, namely the robot stops at a fixed position above a camera, the camera captures an image after the robot stops stably and is set for a certain time, then a positioning deviation value of the material and a target position is calculated according to an image, the robot starts to remove the target position, and finally the positioning deviation value is added during placement, so that the material is placed accurately. The method has the disadvantages that the object to be tested needs to be fixed during image capture, namely, the arm completely stops in the image capture time period, the efficiency is not maximized, the image capture machine only needs to be used once, if abnormal conditions such as image blurring occur, the positioning deviation value cannot be calculated according to the image, the robot needs to give up the material placement, and the robot testing efficiency is not high.
One current technique is to use a triggered sensor between the robot and the camera to achieve synchronization of the motion, i.e. the robot passes the sensor in front of the camera, and the sensor senses the robot and triggers the taking of a picture. The distance between the sensor and the actual photographing position needs to be tested repeatedly so as to ensure that the photographing signal triggered by the sensor can enable the camera to photograph when the robot just walks to the fixed position above the camera. The disadvantage of this approach is the hardware cost of requiring one more sensor and the time involved to repeatedly test the distance of the actual photo location. Therefore, a robot emptying positioning method which is higher in efficiency and lower in cost and does not need to test the actual photographing position repeatedly is needed.
Disclosure of Invention
The invention aims to provide a dynamic image positioning method and a dynamic image positioning system for robot emptying, which solve the problems that in the prior art, when emptying is positioned, a robot needs to stop moving, or the cost needs to be increased and the actual photographing position needs to be tested repeatedly.
The technical scheme provided by the invention is as follows:
the invention provides a dynamic image positioning method for robot discharging, which comprises a mechanical arm reciprocating between a material taking station and a discharging station, and a camera device arranged between the material taking station and the discharging station, and comprises the following steps:
controlling a material taking end of the mechanical arm to absorb a material to be measured from the material taking station and move to the material placing station;
when the material taking end of the mechanical arm moves to the visual field range of the camera device, controlling the camera device to take a picture to obtain an image to be processed;
identifying the edge line of the material to be detected on the image to be processed, and further calculating the positioning deviation value of the material to be detected;
and controlling the material taking end of the mechanical arm to move to the position right above the material placing station, and adjusting the posture of the mechanical arm to place materials according to the positioning deviation value.
The camera device is arranged between the material taking station and the material placing station, so that when the material taking end of the robot control mechanical arm absorbs materials to be tested from the material taking station and moves to the visual field range of the camera device, the camera device can be directly controlled to take pictures to obtain images to be processed, the edge line of the materials to be tested on the images to be processed is identified, the positioning deviation value of the materials to be tested can be calculated, and the robot can adjust the posture of the mechanical arm according to the positioning deviation value to realize accurate material placing. Because the camera shooting device directly gives a trigger signal to the camera shooting device through a software communication mode by the robot when shooting, and the trigger of the sensor is not needed, the robot does not need to stop moving, and the shooting position of the actual camera shooting device does not need to be tested repeatedly, so that the positioning and discharging efficiency of the robot is higher, and the cost is lower.
Furthermore, at least one pair of suckers is arranged at the material taking end of the mechanical arm, one sucker in each pair is used for sucking the material to be detected, and the other sucker is vacant;
calculating the positioning deviation value of the material to be detected specifically comprises:
identifying the edge line of the material to be detected on the image to be processed and the corresponding edge line of the vacant sucker;
and calculating the positioning deviation value of the material to be detected according to the edge line of the material to be detected and the edge line of the vacant sucker.
Specifically, when setting up the reference position, in order to guarantee the accuracy of location, can set up at least a pair of sucking disc at the material taking end of robotic arm, every is used for absorbing the material that awaits measuring in every sucking disc, and another is vacant, because the relative position of two sucking discs is fixed for when handling pending image, through the edge line of discerning the material that awaits measuring on the pending image to and the edge line of the vacant sucking disc that corresponds, just can calculate the location deviation value of the material that awaits measuring.
Furthermore, the suckers are provided with characteristic points;
calculating the positioning deviation value of the material to be detected specifically comprises:
identifying characteristic points of the vacant suckers on the image to be processed and edge lines of the material to be detected on the image to be processed;
acquiring a first deviation value between a standard center point of a standard material to be detected and a standard characteristic point of a standard sucker;
calculating the central point of the material to be detected according to the edge line of the material to be detected;
calculating a second deviation value between the center point of the material to be detected and the characteristic point of the vacant sucker;
and calculating the positioning deviation value of the material to be detected according to the first deviation value and the second deviation value.
By arranging the characteristic points on the suckers, when an image to be processed is processed, the characteristic points of the suckers which are arranged on the image to be processed in an empty mode and the edge lines of the material to be detected on the image to be processed can be identified, and then the central point of the material to be detected can be calculated according to the edge lines of the material to be detected; meanwhile, the positioning deviation value of the material to be measured can be calculated by acquiring a first deviation value between the standard center point of the standard material to be measured and the standard characteristic point of the standard sucker and a second deviation value between the center point of the material to be measured and the characteristic point of the empty sucker.
Further, the positioning deviation value includes an offset amount and an offset angle.
Further, in the plane coordinate system, the offset (X, Y) is calculated by the formula:
X＝(X 0 -X' 0 )+X 0 *cos(θ 0 -θ' 0 )-Y 0 *sin(θ 0 -θ' 0 )，
Y＝(Y 0 -Y' 0 )+Y 0 *cos(θ 0 -θ' 0 )-Y 0 *sin(θ 0 -θ' 0 )；
the offset angle θ is calculated as:
θ＝θ 0 -θ' 0 ；
wherein the standard central point corresponding to the standard material to be measured is (X) 1 ,Y 1 ) The corresponding standard characteristic point of the standard sucker is (X) b ,Y b ) Corresponding to an offset angle of theta 0 ，
X 0 ＝X b -X 1 ，Y 0 ＝Y b -Y 1 ，θ 0 ＝arctan|-Y 0 /X 0 |；
The central point of the material to be detected is (X ', Y'), and the corresponding characteristic point of the vacant sucker is (X b '，Y b ') and the corresponding offset angle is theta' 0 ，
X' 0 ＝X' b -X'，Y' 0 ＝Y' b -Y'，θ' 0 ＝arctan|-Y' 0 /X' 0 |。
Further, before identifying the edge line of the material to be detected on the image to be processed, the method further includes:
the coordinates of the standard characteristic points of the standard sucker and the coordinates of the standard central point of the standard material to be measured are recorded in advance, the standard central point of the standard material and the standard characteristic point of the standard sucker are respectively the material central point when the material taking end of the mechanical arm is preset right above the material placing station and the standard characteristic point of the vacant sucker.
Further, still include:
when the material taking end of the mechanical arm moves to the visual field range of the camera device, controlling the camera device to take pictures to obtain a plurality of images to be processed;
calculating a plurality of positioning deviation values of the material to be detected according to the images to be processed respectively;
and adjusting the posture of the mechanical arm according to the average value of the positioning deviation values.
In addition, the invention also provides a dynamic image positioning system for robot emptying, which comprises:
the robot is provided with a mechanical arm which reciprocates between a material taking station and a material placing station, and controls a material taking end of the mechanical arm to absorb a material to be detected from the material taking station and move to the material placing station;
the camera device is arranged between the material taking station and the material placing station, and when the robot moves to the visual field range of the camera device at the material taking end of the mechanical arm, the camera device is controlled to take a picture to obtain an image to be processed;
the image processing end is used for identifying the edge line of the material to be detected on the image to be processed so as to calculate the positioning deviation value of the material to be detected;
and when the material taking end of the mechanical arm moves to a position right above the material placing station, the robot adjusts the posture of the mechanical arm to place materials according to the positioning deviation value.
The camera device is arranged between the material taking station and the material placing station, so that when the material taking end of the robot control mechanical arm absorbs materials to be tested from the material taking station and moves to the visual field range of the camera device, the camera device can be directly controlled to take pictures to obtain images to be processed, the edge line of the materials to be tested on the images to be processed is identified, the positioning deviation value of the materials to be tested can be calculated, and the robot can adjust the posture of the mechanical arm according to the positioning deviation value to realize accurate material placing. Because the camera shooting device directly gives a trigger signal to the camera shooting device through a software communication mode by the robot when shooting, and the trigger of the sensor is not needed, the robot does not need to stop moving, and the shooting position of the actual camera shooting device does not need to be tested repeatedly, so that the positioning and discharging efficiency of the robot is higher, and the cost is lower.
Furthermore, at least one pair of suckers is arranged at the material taking end of the mechanical arm, one sucker in each pair is used for sucking the material to be detected, and the other sucker is vacant;
and the image processing end identifies the edge line of the material to be detected on the image to be processed and the corresponding edge line of the vacant sucker, and calculates the positioning deviation value of the material to be detected according to the edge line of the material to be detected and the edge line of the vacant sucker.
Specifically, when setting up the reference position, in order to guarantee the accuracy of location, can set up at least a pair of sucking disc at the material taking end of robotic arm, every is used for absorbing the material that awaits measuring in every sucking disc, and another is vacant, because the relative position of two sucking discs is fixed for when handling pending image, through the edge line of discerning the material that awaits measuring on the pending image to and the edge line of the vacant sucking disc that corresponds, just can calculate the location deviation value of the material that awaits measuring.
Furthermore, the suckers are provided with characteristic points;
the image processing end identifies characteristic points of the vacant suckers on the image to be processed and edge lines of the material to be detected on the image to be processed, and calculates the central point of the material to be detected according to the edge lines of the material to be detected;
the image processing end obtains a first deviation value of a standard center point of a standard material to be measured and a standard characteristic point of a standard sucker and a second deviation value of the center point of the material to be measured and the characteristic point of the empty sucker, and calculates the positioning deviation value of the material to be measured according to the first deviation value and the second deviation value.
By arranging the characteristic points on the suckers, when an image to be processed is processed, the characteristic points of the suckers which are arranged on the image to be processed in an empty mode and the edge lines of the material to be detected on the image to be processed can be identified, and then the central point of the material to be detected can be calculated according to the edge lines of the material to be detected; meanwhile, the positioning deviation value of the material to be measured can be calculated by acquiring a first deviation value between a standard center point of the standard material to be measured and a standard characteristic point of the standard sucker and a second deviation value between the center point of the material to be measured and the characteristic point of the empty sucker.
According to the dynamic image positioning method and system for robot discharging provided by the invention, the camera device is arranged between the material taking station and the discharging station, so that when the material taking end of the robot control mechanical arm sucks the material to be detected from the material taking station and moves to the visual field range of the camera device, the camera device can be directly controlled to take a picture to obtain an image to be processed, the edge line of the material to be detected on the image to be processed is identified, the positioning deviation value of the material to be detected can be calculated, and the robot adjusts the posture of the mechanical arm according to the positioning deviation value, so that accurate discharging can be realized. Because the camera shooting device directly gives a trigger signal to the camera shooting device through a software communication mode by the robot when shooting, and the trigger of the sensor is not needed, the robot does not need to stop moving, and the shooting position of the actual camera shooting device does not need to be tested repeatedly, so that the positioning and discharging efficiency of the robot is higher, and the cost is lower.
Drawings
The foregoing features, technical features, advantages and embodiments of the present invention will be further explained in the following detailed description of the preferred embodiments, which is to be read in connection with the accompanying drawings.
FIG. 1 is a schematic overall flow diagram of an embodiment of the present invention;
FIG. 2 is a schematic view of a robot reclaiming end of an embodiment of the present invention;
FIG. 3 is a schematic bottom view of a material pick-up end of a robotic arm according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of an embodiment of the present invention;
FIG. 5 is another schematic flow chart of an embodiment of the present invention;
fig. 6 is a schematic system structure according to an embodiment of the present invention.
Reference numbers in the figures: 1-a sucker; 2-materials to be detected; 3-feature points; 4-a robot; 5-a camera device; 6-image processing end.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description will be made with reference to the accompanying drawings. It is obvious that the drawings in the following description are only some examples of the invention, and that for a person skilled in the art, other drawings and embodiments can be derived from them without inventive effort.
For the sake of simplicity, the drawings only schematically show the parts relevant to the present invention, and they do not represent the actual structure as a product. In addition, in order to make the drawings concise and understandable, components having the same structure or function in some of the drawings are only schematically illustrated or only labeled. In this document, "one" means not only "only one" but also a case of "more than one".
Example 1
In an embodiment of the present invention, as shown in fig. 1, the present invention provides a dynamic image positioning method for robot material placing, including a mechanical arm reciprocating between a material taking station and a material placing station, and a camera device disposed between the material taking station and the material placing station. The mechanical arm is a multi-joint mechanical arm, is controlled by a robot and is used for realizing the grabbing, transporting and placing of materials. Preferably, the camera device can be arranged at a position close to the emptying station.
The scheme comprises the following steps:
s1, controlling a material taking end of a mechanical arm to absorb a material to be detected from a material taking station and moving the material taking end to a material placing station.
Specifically, when the material end of getting of arm is shifting the material, can adopt the absorbent mode of sucking disc, can not make material positional deviation great, in other embodiments, can also snatch modes such as. In addition, this scheme can not stop in the middle of the arm when shifting the material, also can not slow down to guarantee work efficiency.
And S2, when the material taking end of the mechanical arm moves to the visual field range of the camera device, controlling the camera device to take a picture to obtain an image to be processed.
Specifically, when the material taking end of the mechanical arm moves to the visual field range of the camera device, the robot gives a trigger signal to the camera device through a software communication mode, so that the camera device starts to take a picture. The camera device can directly acquire the top view of the material taking end of the mechanical arm. Different from the common sensor triggering mode in the prior art, the mode can enable the camera device to be prepared for taking pictures in advance, so that the mechanical arm does not need to be stopped or decelerated. The camera device can be an industrial camera and the like, and can be a high-frame-rate global shutter camera in order to ensure that the camera device obtains clear images to be processed in the continuous movement of the mechanical arm.
And S3, identifying the edge line of the material to be detected on the image to be processed, and further calculating the positioning deviation value of the material to be detected.
After the image to be processed is obtained, the edge line of the material to be detected on the processed image can be identified through image analysis, and therefore the positioning deviation value of the material to be detected is calculated.
And S4, controlling the material taking end of the mechanical arm to move right above the material placing station, and adjusting the posture of the mechanical arm according to the positioning deviation value.
Specifically, after the positioning deviation value of the material to be detected is calculated, the posture of the mechanical arm can be adjusted, so that the position of the material to be detected returns to the standard position, the standardized discharging is realized, and the transportation, the test and the like after the material to be detected are facilitated.
The camera device is arranged between the material taking station and the material placing station, so that when the material taking end of the robot control mechanical arm absorbs materials to be tested from the material taking station and moves to the visual field range of the camera device, the camera device can be directly controlled to take pictures to obtain images to be processed, the edge line of the materials to be tested on the images to be processed is identified, the positioning deviation value of the materials to be tested can be calculated, and the robot can adjust the posture of the mechanical arm according to the positioning deviation value to realize accurate material placing. Because the camera shooting device directly gives a trigger signal to the camera shooting device through a software communication mode by the robot when shooting, and the trigger of the sensor is not needed, the robot does not need to stop moving, and the shooting position of the actual camera shooting device does not need to be tested repeatedly, so that the positioning and discharging efficiency of the robot is higher, and the cost is lower.
Example 2
In an embodiment of the present invention, as shown in fig. 2 and 3, on the basis of embodiment 1, at least one pair of suction cups 1 is disposed at a material taking end of a mechanical arm, one of each pair of suction cups 1 is used for sucking a material 2 to be measured, and the other suction cup is empty.
Specifically, in this scheme, can adopt the absorbent mode of sucking disc to shift the material, in addition, for the convenience of deviation location, can set up sucking disc 1 into at least a pair of, every is used for absorbing material 2 that awaits measuring to one in the sucking disc 1, and another vacancy, two sucking discs relative position are fixed to can use the vacancy sucking disc as the reference, calculate the deviation degree of the material that awaits measuring.
As shown in fig. 4, calculating the positioning deviation value of the material to be measured specifically includes:
s31, identifying the edge line of the material to be detected on the image to be processed and the corresponding edge line of the vacant sucker.
And S32, calculating the positioning deviation value of the material to be detected according to the edge line of the material to be detected and the edge line of the vacant sucker.
Specifically, when setting up the reference position, in order to guarantee the accuracy of location, can set up at least a pair of sucking disc 1 at the material end of getting of robotic arm, every is used for absorbing the material that awaits measuring in every sucking disc 1, and another is vacant, because the relative position of two sucking discs 1 is fixed for when handling pending image, through the edge line of discerning the material that awaits measuring 2 on the pending image to and the edge line of the vacant sucking disc that corresponds, just can calculate the location deviation value of the material that awaits measuring.
Preferably, the suction cups 1 are each provided with a characteristic point 3.
As shown in fig. 5, calculating the positioning deviation value of the material to be measured specifically includes:
and S33, identifying the characteristic points of the vacant suckers on the image to be processed and the edge lines of the material to be detected on the image to be processed.
S34, acquiring a first deviation value between a standard center point of the standard material to be detected and a standard characteristic point of the standard sucker.
And S35, calculating the central point of the material to be detected according to the edge line of the material to be detected.
And S36, calculating a second deviation value between the center point of the material to be detected and the characteristic point of the vacant sucker.
And S37, calculating a positioning deviation value of the material to be measured according to the first deviation value and the second deviation value.
By arranging the characteristic points 3 on the sucker 1, when an image to be processed is processed, the characteristic points of the sucker which is arranged in the vacancy on the image to be processed and the edge line of the material 2 to be detected on the image to be processed can be identified, and then the central point of the material 2 to be detected can be calculated according to the edge line of the material 2 to be detected; meanwhile, the positioning deviation value of the material to be measured can be calculated by acquiring a first deviation value between the standard center point of the standard material to be measured and the standard characteristic point of the standard sucker and a second deviation value between the center point of the material to be measured 2 and the characteristic point of the empty sucker.
Preferably, the positioning offset value includes an offset amount and an offset angle.
Further preferably, in the plane coordinate system, the offset (X, Y) is calculated by the formula:
X＝(X 0 -X' 0 )+X 0 *cos(θ 0 -θ' 0 )-Y 0 *sin(θ 0 -θ' 0 )，
Y＝(Y 0 -Y' 0 )+Y 0 *cos(θ 0 -θ' 0 )-Y 0 *sin(θ 0 -θ' 0 )；
the offset angle θ is calculated as:
θ＝θ 0 -θ' 0 ；
wherein, the standard central point corresponding to the standard material to be measured is (X) 1 ,Y 1 ) The standard characteristic point of the corresponding standard sucker is (X) b ,Y b ) Corresponding to an offset angle of theta 0 ，
X 0 ＝X b -X 1 ，Y 0 ＝Y b -Y 1 ，θ 0 ＝arctan|-Y 0 /X 0 |；
The central point of the material to be detected is (X ', Y '), and the characteristic point of the corresponding vacant sucker is (X ' b ，Y' b ) The corresponding offset angle is theta' 0 ，
X' 0 ＝X' b -X'，Y' 0 ＝Y' b -Y'，θ' 0 ＝arctan|-Y' 0 /X' 0 |。
Preferably, before identifying the preset position of the robot arm on the image to be processed and the edge line of the material to be detected, the method further includes:
the coordinate of a standard characteristic point of a standard sucker and the coordinate of a standard central point of a standard material to be detected are input in advance, wherein the standard central point of the standard material and the standard characteristic point of the standard sucker are respectively a material central point and a standard characteristic point of a vacant sucker when the material taking end of the mechanical arm is preset right above a material placing station.
Preferably, the method for positioning a dynamic image of robot material placement provided by the present invention further comprises:
and S5, when the material taking end of the mechanical arm moves to the visual field range of the camera device, controlling the camera device to take pictures to obtain a plurality of images to be processed.
And S6, calculating a plurality of positioning deviation values of the material to be detected according to the images to be processed respectively.
And S7, adjusting the posture of the mechanical arm according to the average value of the positioning deviation values.
In order to guarantee the positioning accuracy, the camera device is controlled to shoot for multiple times when the material taking end of the mechanical arm moves to the visual field range of the camera device, so that a plurality of images to be processed are obtained, a plurality of positioning deviation values of the materials to be detected are calculated according to the images to be processed respectively, the average value of the plurality of positioning deviation values can be obtained, the posture of the mechanical arm is adjusted according to the average value, and the adjustment accuracy can be higher.
Example 3
In an embodiment of the present invention, as shown in fig. 6, the present invention further provides a dynamic image positioning system for robot emptying, which includes a robot 4, a camera 5 and an image processing terminal 6.
The robot 4 is provided with a mechanical arm which reciprocates between the material taking station and the material placing station, and the robot 4 controls the material taking end of the mechanical arm to absorb the material to be measured from the material taking station and move to the material placing station.
Specifically, when the material end of getting of arm is shifting the material, can adopt the absorbent mode of sucking disc, can not make material positional deviation great, in other embodiments, can also snatch modes such as. In addition, this scheme can not stop in the middle of the arm when shifting the material, also can not slow down to guarantee work efficiency.
The camera device 5 is arranged between the material taking station and the material placing station, and when the robot 4 moves to the visual field range of the camera device 5 at the material taking end of the mechanical arm, the camera device 5 is controlled to take a picture to obtain an image to be processed.
Specifically, when the material taking end of the mechanical arm moves to the visual field range of the camera device 5, the robot 4 gives a trigger signal to the camera device 5 through software communication, so that the camera device 5 starts to take a picture. The camera device 5 can directly acquire the top view of the material taking end of the mechanical arm. Unlike the sensor-triggered approach commonly used in the prior art, this approach enables the camera device 5 to be prepared for taking a picture in advance, thereby eliminating the need for the mechanical arm to stop or slow down. The image capturing device 5 may be an industrial camera, and in order to ensure that the image capturing device 5 obtains a clear image to be processed during the continuous movement of the robot arm, the image capturing device 5 may be a high frame rate global shutter camera.
The image processing terminal 6 is used for identifying the edge line of the material to be measured on the image to be processed, and further calculating the positioning deviation value of the material to be measured.
After the image to be processed is obtained, the edge line of the material to be detected on the processed image can be identified through image analysis, and therefore the positioning deviation value of the material to be detected is calculated.
When the material taking end of the mechanical arm moves to a position right above the material placing station, the robot 4 adjusts the posture of the mechanical arm to place materials according to the positioning deviation value.
Specifically, after the positioning deviation value of the material to be detected is calculated, the posture of the mechanical arm can be adjusted, so that the position of the material to be detected returns to the standard position, the standardized discharging is realized, and the transportation, the test and the like after the material to be detected are facilitated.
Through establishing camera device 5 between getting material station and blowing station for get the material from getting the material station and absorb the material to be measured when the material end of getting of robot 4 control arm, and when moving to camera device 5 field of vision within range, can directly control camera device 5 and shoot, obtain the image of awaiting processing, discern the edge line of the material to be measured on the image of awaiting processing again, just can calculate the location deviation value of the material that awaits measuring, the robot is according to the gesture of location deviation value adjustment arm, just can realize accurate blowing. Because the camera shooting device directly gives a trigger signal to the camera shooting device through a software communication mode by the robot when shooting, and the trigger of the sensor is not needed, the robot does not need to stop moving, and the shooting position of the actual camera shooting device does not need to be tested repeatedly, so that the positioning and discharging efficiency of the robot is higher, and the cost is lower.
Example 4
In an embodiment of the present invention, as shown in fig. 2 and 3, on the basis of embodiment 3, at least one pair of suction cups 1 is disposed at a material taking end of the mechanical arm, one of each pair of suction cups 1 is used for sucking a material 2 to be measured, and the other suction cup is empty.
Specifically, in this scheme, can adopt the absorbent mode of sucking disc to shift the material, in addition, for the convenience of deviation location, can set up sucking disc 1 into at least a pair of, every is used for absorbing material 2 that awaits measuring to one in every sucking disc 1, and another vacancy, two sucking discs relative position are fixed to can use the vacancy sucking disc as the reference, calculate the deviation degree of the material that awaits measuring.
The image processing terminal 6 identifies the edge line of the material 2 to be detected on the image to be processed and the corresponding edge line of the vacant sucker, and calculates the positioning deviation value of the material 2 to be detected according to the edge line of the material 2 to be detected and the edge line of the vacant sucker.
Specifically, when setting up the reference position, in order to guarantee the accuracy of location, can set up at least a pair of sucking disc 1 at the material taking end of robotic arm, every is used for absorbing the material that awaits measuring to one in the sucking disc 1, and another is vacant, because the relative position of two sucking discs 1 is fixed for when handling pending image, through the edge line of discerning the material that awaits measuring 2 on the pending image to and the edge line of the vacant sucking disc that corresponds, just can calculate the location offset value of the material that awaits measuring.
Preferably, the suction cups 1 are each provided with a characteristic point 3.
The image processing terminal 6 identifies the characteristic points of the empty suckers on the image to be processed and the edge lines of the material 2 to be detected on the image to be processed, and calculates the central point of the material 2 to be detected according to the edge lines of the material 2 to be detected.
The image processing terminal 6 obtains a first deviation value between the standard center point of the standard material to be measured and the standard characteristic point of the standard sucker and a second deviation value between the center point of the material to be measured 2 and the characteristic point of the empty sucker, and calculates a positioning deviation value of the material to be measured.
By arranging the characteristic points 3 on the sucker 1, when an image to be processed is processed, the characteristic points of the sucker which is arranged in the vacancy on the image to be processed and the edge line of the material 2 to be detected on the image to be processed can be identified, and then the central point of the material 2 to be detected can be calculated according to the edge line of the material 2 to be detected; meanwhile, the positioning deviation value of the material to be measured can be calculated by acquiring a first deviation value between the standard center point of the standard material to be measured and the standard characteristic point of the standard sucker and a second deviation value between the center point of the material to be measured 2 and the characteristic point of the empty sucker.
It should be noted that the above embodiments can be freely combined as necessary. The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (6)

1. A dynamic image positioning method for robot discharging is characterized by comprising a mechanical arm which reciprocates between a material taking station and a discharging station and a camera device arranged between the material taking station and the discharging station, and comprises the following steps:
controlling a material taking end of the mechanical arm to absorb a material to be measured from the material taking station and move to the material placing station;
when the material taking end of the mechanical arm moves to the visual field range of the camera device, controlling the camera device to take a picture to obtain an image to be processed;
identifying the edge line of the material to be detected on the image to be processed, and further calculating the positioning deviation value of the material to be detected;
controlling the material taking end of the mechanical arm to move to a position right above the material placing station, and adjusting the posture of the mechanical arm to place materials according to the positioning deviation value;
the material taking end of the mechanical arm is provided with at least one pair of suckers, one of each pair of suckers is used for sucking the material to be detected, and the other sucker is empty;
the sucking discs are provided with characteristic points;
calculating the positioning deviation value of the material to be detected specifically comprises:
identifying characteristic points of the vacant suckers on the image to be processed and edge lines of the material to be detected on the image to be processed;
acquiring a first deviation value between a standard center point of a standard material to be detected and a standard characteristic point of a standard sucker;
calculating the central point of the material to be detected according to the edge line of the material to be detected;
calculating a second deviation value between the center point of the material to be detected and the characteristic point of the vacant sucker;
and calculating the positioning deviation value of the material to be detected according to the first deviation value and the second deviation value.
2. The dynamic image positioning method for robot emptying according to claim 1, wherein the method comprises the following steps: the positioning offset value includes an offset amount and an offset angle.
3. The method of claim 2, wherein the offset (X, Y) in the plane coordinate system is calculated by the following formula:
X＝(X 0 -X' 0 )+X 0 *cos(θ 0 -θ′ 0 )-Y 0 *sin(θ 0 -θ′ 0 )，
Y＝(Y 0 -Y′ 0 )+Y 0 *cos(θ 0 -θ′ 0 )-Y 0 *sin(θ 0 -θ′ 0 )；
the offset angle θ is calculated as:
θ＝θ 0 -θ′ 0 ；
wherein the standard central point corresponding to the standard material to be measured is (X) 1 ,Y 1 ) The corresponding standard characteristic point of the standard sucker is (X) b ,Y b ) Corresponding to an offset angle of theta 0 ，
X 0 ＝X b -X 1 ，Y 0 ＝Y b -Y 1 ，θ 0 ＝arctan|-Y 0 /X 0 |；
The central point of the material to be detected is (X ', Y '), and the corresponding characteristic point of the vacant sucker is (X ' b ，Y′ b ) The corresponding offset angle is theta' 0 ，
X' 0 ＝X′ b -X'，Y′ 0 ＝Y′ b -Y'，θ′ 0 ＝arctan|-Y′ 0 /X' 0 |。
4. The method as claimed in claim 1, wherein before identifying the edge line of the material to be tested on the image to be processed, the method further comprises:
the coordinates of the standard characteristic points of the standard sucker and the coordinates of the standard central point of the standard material to be measured are recorded in advance, the standard central point of the standard material and the standard characteristic point of the standard sucker are respectively the material central point when the material taking end of the mechanical arm is preset right above the material placing station and the standard characteristic point of the vacant sucker.
5. The method for positioning dynamic image of robot feeding according to any one of claims 1 to 4, further comprising:
when the material taking end of the mechanical arm moves to the visual field range of the camera device, controlling the camera device to take pictures to obtain a plurality of images to be processed;
calculating a plurality of positioning deviation values of the material to be detected according to the images to be processed respectively;
and adjusting the posture of the mechanical arm according to the average value of the positioning deviation values.
6. The utility model provides a dynamic image positioning system for blowing of robot which characterized in that includes:
the robot is provided with a mechanical arm which reciprocates between a material taking station and a material placing station, and controls a material taking end of the mechanical arm to absorb a material to be detected from the material taking station and move to the material placing station;
the camera device is arranged between the material taking station and the material placing station, and when the robot moves to the visual field range of the camera device at the material taking end of the mechanical arm, the camera device is controlled to take a picture to obtain an image to be processed;
the image processing end is used for identifying the edge line of the material to be detected on the image to be processed so as to calculate the positioning deviation value of the material to be detected;
when the material taking end of the mechanical arm moves to a position right above the material placing station, the robot adjusts the posture of the mechanical arm to place materials according to the positioning deviation value;
the material taking end of the mechanical arm is provided with at least one pair of suckers, one of each pair of suckers is used for sucking the material to be detected, and the other sucker is empty;
the sucking discs are provided with characteristic points;
the image processing end identifies characteristic points of the vacant suckers on the image to be processed and edge lines of the material to be detected on the image to be processed, and calculates the central point of the material to be detected according to the edge lines of the material to be detected;
the image processing end obtains a first deviation value of a standard center point of a standard material to be measured and a standard characteristic point of a standard sucker and a second deviation value of the center point of the material to be measured and the characteristic point of the empty sucker, and calculates a positioning deviation value of the material to be measured according to the first deviation value and the second deviation value.
CN202111223243.8A 2021-10-20 2021-10-20 Dynamic image positioning method and system for robot emptying Active CN113814984B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202111223243.8A CN113814984B (en) 2021-10-20 2021-10-20 Dynamic image positioning method and system for robot emptying
TW110143433A TWI778870B (en) 2021-10-20 2021-11-22 Dynamic image positioning method and system for robot feeding

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111223243.8A CN113814984B (en) 2021-10-20 2021-10-20 Dynamic image positioning method and system for robot emptying

Publications (2)

Publication Number Publication Date
CN113814984A CN113814984A (en) 2021-12-21
CN113814984B true CN113814984B (en) 2023-04-18

Family

ID=78920740

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111223243.8A Active CN113814984B (en) 2021-10-20 2021-10-20 Dynamic image positioning method and system for robot emptying

Country Status (2)

Country Link
CN (1) CN113814984B (en)
TW (1) TWI778870B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114749981B (en) * 2022-05-27 2023-03-24 中迪机器人(盐城)有限公司 Feeding and discharging control system and method based on multi-axis robot

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011209064A (en) * 2010-03-29 2011-10-20 Fuji Xerox Co Ltd Article recognition apparatus and article processing apparatus using the same
JP6415190B2 (en) * 2014-09-03 2018-10-31 キヤノン株式会社 ROBOT DEVICE, ROBOT CONTROL PROGRAM, RECORDING MEDIUM, AND ROBOT DEVICE CONTROL METHOD
CN107150032B (en) * 2016-03-04 2020-06-23 上海电气集团股份有限公司 Workpiece identification and sorting device and method based on multi-image acquisition equipment
CN108839024A (en) * 2018-06-29 2018-11-20 易思维（杭州）科技有限公司 A kind of visual guide method suitable for the automatic loading process of arrangements for automotive doors
CN210121750U (en) * 2019-06-28 2020-03-03 Oppo（重庆）智能科技有限公司 Assembling device
CN110561435B (en) * 2019-09-17 2021-04-27 北京康视杰视觉技术有限公司 Method, device and system for guiding manipulator and upper computer
CN111490283A (en) * 2019-12-10 2020-08-04 江苏丰盈科技有限公司 Lamination process, lamination equipment and manipulator applied to lamination equipment
CN111152222A (en) * 2020-01-07 2020-05-15 理光图像技术（上海）有限公司 Target object moving system
CN112894823B (en) * 2021-02-08 2022-06-21 珞石（山东）智能科技有限公司 Robot high-precision assembling method based on visual servo

Also Published As

Publication number Publication date
TW202317337A (en) 2023-05-01
TWI778870B (en) 2022-09-21
CN113814984A (en) 2021-12-21

Similar Documents

Publication Publication Date Title
JP4565023B2 (en) Article take-out device
CN111250406A (en) PCB detection production line automatic placement method and system based on visual positioning
CN109940662B (en) Image pickup device provided with vision sensor for picking up workpiece
EP3173194B1 (en) Manipulator system, image capturing system, transfer method of object, and carrier medium
JP5893695B1 (en) Article transport system
CN104511436A (en) Express sorting method and system based on robot visual servo technology
CN110980276B (en) Method for implementing automatic casting blanking by three-dimensional vision in cooperation with robot
CN109052180B (en) Automatic container alignment method and system based on machine vision
US10179380B2 (en) Temporary placement device able to adjust orientation of workpiece
CN113814984B (en) Dynamic image positioning method and system for robot emptying
JP5544320B2 (en) Stereoscopic robot picking device
US11065768B2 (en) Automatic calibration for camera-robot system with tool offsets
CN112658631B (en) Automatic change rigging equipment
CN110977939B (en) Target workpiece identification and positioning system
CN112001967A (en) Method and device for guiding manipulator to carry object by camera
JPH03228589A (en) Positioning method for work
CN212238247U (en) Robot sorting system with flexible feeding mechanism
JP2011143494A (en) Robot control device and method
CN210732458U (en) Identification system and material picking mechanism
CN110077848A (en) A kind of automatic identification grabbing device and method that capacitor is miniaturized
CN115008477A (en) Manipulator movement compensation method, manipulator movement compensation device and computer-readable storage medium
CN107274447B (en) Depth image acquisition device and depth image acquisition method
CN212263890U (en) PCB detects automatic placement system of assembly line based on visual positioning
CN106530357B (en) Visual alignment control device and calibration method
CN112605990A (en) Robot vision control method and system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant