CN116423525B - Automatic hand-eye calibration method and system and storage medium - Google Patents
Automatic hand-eye calibration method and system and storage medium Download PDFInfo
- Publication number
- CN116423525B CN116423525B CN202310687548.7A CN202310687548A CN116423525B CN 116423525 B CN116423525 B CN 116423525B CN 202310687548 A CN202310687548 A CN 202310687548A CN 116423525 B CN116423525 B CN 116423525B
- Authority
- CN
- China
- Prior art keywords
- calibration
- hand
- eye
- mechanical arm
- eye calibration
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 77
- 239000011159 matrix material Substances 0.000 claims abstract description 69
- 238000012545 processing Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 description 16
- 230000008859 change Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 239000004973 liquid crystal related substance Substances 0.000 description 8
- 230000033764 rhythmic process Effects 0.000 description 8
- 230000033001 locomotion Effects 0.000 description 6
- 238000013178 mathematical model Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
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
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/1653—Programme controls characterised by the control loop parameters identification, estimation, stiffness, accuracy, error analysis
-
- 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
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Manipulator (AREA)
Abstract
The application provides an automatic hand-eye calibration method, an automatic hand-eye calibration system and a storage medium, wherein the automatic hand-eye calibration method comprises the following steps ofThe method comprises the following steps: step S100, setting initial point positions of a mechanical arm for debugging hand and eye pose and establishing an initial hand and eye calibration matrix; step S200, constructing a calibration ring by taking a position point of a camera under the base coordinates of the mechanical arm at an initial point as a circle center and taking r as a radius on a plane where a camera scenic spot is located; step S300, dividing the calibration ring into a plurality of quadrants uniformly, rotating the calibration ring by a preset angle to obtain a plurality of points on the ring where each quadrant is located, and converting the points into the points of the tail end of the mechanical arm under the base coordinates through an initial hand-eye calibration matrixAs hand-eye calibration data; step S400 calculates a standard hand-eye calibration matrix according to the obtained hand-eye calibration data. Therefore, the point location information required by calibration is enriched, and the robustness of the calibration is improved.
Description
Technical Field
The application relates to the technical field of robot vision, in particular to an automatic hand-eye calibration method and system and a storage medium.
Background
With the continuous demands of industrial flexibility, the application of visual technology is increasingly applied to industrial scenes. The hand-eye calibration technology can assist the mechanical arm to pass through vision, and reduce errors in movement. However, calibration requires manual intervention to control the movement of the mechanical arm, and recalibration is required when the relationship between the camera and the arm changes. Therefore, the method has the problems of difficult operation, complicated implementation process and multiple calibration requirements for implementation personnel.
For this purpose, various schemes for automatic hand-eye calibration have been proposed in the prior art, such as "full-automatic hand-eye calibration method and apparatus" (patent publication No. CN 107498558A), which includes the steps of: acquiring the current pose of the mechanical arm; acquiring the next pose of the mechanical arm according to the current pose of the mechanical arm and a preset motion path; acquiring calibration plate data under each pose of the mechanical arm; and obtaining a hand-eye calibration result of the camera and the mechanical arm according to the pose of the mechanical arm and the calibration plate data.
However, in the practical process, the mechanical arm has a small moving range in the calibration process, and the point position information is not rich enough, so that the diversity of the mechanical arm point positions cannot be met, the calibrated data result is easy to cause, and the recognition requirements under a plurality of postures cannot be adapted.
Disclosure of Invention
Therefore, the application mainly aims to provide an automatic hand-eye calibration method, an automatic hand-eye calibration system and a storage medium, so that point location information required by calibration is enriched, and the robustness of the calibration is improved.
In order to achieve the above object, according to one aspect of the present application, there is provided an automatic hand-eye calibration method, comprising the steps of:
step S100, setting initial point positions of a mechanical arm for debugging hand and eye pose and establishing an initial hand and eye calibration matrix;
step S200, constructing a calibration ring by taking a position point of a camera under the base coordinates of the mechanical arm at an initial point as a circle center and taking r as a radius on a plane where a camera scenic spot is located;
step S300, dividing the calibration ring into a plurality of quadrants uniformly, rotating the calibration ring by a preset angle to obtain a plurality of points on the ring where each quadrant is located, and converting the points into the points of the tail end of the mechanical arm under the base coordinates through an initial hand-eye calibration matrixAs hand-eye calibration data;
step S400 calculates a standard hand-eye calibration matrix according to the obtained hand-eye calibration data.
In a possibly preferred embodiment, the step of establishing the initial point location in step S100 includes: and adjusting the pose of the mechanical arm to enable the view finding area of the camera to be perpendicular to the calibration object, and identifying the calibration object to be marked as an initial point position.
In a possibly preferred embodiment, the initial hand-eye calibration matrix establishment step in step S100 includes: and (3) taking the initial point position as a starting point, adjusting the mechanical arm to conduct coordinate offset for a plurality of times in the positive and negative directions of the X, Y axis, recording the coordinate offset as initial hand-eye calibration data, establishing a plurality of groups of equations through the hand-eye calibration formula, and establishing an initial hand-eye calibration matrix based on a least square method.
In order to achieve the above object, according to a second aspect of the present application, there is also provided an automatic hand-eye calibration method, comprising the steps of:
step S100, setting initial point positions of a mechanical arm for debugging hand and eye pose and establishing an initial hand and eye calibration matrix;
step S200, constructing a calibration ring by taking a position point of a camera under the base coordinates of the mechanical arm at an initial point as a circle center and taking r as a radius on a plane where a camera scenic spot is located;
step S300, obtaining the distance D between the camera and the calibration object, taking a point P on the calibration ring, and calculating the distance D from the P to the center of the calibration object;
step S400, dividing the calibration ring into a plurality of quadrants uniformly, rotating the calibration ring by a preset angle to obtain a plurality of points on the ring where each quadrant is located, and converting the points into the points of the tail end of the mechanical arm under the base coordinates through an initial hand-eye calibration matrixAs hand-eye calibration data;
step S500, adjusting the distance between the camera and the calibration object to be d' so as toEstablishing an auxiliary calibration ring for the radius, wherein the distance D from a point P' on the auxiliary calibration ring to the center of the calibration object is unchanged, and repeating the steps S400-S500 until the hand-eye calibration data volume reaches the standard;
step S600 calculates a standard hand-eye calibration matrix according to the obtained hand-eye calibration data.
In a possibly preferred embodiment, the automatic hand-eye calibration method further comprises the steps of:
step S410 sets each pointPerforming inverse solution calculation and reserving the value of the inverse solutionAnd the point position which can not collide with the hand and eye calibration data is marked.
In a possibly preferred embodiment, the automatic hand-eye calibration method further comprises the steps of:
step S420 controls the tail end of the mechanical arm to move to each point respectivelyAnd then enabling the camera to identify the calibration object, and storing the point position information of the mechanical arm at the moment as hand-eye calibration data when the identification rate accords with the expectation.
In a possibly preferred embodiment, the step of establishing the initial point location in step S100 includes: and adjusting the pose of the mechanical arm to enable the view finding area of the camera to be perpendicular to the calibration object, and identifying the calibration object to be marked as an initial point position.
In a possibly preferred embodiment, the initial hand-eye calibration matrix establishment step in step S100 includes: and adjusting the mechanical arm to conduct coordinate offset for a plurality of times in the positive and negative directions of the X, Y axis and recording the coordinate offset as initial hand-eye calibration data, establishing a plurality of groups of equations through a hand-eye calibration formula, and establishing an initial hand-eye calibration matrix based on a least square method.
In order to achieve the above object, corresponding to the above method, a third aspect of the present application further provides an automatic hand-eye calibration system, which includes:
the storage unit is used for storing a program comprising the steps of the automatic hand-eye calibration method, so that the control unit and the processing unit can timely adjust and execute the program;
the control unit is used for controlling the mechanical arm to adjust the pose, enabling the view finding area of the camera to be perpendicular to the calibration object, and identifying the calibration object to be marked as an initial point position; then, taking the initial point position as a starting point, adjusting the mechanical arm to carry out coordinate offset for a plurality of times in the positive and negative directions of the X, Y axis, and recording the coordinate offset as initial hand-eye calibration data; then controlling the mechanical arm to return to the initial point position;
the processing unit is used for establishing an initial hand-eye calibration matrix based on a least square method by combining a plurality of groups of equations through hand-eye calibration formulas according to the initial hand-eye calibration data; then when the mechanical arm returns to the initial point position, according to the initial positionCalculating the position point of the current camera under the base coordinates of the mechanical arm by using the starting hand-eye calibration matrix, constructing a calibration ring by taking the point as the circle center and taking r as the radius on the plane of a camera scenic spot, obtaining the distance D between the camera and a calibration object, taking a point P on the calibration ring, calculating the distance D from the P to the center of the calibration object, equally dividing the calibration ring into a plurality of quadrants, uniformly rotating a preset angle to obtain a plurality of point positions on the calibration ring, and converting the point positions into the point positions of the tail end of the mechanical arm under the base coordinates by using the initial hand-eye calibration matrix；
The control unit is also used for controlling the tail end of the mechanical arm to move to each point respectivelyThen, enabling the camera to identify the calibration object, and when the identification rate accords with the expectation, storing the point position information of the mechanical arm as hand-eye calibration data; then adjusting the distance between the camera and the calibration object to be d';
a processing unit for further processingEstablishing an auxiliary calibration ring for the radius, wherein the distance D from a point P' on the auxiliary calibration ring to the center of the calibration object is unchanged; then repeatedly dividing the auxiliary calibration ring into a plurality of quadrants, rotating the auxiliary calibration ring by a preset angle to obtain a plurality of point positions on the auxiliary calibration ring, and converting the point positions into point positions +_in the base coordinates of the tail end of the mechanical arm through an initial hand-eye calibration matrix>For the control unit to repeat the identification rate to be in line with the expected +.>And marking the hand-eye calibration data until the hand-eye calibration data reach the standard, and calculating a new hand-eye calibration matrix according to the obtained hand-eye calibration data.
In order to achieve the above object, according to a fourth aspect of the present application, there is also provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the above-mentioned automatic hand-eye calibration methods.
According to the automatic hand-eye calibration method, the automatic hand-eye calibration system and the storage medium, the calibration ring is skillfully constructed in the calibration process to define quadrants therein, so that the values of the X and Y axes between the calibration points acquired on the calibration ring can be changed, point location information required by calibration is enriched, the robustness of calibration is improved, the homogeneous matrix of the relative position relationship from the tail end of the mechanical arm to the base coordinate system of the mechanical arm can be ensured to be changed during calculation, the conversion of X and Y axis dimension information is not lost, in addition, the moving process between the points can be shortened, the rhythm is accelerated, and the safety is ensured.
On the other hand, in some embodiments, by constructing the auxiliary calibration ring, multiple layers of calibration surfaces can be established, so that more calibration points can be obtained, point information obtained in the whole calibration process is more abundant, the speed rhythm is faster during operation, calibration errors caused by the change of the relative distance between the calibration object and the mechanical arm can be well reduced, and the robustness of the calibration result is ensured.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
FIG. 1 is a schematic diagram showing steps of an automatic hand-eye calibration method according to a first embodiment of the present application;
FIG. 2 is a schematic diagram showing the constitution of a calibration ring in an automatic hand-eye calibration method according to a first embodiment of the present application;
FIG. 3 shows four quadrants of the calibration ring set to obtain P in the automatic hand-eye calibration method according to the first embodiment of the present application n Schematic of (2);
FIG. 4 is a schematic diagram showing the spatial relationship between the calibration ring and the calibration object and the camera in the automatic hand-eye calibration method according to the first embodiment of the present application;
FIG. 5 is a schematic diagram showing steps of an automatic hand-eye calibration method according to a second embodiment of the present application;
FIG. 6 is a schematic diagram of calibration logic of an automatic hand-eye calibration method according to a second embodiment of the present application;
FIG. 7 is a schematic diagram showing the constitution of an accessory calibration ring in an automatic hand-eye calibration method according to a second embodiment of the present application;
FIG. 8 is a schematic diagram showing the spatial relationship between an accessory calibration ring and a calibration object and material table in an automatic hand-eye calibration method according to a second embodiment of the present application;
FIG. 9 is a diagram illustrating an example of identification of a calibration object in an automatic hand-eye calibration method according to a second embodiment of the present application;
FIG. 10 is a schematic diagram of an automatic hand-eye calibration system according to the present application.
Description of the reference numerals
The device comprises a calibration ring 1, a calibration object 2, a mechanical arm 3, a camera 4, a material table 5, a mechanical arm tail end 6 and an auxiliary calibration ring 7.
Detailed Description
In order that those skilled in the art can better understand the technical solutions of the present application, the following description will clearly and completely describe the specific technical solutions of the present application in conjunction with the embodiments to help those skilled in the art to further understand the present application. It will be apparent that the embodiments described herein are merely some, but not all embodiments of the application. It should be noted that embodiments of the present application and features of embodiments may be combined with each other by those of ordinary skill in the art without departing from the spirit of the present application and without conflicting with each other. All other embodiments, which are derived from the embodiments herein without creative effort for a person skilled in the art, shall fall within the disclosure and the protection scope of the present application.
Furthermore, the terms "first," "second," "S100," "S200," and the like in the description and in the claims and drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those described herein. Also, the terms "comprising" and "having" and any variations thereof herein are intended to cover a non-exclusive inclusion. Unless specifically stated or limited otherwise, the terms "disposed," "configured," "mounted," "connected," "coupled" and "connected" are to be construed broadly, e.g., as being either permanently connected, removably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the terms in this case will be understood by those skilled in the art in view of the specific circumstances and in combination with the prior art.
Referring to fig. 1 to 4, in order to enrich the point location information required by calibration and improve the robustness of calibration, the automatic hand-eye calibration method provided by the application comprises the following steps:
step S100 sets an initial point position of the mechanical arm for debugging hand and eye pose and establishing an initial hand and eye calibration matrix.
Specifically, the step of establishing the initial point location includes: and adjusting the pose of the mechanical arm to enable the view finding area of the camera to be perpendicular to the calibration object, and identifying the calibration object to be marked as an initial point position.
For example, as shown in fig. 4, before starting calibration, the mechanical arm is manually moved to a position right above the calibration object, so that the camera is vertically downward at this time, the calibration object is positioned at the center of the view taking area of the camera, the direct distance d between the camera and the calibration plate can be set to be about 200mm to 350mm, and the point position information at this time is stored and recorded as an initial point position.
Further, the initial hand-eye calibration matrix establishing step includes: and (3) taking the initial point position as a starting point, adjusting the mechanical arm to conduct coordinate offset for a plurality of times in the positive and negative directions of the X, Y axis, recording the coordinate offset as initial hand-eye calibration data, establishing a plurality of groups of equations through the hand-eye calibration formula, and establishing an initial hand-eye calibration matrix based on a least square method.
For example, the mechanical arm is moved in the positive and negative directions of the X axis and the Y axis respectively for 3 times according to a certain step length, such as 1cm, and simultaneously, pictures are collected. After the acquisition is completed, a rough hand-eye calibration is performed through a hand-eye calibration formula. The formula is as follows:
；
；
...
。
wherein, the liquid crystal display device comprises a liquid crystal display device,the system is a homogeneous matrix for representing the relative position relation from the tail end of the mechanical arm to the base coordinate system of the mechanical arm. The method can be obtained through the positive solution of the joint value of the mechanical arm or the pose reporting module of the mechanical arm, and the known quantity is obtained.
The homogeneous matrix representing the relative relationship between the camera and the tail end of the mechanical arm is an unknown quantity to be solved.
To represent the homogeneous matrix of camera-to-calibration relative relationships, one can obtain, by identifying a particular object, a known quantity to be solved for.
In order to represent the homogeneous matrix from the calibration object to the mechanical arm base coordinate system, the position relationship of the calibration plate cannot change in the calibration process, so that the calibration plate can be ignored.
By the above formula, 10 groups of equations are combined, and based on the least square method, an initial hand-eye calibration matrix can be obtained. It can be seen that, by calculation in this step, the position information of the camera in the coordinate system of the mechanical arm can be approximately known, but although the position information is not very accurate, the inaccuracy can be eliminated later according to the rough result, and an accurate value is finally obtained.
And step S200, constructing a calibration ring by taking a position point of the camera under the base coordinates of the mechanical arm at the initial point as a circle center and taking r as a radius on a plane where a camera scenic spot is located.
Specifically, the initial acquired through step S100Which can be used for subsequent coordinate transformation operations. As shown in fig. 2, the manipulator arm moves to the initial point at this time by: />And obtaining the position relation of the camera under the mechanical arm base coordinate system, taking the point as a round point, and constructing a mathematical model of the calibration ring by taking r as a radius on a plane where the camera scenic spot is located.
Step S300, dividing the calibration ring into a plurality of quadrants uniformly, rotating the calibration ring by a preset angle to obtain a plurality of points on the ring where each quadrant is located, and converting the points into the points of the tail end of the mechanical arm under the base coordinates through an initial hand-eye calibration matrixAs hand-eye calibration data.
Specifically, as shown in fig. 3, after the mathematical model of the calibration ring is provided, the mechanical arm needs to be controlled to move, and in this example, for the diversified characteristics of the points, one calibration ring is split into four quadrants, and four points are regularly taken on the calibration ring.
For example, in the first quadrant, a value is randomly generated from 0 to 90 degrees. The angle values of the second quadrant, the third quadrant and the fourth quadrant can be expressed as +.>，/>，/>. Each angle corresponds to +.>，/>，/>，/>The point location may be specifically shown in fig. 3.
It should be noted that the purpose of quadrant construction is to ensure that the X and Y axis values change due to the point-to-point movement, thus ensuring that the matrix changes during computation without losing the X and Y axis dimensional information. In addition, another benefit of determining four quadrants is that the moving process between points can be shortened, the rhythm is quickened, and meanwhile safety is ensured.
Step S310 is based on the angle valueAt this time, the new camera coordinates are solved by applying the new camera coordinates to the calibration ring, and the formula is expressed as follows:
；
；
；
wherein:，/>，/>the new X, Z, Y coordinate values for the cameras, respectively. />，/>，/>The original coordinates of the initial point position camera. The Z coordinate does not change because of the initial position plane used at this time. Further, since each quadrant angle is different by 90 °, there is no need to judge +.>And->Is a direction of (2).
Step S320 further solves the pose of the new camera in the mechanical arm coordinate system, where the formula is:
；
；
；
wherein:，/>，/>representing a new X, Y, Z direction vector for the camera. />Indicating the position of the calibration plate in the base coordinate system, and (2)>Representing the position of the camera in the base coordinate system, a +.>Representing the position of the randomly generated new camera point in the base coordinate system.
Because the point location at this time is the coordinate of the camera, the coordinate value of the camera cannot be given to the mechanical arm, otherwise, the mechanical arm moves incorrectly, so that the coordinate value of the camera needs to be converted into the coordinate value of the tail end of the mechanical arm, and the formula can be expressed as follows:. And obtaining the point position of the tail end of the mechanical arm under the base coordinate system at the moment.
Wherein, the liquid crystal display device comprises a liquid crystal display device,expressed as an inverse of the camera to robot end relative relationship. />Representing the homogeneous matrix from camera to calibration.
Then, the angle values are used respectively，/>，/>Steps S310 to S320 are repeatedly performed until +.>，/>，/>，/>After the use, if the hand-eye calibration data amount does not reach the standard, a new angle value is randomly generated, and the steps S300 to S320 are repeated until, for example, 10 groups of hand-eye calibration data are obtained.
And step S400, finally, according to the hand-eye calibration data obtained in the previous step, a simultaneous equation set is used, and the standard hand-eye calibration matrix at the moment can be obtained through calculation based on a least square method.
；
...
。
Therefore, point position information required by calibration can be enriched, the robustness of the calibration is improved, the fact that a homogeneous matrix of the relative position relation from the tail end of the mechanical arm to the base coordinate system of the mechanical arm is changed during calculation can be ensured, the conversion of X-axis dimension information and Y-axis dimension information cannot be lost, in addition, the moving process between points can be shortened, the rhythm is accelerated, and meanwhile safety is ensured.
On the other hand, referring to fig. 5 to 9, in a second aspect of the present application, an automatic hand-eye calibration method is provided, which includes the steps of:
step S100 sets an initial point position of the mechanical arm for debugging hand and eye pose and establishing an initial hand and eye calibration matrix.
Specifically, the step of establishing the initial point location includes: and adjusting the pose of the mechanical arm to enable the view finding area of the camera to be perpendicular to the calibration object, and identifying the calibration object to be marked as an initial point position.
For example, as shown in fig. 7, before starting calibration, the mechanical arm is manually moved to a position right above the calibration object, so that the camera is vertically downward at this time, the calibration object is positioned at the center of the view taking area of the camera, the direct distance d between the camera and the calibration plate can be set to be about 200mm to 350mm, and the point position information at this time is stored and recorded as an initial point position.
Further, the initial hand-eye calibration matrix establishing step includes: and (3) taking the initial point position as a starting point, adjusting the mechanical arm to conduct coordinate offset for a plurality of times in the positive and negative directions of the X, Y axis, recording the coordinate offset as initial hand-eye calibration data, establishing a plurality of groups of equations through the hand-eye calibration formula, and establishing an initial hand-eye calibration matrix based on a least square method.
For example, the mechanical arm is moved in the positive and negative directions of the X axis and the Y axis respectively for 3 times according to a certain step length, such as 1cm, and simultaneously, pictures are collected. After the acquisition is completed, a rough hand-eye calibration is performed through a hand-eye calibration formula. The formula is as follows:
；
；
...
。
wherein, the liquid crystal display device comprises a liquid crystal display device,the system is a homogeneous matrix for representing the relative position relation from the tail end of the mechanical arm to the base coordinate system of the mechanical arm. The method can be obtained through the positive solution of the joint value of the mechanical arm or the pose reporting module of the mechanical arm, and the known quantity is obtained.
The homogeneous matrix representing the relative relationship between the camera and the tail end of the mechanical arm is an unknown quantity to be solved.
To represent the homogeneous matrix of camera-to-calibration relative relationships, one can obtain, by identifying a particular object, a known quantity to be solved for.
In order to represent the homogeneous matrix from the calibration object to the mechanical arm base coordinate system, the position relationship of the calibration plate cannot change in the calibration process, so that the calibration plate can be ignored.
Through the formula, 10 groups of equations are combined, and based on a least square method, an initial hand-eye calibration matrix can be obtained. It can be seen that, by calculation in this step, the position information of the camera in the coordinate system of the mechanical arm can be approximately known, but although the position information is not very accurate, the inaccuracy can be eliminated later according to the rough result, and an accurate value is finally obtained.
And step S200, constructing a calibration ring by taking a position point of the camera under the base coordinates of the mechanical arm at the initial point as a circle center and taking r as a radius on a plane where a camera scenic spot is located.
Specifically, the initial acquired through step S100Which can be used for subsequent coordinate transformation operations. As shown in fig. 2, the manipulator arm moves to the initial point at this time by: />And obtaining the position relation of the camera under the mechanical arm base coordinate system, taking the point as a round point, and constructing a mathematical model of the calibration ring by taking r as a radius on a plane where the camera scenic spot is located.
Step S300, the distance D between the camera and the calibration object is obtained, a point P on the calibration ring is taken, and the distance D from the P to the center of the calibration object is calculated.
Specifically, as shown in fig. 2, a calibration object is identified by a camera, the distance d between the current camera and the calibration object is obtained, and the plane where the camera is located at the moment is set to be a circular surface with a radius r. Then according to Pythagorean theorem, a point P on the ring can be obtained to the calibration plateDistance of heartThe distance D can provide basis for realizing multi-level movement subsequently.
Step S400, dividing the calibration ring into a plurality of quadrants uniformly, rotating the calibration ring by a preset angle to obtain a plurality of points on the ring where each quadrant is located, and converting the points into the points of the tail end of the mechanical arm under the base coordinates through an initial hand-eye calibration matrixAs hand-eye calibration data.
Specifically, as shown in fig. 3, after the mathematical model of the calibration ring is provided, the mechanical arm needs to be controlled to move, and in this example, for the diversified characteristics of the points, one calibration ring is split into four quadrants, and four points are regularly taken on the calibration ring.
For example, in the first quadrant, a value is randomly generated from 0 to 90 degrees. The angle values of the second quadrant, the third quadrant and the fourth quadrant can be expressed as +.>，/>，/>. Each angle corresponds to +.>，/>，/>，/>The point location can be shown in figure 3。
It should be noted that the purpose of constructing quadrants is to ensure that the point-to-point movement will change the X and Y axis values, thus ensuring that the calculation is performedThe matrix of (a) is changed without losing the transformation of the X and Y axis dimension information. In addition, another benefit of determining four quadrants is that the moving process between points can be shortened, the rhythm is quickened, and meanwhile safety is ensured.
Step S401 is based on the angle valueAt this time, the new camera coordinates are solved by applying the new camera coordinates to the calibration ring, and the formula is expressed as follows:
；
；
；
wherein:，/>，/>the new X, Z, Y coordinate values for the cameras, respectively. />，/>，/>The original coordinates of the initial point position camera. The Z coordinate does not change because of the initial position plane used at this time. Further, since each quadrant angle is different by 90 °, there is no need to judge +.>And->Is a direction of (2).
Step S402 further solves the pose of the new camera under the mechanical arm coordinate system, where the formula is:
；
；
；
wherein:，/>，/>representing a new X, Y, Z direction vector for the camera. />Indicating the position of the calibration plate in the base coordinate system, and (2)>Representing the position of the camera in the base coordinate system, a +.>Representing the position of the randomly generated new camera point in the base coordinate system.
Because the point location at this time is the coordinate of the camera, the coordinate value of the camera cannot be given to the mechanical arm, otherwise, the mechanical arm moves incorrectly, so that the coordinate value of the camera needs to be converted into the coordinate value of the tail end of the mechanical arm, and the formula can be expressed as follows:. And obtaining the point position of the tail end of the mechanical arm under the base coordinate system at the moment.
Wherein, the liquid crystal display device comprises a liquid crystal display device,expressed as an inverse of the camera to robot end relative relationship. />Representing the homogeneous matrix from camera to calibration.
In a preferred embodiment, in order to determine the availability and safety of the calibration process, step S400 further includes:
step S410 sets each pointAnd (3) performing inverse solution calculation at least once, judging whether the specific joint value corresponds to the inverse solution, and marking the point positions which have the value and cannot collide with each other as hand-eye calibration data.
In addition, if the calibrated result can meet the recognition rate after calibration in order to better ensure that the calibration result is met, in the preferred embodiment, the hand-eye calibration data obtained in step S410 may further enter step S420 for processing.
Step S420 controls the tail end of the mechanical arm to move to each point respectivelyAnd then enabling the camera to identify the calibration object, and storing the point position information of the mechanical arm at the moment as hand-eye calibration data when the identification rate accords with the expectation.
Specifically, the point location obtained in step S410The calibration object is sent to the mechanical arm to move, and after moving to the corresponding point location, camera identification is carried out once, wherein in the example, the calibration object is in a checkerboard form as shown in fig. 9, and angular points needing to be identified exist between the longitudinal and the transverse directions, so that whether the current image can be completely identified can be judged by identifying and extracting the angular points.
If the requirements (such as identifying the corner points extracted to 80% and above) are met, the hand-eye calibration data is passed and recorded, otherwise, the hand-eye calibration data is selected and removed.
For example, a checkerboard of 5*4. The camera can take the angular points of the intersection of the lattices as the recognition basis, one lattice has four angular points, when all the four angular points can be recognized, one lattice can be considered to be recognized as the lattice 1 in fig. 9, and when any angular point is absent, the lattice can not be considered to be recognized as the lattice 4 in fig. 9.
Therefore, when 16 lattices or more are recognized, it is considered that the recognition condition is satisfied, and the current robot arm point position information and the camera recognition information are saved. When 16 points are not met, the mechanical arm point positions are not recorded at the moment. Thereby screening out partial unsatisfactory spots。
Then, the angle values are used respectively，/>，/>Steps S401 to S420 are repeatedly performed until +.>，/>，/>，/>After the use, if the hand-eye calibration data amount does not reach the standard, a new angle value is randomly generated, and the steps S400 to S420 are repeated until, for example, 10 groups of hand-eye calibration data are obtained.
At this time, the obtained point location information of the same plane, namely the Z-axis information of the mechanical arm, is relatively fixed. Therefore, if the distance between the camera and the calibration object is too large compared with the distance when the manipulator performs hand-eye calibration when the camera recognizes, the visual recognition is inaccurate. Therefore, in order to adapt to a more general scene, we need to change the Z-axis point location information of the mechanical arm.
Step S500 is shown in FIG. 8, in which the distance between the camera and the calibration object is adjusted to d' toAnd (3) establishing an auxiliary calibration ring for the radius, wherein the distance D from a point P' on the auxiliary calibration ring to the center of the calibration object is unchanged, and repeating the steps S400-S500 until the hand-eye calibration data volume reaches the standard.
Specifically, as shown in fig. 4 compared with fig. 7, after 10 points satisfying the condition are actually acquired in the plane in which the calibration ring lies, the hand-eye matrix can be calculated. However, in order to obtain a more general solution to meet the requirements of the camera in different poses, in this example, it is preferable to perform some lifting or lowering operation on the initial plane where the calibration loop is located.
As shown in fig. 7 to 8, 10 different sets of points are taken in the two auxiliary calibration rings 7 generated randomly in this example. The distance D calculated at this time due to step S300 is a fixed value. Then the example may randomly generate a value Y in-50 mm to 50mm for specifying the distance of the camera from the calibration plate at this timeThe expression can be as follows: />=d-Y。
Then the radius of the attached calibration ring。
At the radius of the auxiliary calibration ringLater, due to ∈>The change has occurred and it is necessary to repeatedly perform steps S400-S500, wherein +.>A corresponding increase or decrease in Y value is required, such as: />. And (3) until the hand-eye calibration data corresponding to the data acquired by the effective camera for 10 times are met.
Step S600 calculates a standard hand-eye calibration matrix according to the obtained hand-eye calibration data.
Specifically, 20 groups of hand-eye calibration data are obtained in total before and after the step S100 is performed reversely, and then accurate hand-eye calibration data are obtained. The specific derivation process can be as follows.
；
...
。
At the moment, the hand-eye calibration matrix can be calculated based on a least square method through simultaneous equations, and the hand-eye calibration matrix is defined as a standard hand-eye calibration matrix.
Therefore, compared with the first embodiment, the second embodiment can establish a plurality of layers of calibration surfaces by constructing the auxiliary calibration ring, so that more calibration points are acquired, the point information obtained by the whole calibration flow is richer, the speed rhythm is faster during operation, the calibration error caused by the change of the relative distance between the calibration object and the mechanical arm can be well reduced, and the robustness of the calibration result for a plurality of times is ensured. Meanwhile, on the other hand, the problem that the camera cannot capture a complete image due to the fact that the tail end of the mechanical arm is used as the center during calibration is solved.
On the other hand, referring to fig. 10, corresponding to the above method example, the present application further provides an automatic hand-eye calibration system, which includes:
the storage unit is used for storing a program comprising the steps of the automatic hand-eye calibration method, so that the control unit and the processing unit can timely adjust and execute the program.
The control unit is used for controlling the mechanical arm to adjust the pose, enabling the view finding area of the camera to be perpendicular to the calibration object, and identifying the calibration object to be marked as an initial point position; then, taking the initial point position as a starting point, adjusting the mechanical arm to carry out coordinate offset for a plurality of times in the positive and negative directions of the X, Y axis, and recording the coordinate offset as initial hand-eye calibration data; and then controlling the mechanical arm to return to the initial point position.
The processing unit is used for establishing an initial hand-eye calibration matrix based on a least square method by combining a plurality of groups of equations through hand-eye calibration formulas according to the initial hand-eye calibration data; when the mechanical arm returns to the initial point position, calculating the position point of the current camera under the mechanical arm base coordinate according to the initial hand-eye calibration matrix, taking the position point as the center of a circle, constructing a calibration ring on a plane where a camera scenic spot is located by taking r as a radius, obtaining the distance D between the camera and a calibration object, taking one point P on the calibration ring, calculating the distance D from the P to the center of the calibration object, equally dividing the calibration ring into a plurality of quadrants, uniformly rotating preset angles to obtain a plurality of point positions on the calibration ring, and converting the point positions into the point positions of the tail end of the mechanical arm under the base coordinate through the initial hand-eye calibration matrix。
The control unit is also used for controlling the tail end of the mechanical arm to move to each point respectivelyThen, make the camera recognize and calibrateWhen the recognition rate meets the expectation, storing the point position information of the mechanical arm as hand-eye calibration data; and then adjusting the distance between the camera and the calibration object to be d'.
A processing unit for further processingEstablishing an auxiliary calibration ring for the radius, wherein the distance D from a point P' on the auxiliary calibration ring to the center of the calibration object is unchanged; then repeatedly dividing the auxiliary calibration ring into a plurality of quadrants, rotating the auxiliary calibration ring by a preset angle to obtain a plurality of point positions on the auxiliary calibration ring, and converting the point positions into point positions +_in the base coordinates of the tail end of the mechanical arm through an initial hand-eye calibration matrix>For the control unit to repeat the identification rate to be in line with the expected +.>And marking the hand-eye calibration data until the hand-eye calibration data reach the standard, and calculating a new hand-eye calibration matrix according to the obtained hand-eye calibration data.
In another aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the above-mentioned automatic hand-eye calibration methods.
In summary, according to the automatic hand-eye calibration method, the automatic hand-eye calibration system and the storage medium provided by the application, during the calibration process, the calibration ring is skillfully constructed to define quadrants therein, so that the values of the X and Y axes between the calibration points acquired on the calibration ring can be changed, the point position information required by the calibration is enriched, the robustness of the calibration is improved, the homogeneous matrix of the relative position relationship from the tail end of the mechanical arm to the base coordinate system of the mechanical arm can be ensured to be changed during the calculation, the conversion of the dimension information of the X and Y axes is not lost, in addition, the moving process between the points can be shortened, the rhythm is accelerated, and the safety is ensured.
On the other hand, in some embodiments, by constructing the auxiliary calibration ring, multiple layers of calibration surfaces can be established, so that more calibration points can be obtained, point information obtained in the whole calibration process is more abundant, the speed rhythm is faster during operation, calibration errors caused by the change of the relative distance between the calibration object and the mechanical arm can be well reduced, and the robustness of the calibration result is ensured.
The preferred embodiments of the application disclosed above are intended only to assist in the explanation of the application. The preferred embodiments are not exhaustive or to limit the application to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the application and the practical application, to thereby enable others skilled in the art to best understand and utilize the application. The application is to be limited only by the following claims and their full scope and equivalents, and any modifications, equivalents, improvements, etc., which fall within the spirit and principles of the application are intended to be included within the scope of the application.
It will be appreciated by those skilled in the art that the system, apparatus and their respective modules provided by the present application may be implemented entirely by logic programming method steps, in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc., except for implementing the system, apparatus and their respective modules provided by the present application in a purely computer readable program code. Therefore, the system, the apparatus, and the respective modules thereof provided by the present application may be regarded as one hardware component, and the modules included therein for implementing various programs may also be regarded as structures within the hardware component; modules for implementing various functions may also be regarded as being either software programs for implementing the methods or structures within hardware components.
Furthermore, all or part of the steps in implementing the methods of the embodiments described above may be implemented by a program, where the program is stored in a storage medium and includes several instructions for causing a single-chip microcomputer, chip or processor (processor) to execute all or part of the steps in the methods of the embodiments of the application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In addition, any combination of various embodiments of the present application may be performed, so long as the concept of the embodiments of the present application is not violated, and the disclosure of the embodiments of the present application should also be considered.
Claims (10)
1. An automatic hand-eye calibration method comprises the following steps:
step S100, setting initial point positions of a mechanical arm for debugging hand and eye pose and establishing an initial hand and eye calibration matrix;
step S200, constructing a calibration ring by taking a position point of a camera under the base coordinates of the mechanical arm at an initial point as a circle center and taking r as a radius on a plane where a camera scenic spot is located;
step S300, dividing the calibration ring into a plurality of quadrants uniformly, rotating the calibration ring by a preset angle to obtain a plurality of points on the ring where each quadrant is located, and converting the points into the points of the tail end of the mechanical arm under the base coordinates through an initial hand-eye calibration matrixAs hand-eye calibration data;
step S400 calculates a standard hand-eye calibration matrix according to the obtained hand-eye calibration data.
2. The automatic hand-eye calibration method according to claim 1, wherein the establishing of the initial point location in step S100 comprises: and adjusting the pose of the mechanical arm to enable the view finding area of the camera to be perpendicular to the calibration object, and identifying the calibration object to be marked as an initial point position.
3. The automatic hand-eye calibration method according to claim 1, wherein the initial hand-eye calibration matrix establishment step in step S100 comprises: and (3) taking the initial point position as a starting point, adjusting the mechanical arm to conduct coordinate offset for a plurality of times in the positive and negative directions of the X, Y axis, recording the coordinate offset as initial hand-eye calibration data, establishing a plurality of groups of equations through the hand-eye calibration formula, and establishing an initial hand-eye calibration matrix based on a least square method.
4. An automatic hand-eye calibration method comprises the following steps:
step S100, setting initial point positions of a mechanical arm for debugging hand and eye pose and establishing an initial hand and eye calibration matrix;
step S200, constructing a calibration ring by taking a position point of a camera under the base coordinates of the mechanical arm at an initial point as a circle center and taking r as a radius on a plane where a camera scenic spot is located;
step S300, obtaining the distance D between the camera and the calibration object, taking a point P on the calibration ring, and calculating the distance D from the P to the center of the calibration object;
step S400, dividing the calibration ring into a plurality of quadrants uniformly, rotating the calibration ring by a preset angle to obtain a plurality of points on the ring where each quadrant is located, and converting the points into the points of the tail end of the mechanical arm under the base coordinates through an initial hand-eye calibration matrixAs hand-eye calibration data;
step S500, adjusting the distance between the camera and the calibration object to be d' so as toEstablishing an auxiliary calibration ring for the radius, wherein the distance D from a point P' on the auxiliary calibration ring to the center of the calibration object is unchanged, and repeating the steps S400-S500 until the hand-eye calibration data volume reaches the standard;
step S600 calculates a standard hand-eye calibration matrix according to the obtained hand-eye calibration data.
5. The automatic hand-eye calibration method of claim 4, wherein the steps further comprise:
step S410 sets each pointPerforming inverse solution calculation and reserving the inverse solutionThe point position which has a value and can not collide with itself is marked as hand-eye calibration data.
6. The automatic hand-eye calibration method of claim 4, wherein the steps further comprise:
step S420 controls the tail end of the mechanical arm to move to each point respectivelyAnd then enabling the camera to identify the calibration object, and storing the point position information of the mechanical arm at the moment as hand-eye calibration data when the identification rate accords with the expectation.
7. The automatic hand-eye calibration method according to claim 4, wherein the establishing of the initial point location in step S100 comprises: and adjusting the pose of the mechanical arm to enable the view finding area of the camera to be perpendicular to the calibration object, and identifying the calibration object to be marked as an initial point position.
8. The automatic hand-eye calibration method according to claim 4, wherein the initial hand-eye calibration matrix establishment step in step S100 comprises: and adjusting the mechanical arm to conduct coordinate offset for a plurality of times in the positive and negative directions of the X, Y axis and recording the coordinate offset as initial hand-eye calibration data, establishing a plurality of groups of equations through a hand-eye calibration formula, and establishing an initial hand-eye calibration matrix based on a least square method.
9. An automatic hand-eye calibration system, comprising:
a storage unit for storing a program comprising the steps of the automatic hand-eye calibration method according to any one of claims 1 to 8 for the control unit, the processing unit to timely retrieve and execute;
the control unit is used for controlling the mechanical arm to adjust the pose, enabling the view finding area of the camera to be perpendicular to the calibration object, and identifying the calibration object to be marked as an initial point position; then, taking the initial point position as a starting point, adjusting the mechanical arm to carry out coordinate offset for a plurality of times in the positive and negative directions of the X, Y axis, and recording the coordinate offset as initial hand-eye calibration data; then controlling the mechanical arm to return to the initial point position;
a processing unit for according to the initialThe hand-eye calibration data are combined into a plurality of groups of equations through a hand-eye calibration formula, and an initial hand-eye calibration matrix is established based on a least square method; when the mechanical arm returns to the initial point position, calculating the position point of the current camera under the mechanical arm base coordinate according to the initial hand-eye calibration matrix, taking the position point as the center of a circle, constructing a calibration ring on a plane where a camera scenic spot is located by taking r as a radius, obtaining the distance D between the camera and a calibration object, taking one point P on the calibration ring, calculating the distance D from the P to the center of the calibration object, equally dividing the calibration ring into a plurality of quadrants, uniformly rotating preset angles to obtain a plurality of point positions on the calibration ring, and converting the point positions into the point positions of the tail end of the mechanical arm under the base coordinate through the initial hand-eye calibration matrix；
The control unit is also used for controlling the tail end of the mechanical arm to move to each point respectivelyThen, enabling the camera to identify the calibration object, and when the identification rate accords with the expectation, storing the point position information of the mechanical arm as hand-eye calibration data; then adjusting the distance between the camera and the calibration object to be d';
a processing unit for further processingEstablishing an auxiliary calibration ring for the radius, wherein the distance D from a point P' on the auxiliary calibration ring to the center of the calibration object is unchanged; then repeatedly dividing the auxiliary calibration ring into a plurality of quadrants, rotating the auxiliary calibration ring by a preset angle to obtain a plurality of point positions on the auxiliary calibration ring, and converting the point positions into point positions +_in the base coordinates of the tail end of the mechanical arm through an initial hand-eye calibration matrix>For the control unit to repeat the identification rate to be in line with the expected +.>Marking as hand-eye calibration data until the hand-eye calibration data reach standard, and according to the standardAnd obtaining hand-eye calibration data to calculate a new hand-eye calibration matrix.
10. A computer readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of the automatic hand-eye calibration method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310687548.7A CN116423525B (en) | 2023-06-12 | 2023-06-12 | Automatic hand-eye calibration method and system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310687548.7A CN116423525B (en) | 2023-06-12 | 2023-06-12 | Automatic hand-eye calibration method and system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116423525A CN116423525A (en) | 2023-07-14 |
| CN116423525B true CN116423525B (en) | 2023-09-01 |
Family
ID=87083553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310687548.7A Active CN116423525B (en) | 2023-06-12 | 2023-06-12 | Automatic hand-eye calibration method and system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116423525B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007061979A (en) * | 2005-09-01 | 2007-03-15 | Sharp Corp | Visual sensor correction method for robot arm and computer program |
| EP2199036A2 (en) * | 2008-12-02 | 2010-06-23 | KUKA Roboter GmbH | Method and device for compensating a kinematic deviation |
| CN112792816A (en) * | 2021-01-26 | 2021-05-14 | 杭州素问九州医疗科技有限公司 | Geometry-based hand-eye calibration method, robot, computer and storage medium |
| CN113664835A (en) * | 2021-09-15 | 2021-11-19 | 上海景吾智能科技有限公司 | Automatic hand-eye calibration method and system for robot |
| CN113696188A (en) * | 2021-10-27 | 2021-11-26 | 季华实验室 | Hand-eye calibration data acquisition method and device, electronic equipment and storage medium |
| CN116026368A (en) * | 2023-03-29 | 2023-04-28 | 上海仙工智能科技有限公司 | Mobile robot parameter joint calibration method and system, equipment and storage medium |
-
2023
- 2023-06-12 CN CN202310687548.7A patent/CN116423525B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007061979A (en) * | 2005-09-01 | 2007-03-15 | Sharp Corp | Visual sensor correction method for robot arm and computer program |
| EP2199036A2 (en) * | 2008-12-02 | 2010-06-23 | KUKA Roboter GmbH | Method and device for compensating a kinematic deviation |
| CN112792816A (en) * | 2021-01-26 | 2021-05-14 | 杭州素问九州医疗科技有限公司 | Geometry-based hand-eye calibration method, robot, computer and storage medium |
| CN113664835A (en) * | 2021-09-15 | 2021-11-19 | 上海景吾智能科技有限公司 | Automatic hand-eye calibration method and system for robot |
| CN113696188A (en) * | 2021-10-27 | 2021-11-26 | 季华实验室 | Hand-eye calibration data acquisition method and device, electronic equipment and storage medium |
| CN116026368A (en) * | 2023-03-29 | 2023-04-28 | 上海仙工智能科技有限公司 | Mobile robot parameter joint calibration method and system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116423525A (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111331592B (en) | Mechanical arm tool center point correcting device and method and mechanical arm system | |
| JP3946711B2 (en) | Robot system | |
| CN108827154B (en) | Robot non-teaching grabbing method and device and computer readable storage medium | |
| JP4191080B2 (en) | Measuring device | |
| CN113001535B (en) | Automatic correction system and method for robot workpiece coordinate system | |
| JP2005201824A (en) | Measuring device | |
| CN113492393A (en) | Robot teaching demonstration by human | |
| CN109822568B (en) | Robot control method, system and storage medium | |
| CN104802186A (en) | Robot programming apparatus for creating robot program for capturing image of workpiece | |
| CN101733755A (en) | Robot system, robot control device and method for controlling robot | |
| CN113664835B (en) | Automatic hand-eye calibration method and system for robot | |
| CN106003020A (en) | Robot, robot control device, and robotic system | |
| JP2015071206A (en) | Control device, robot, teaching data generation method, and program | |
| CN113379849A (en) | Robot autonomous recognition intelligent grabbing method and system based on depth camera | |
| US20220080581A1 (en) | Dual arm robot teaching from dual hand human demonstration | |
| US20090281662A1 (en) | Simulator for visual inspection apparatus | |
| JPH0780790A (en) | Three-dimensional object grasping system | |
| CN114347015A (en) | Robot grabbing control method, system, device and medium | |
| JP2003311670A (en) | Positioning control method of robot arm and robot equipment | |
| CN116423525B (en) | Automatic hand-eye calibration method and system and storage medium | |
| CN116423526B (en) | Automatic calibration method and system for mechanical arm tool coordinates and storage medium | |
| CN110039520B (en) | Teaching and processing system based on image contrast | |
| Xu et al. | Industrial robot base assembly based on improved Hough transform of circle detection algorithm | |
| CN116542914A (en) | Weld joint extraction and fitting method based on 3D point cloud | |
| CN111098306A (en) | Calibration method and device of robot, robot and storage medium |
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 |