CN110533727A - A kind of robot self-localization method based on single industrial camera - Google Patents
A kind of robot self-localization method based on single industrial camera Download PDFInfo
- Publication number
- CN110533727A CN110533727A CN201910666397.0A CN201910666397A CN110533727A CN 110533727 A CN110533727 A CN 110533727A CN 201910666397 A CN201910666397 A CN 201910666397A CN 110533727 A CN110533727 A CN 110533727A
- Authority
- CN
- China
- Prior art keywords
- robot
- coordinate system
- industrial
- industrial camera
- anchor point
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000009466 transformation Effects 0.000 claims abstract description 18
- 230000000007 visual effect Effects 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000003384 imaging method Methods 0.000 claims description 16
- 238000013519 translation Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- HOWHQWFXSLOJEF-MGZLOUMQSA-N systemin Chemical compound NCCCC[C@H](N)C(=O)N[C@@H](CCSC)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H]([C@@H](C)O)C(=O)N[C@@H](CC(O)=O)C(=O)OC(=O)[C@@H]1CCCN1C(=O)[C@H]1N(C(=O)[C@H](CC(O)=O)NC(=O)[C@H](CCCN=C(N)N)NC(=O)[C@H](CCCCN)NC(=O)[C@H](CO)NC(=O)[C@H]2N(CCC2)C(=O)[C@H]2N(CCC2)C(=O)[C@H](CCCCN)NC(=O)[C@H](CO)NC(=O)[C@H](CCC(N)=O)NC(=O)[C@@H](NC(=O)[C@H](C)N)C(C)C)CCC1 HOWHQWFXSLOJEF-MGZLOUMQSA-N 0.000 claims description 2
- 108010050014 systemin Proteins 0.000 claims description 2
- 238000005553 drilling Methods 0.000 description 9
- 230000004807 localization Effects 0.000 description 7
- 238000005259 measurement Methods 0.000 description 6
- 230000033001 locomotion Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 231100000572 poisoning Toxicity 0.000 description 2
- 230000000607 poisoning effect Effects 0.000 description 2
- 230000035807 sensation Effects 0.000 description 2
- 241001074085 Scophthalmus aquosus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000012636 effector Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/97—Determining parameters from multiple pictures
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Operations Research (AREA)
- Manipulator (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a kind of robot self-localization methods based on single industrial camera, belong to industrial robot field, anchor point known to six or more coordinates is successively individually imaged in the industrial camera that method of the invention only needs that robot is driven to drive end in a manner of teaching, it can quickly and easily determine the transformation relation between world coordinate system and robot basis coordinates system, realize robot self-localization.The present invention in same piece image without being imaged the multiple target points being distributed within the scope of larger space, as long as and successively each anchor point is individually imaged respectively;The limitation of the method for the present invention not camera subject visual field size and anchor point distributed architecture;The present invention is successively individually imaged established solving model and method for solving for multiple anchor points and can be widely applied to solve the problems, such as the self-positioning of all kinds of " hand-eye " robot systems.
Description
Technical field
The present invention relates to industrial robot field, specially a kind of robot self-localization side based on single industrial camera
Method.
Background technique
With the high speed development of intelligent Manufacturing Technology, industrial robot in industrial circle using more and more extensive.Its
In, riveting actuator will be bored and be fixed on that articulated arm industrial robot end carries out automation drilling and riveting is current aircraft dress
With a research hotspot in field, and gradually start to step into practical stage, substitutes traditional manual work.Machine
People's automatic Drilling/Riveting can not only greatly improve drilling and riveting quality, also can effectively improve and bore riveting efficiency.
Robot bores before the work of riveting system, it is thus necessary to determine that position and posture of the robot in world coordinate system.It is alive
The case where boundary's coordinate system is overlapped with workpiece coordinate system is, that is, it needs to be determined that riveting piece coordinate system to be drilled and robot coordinate
Transformation relation between system.This link is known as robot localization (also referred to as robot centering, workpiece positioning, workpiece centering).
During aircraft puts together machines people's automatic Drilling/Riveting operation at present, robot localization mainly uses the big ruler such as laser tracker
Very little measuring device is completed.On the one hand, it needs to survey multiple characteristic points in drilled riveting piece using external measurement devices
Amount, and then establish workpiece coordinate system and measure the transformation relation between coordinate system;On the other hand, it is arranged on robot end
Target spot (target ball), control robot are rotated around different axis, a position are often rotated to, using external measurement equipment to robot
The target spot arranged on end carries out three-dimensional coordinate measurement, then a series of three-dimensional coordinates of target spot carry out when by rotating around each axis
Circular fitting, and then set up robot basis coordinates system and measure the transformation relation between coordinate system.Then, it is sat according to workpiece
Transformation relation between transformation relation, robot basis coordinates system between mark system and measurement coordinate system and measurement coordinate system, calculates
Transformation relation between workpiece coordinate system and robot basis coordinates system, to realize robot localization.This utilization is externally measured
The method that equipment carries out robot localization is not only needed by additional measuring device, and complex steps are time-consuming, measure
Journey and positioning calculation process are difficult to realize integrated and automate.
In the robot automatic Drilling/Riveting system assembled towards aircraft, in order to guarantee the accuracy of robot hole position,
An industrial camera, the online compensation for drilling location error can be connected firmly in the brill riveting actuator of robot end.According to
Some machine vision theory and methods shoot target point known to n relative position using an industrial camera, can solve
Pose of the camera relative to known target point out, this is referred to as perspective n point problem (PnP problem).It solves PnP problem and requires camera
N target point is imaged simultaneously in piece image, in order to guarantee the uniqueness and accuracy that solve, general n >=6 in industrial application,
And n target point should be distributed in as far as possible in a biggish spatial dimension.However, due to boring the industrial phase in riveting actuator
Machine shoots image every time and all only needs the benchmark to independent 5 millimeters of a diameter or so when carrying out drilling error online compensation
Hole (or benchmark rivet) is imaged, and in order to guarantee the image quality of datum hole, avoid captured single datum hole
Shared region is too small in the picture, and the visual field of the industrial camera connected firmly in end effector of robot is usually smaller, Wu Fa
The multiple target points being distributed within the scope of larger space are imaged in piece image simultaneously.Therefore, automatic Drilling/Riveting before making the present invention
The included industrial camera of robot is not used to robot self poisoning.It is additional to continue to use laser tracker etc. always in the industry at present
Measuring device carry out cumbersome robot localization work.
Summary of the invention
The present invention aiming at the problems existing in the prior art, disclose a kind of robot based on single industrial camera from
Localization method, the single industrial camera for being fixed on robot end using one determine six or more in world coordinate system
Site successively shoots image, determines the transformation relation between robot basis coordinates system and world coordinate system according to this group of image.This
It is quickly and easily self-positioning in working site that the method for invention can be realized industrial robot.
The present invention is implemented as follows:
A kind of robot self-localization method based on single industrial camera, including industrial robot, the industrial machine
People includes robot end's ring flange, and the robot ring flange front end is fixed with an industrial camera;In world coordinate system
There are n anchor points distinguishable in visual pattern, n >=6, and n anchor point be not conllinear, n anchor point is in world coordinate system
OWUnder coordinate it is known that being denoted as Pi=(Xi,Yi,Zi)T, i=1,2, L, n carry out industrial robot certainly using single industrial camera
The method of positioning comprising the steps of:
Step 1: control industrial robot is mobile, the contained industrial camera of robot end is made successively to reach i-th of positioning
Point top can be to the position of the anchor point blur-free imaging, i=1,2, L, n, and control industrial camera shoots the figure of the anchor point
Picture, and record robot ring flange coordinate system O under the positionFOrigin is with respect to industrial robot basis coordinates system ORIt is flat between origin
The amount of shifting toAnd the Eulerian angles α of robot ring flangei,βi,γi;
Step 2: robot ring flange coordinate system O when calculating i-th of anchor point of shooting using formula (1)FRelative to machine
Device people's basis coordinates system ORSpin matrix
Robot ring flange coordinate system O when indicating to shoot i-th of anchor point using formula (2)FRelative to robot basis coordinates
It is ORTransformation matrix
Step 3: in the image of i-th shooting, the image coordinate of i-th of anchor point is extracted, (u is denoted asi,vi);
Step 4: according to the transformation relation and camera imaging model between coordinate system, world coordinates is solved using formula (3)
It is OWRelative to robot basis coordinates system ORTransformation relationComplete positioning of the robot in world coordinate system:
In formula (3), λiFor proportionality coefficient, K is the Intrinsic Matrix of industrial camera,
Wherein αx, αy, s, u0, v0For the camera imaging parameter calibrated.
Further, the industrial robot lower end is provided with robot motion's guide rail;The anchor point, which is set to, to be added
Work tooling rack is further fixedly arranged on workpiece to be processed on the processing tool rack.
Further, the industrial camera is perspective imaging camera;The imaging parameters and coordinate of the industrial camera
It is OCWith ring flange coordinate system OFBetween 4 × 4 transformation matrixsIt is calibrated;N anchor point is in world coordinate system OWUnder
Coordinate it is known that being denoted as Pi=(Xi,Yi,Zi)T, i=1,2, L, n.
Further, the contained industrial camera in industrial robot end successively reaches n anchor point top position shooting
Image, image coordinate (u of the n anchor point in captured n width imagei,vi), i=1,2, L, n, discrete distribution
In the different location of the industrial camera plane of delineation.
Further, it is solved in the step four using formula (3)Method comprise the steps of:
4.1, for known quantityIt enables
Wherein m1 i, m2 i, m3 iIt is three-dimensional row vector, m14 i, m24 i, m34 iFor scalar value;Note:
It is obtained according to formula (3):
According to (4) formula, formed system of linear equations (5)
System of linear equations (5) are solved with least square method, obtain world coordinate system O to be solvedWRelative to industrial machine
People's basis coordinates system ORTransformation relationIn spin matrix and translation vector primary Calculation result
With
4.2, solve so thatFrobenius Norm minimum unit orthogonal matrix
4.3, system of linear equations (6) are solved
It obtains
4.4, withWithFor world coordinate system O to be solvedWRelative to industrial robot (3) basis coordinates system OR's
Transformation relationIn spin matrix and translation vector initial value, by nonlinear optimization method solve formula (7) obtain's
Final result:
Wherein
The beneficial effect of the present invention compared with prior art is:
1, existing robot localization method is needed using additional measuring device, process very complicated at present, and is surveyed
Amount process and positioning calculation process are difficult to realize integrated and automate;Method of the invention is not necessarily to other additional measuring devices, directly
It connects using the single industrial camera carried on industrial robot, robot self-localization can be completed, it is easier, quick, easy
Row;
2, traditional method positioned based on single camera shot image by solving PnP problem, needs camera one
It is secondary that the multiple target points being distributed within the scope of larger space are imaged, but the included industrial camera of robot is regarded under normal conditions
Place limit is difficult to realize, and the industrial camera that the method for the present invention only needs robot included successively respectively determines six or more
Site is individually imaged, and camera subject visual field does not limit;
3, for multiple anchor points, successively individually newly-established solving model and solution are created in imaging to the method for the invention
Method can be widely applied to solve the problems, such as the self-positioning of all kinds of " hand-eye " robot systems;
4, method of the invention only need the industrial camera of robot end to anchor point known to six or more coordinates according to
Secondary independent imaging can quickly and easily determine the transformation relation between world coordinate system and robot basis coordinates system, realize
Robot self-localization;This method is in addition to also can be applied to other than aircraft puts together machines in people's automatic Drilling/Riveting and has clear demand
End has the robot self-localization of industrial camera in other field.
Detailed description of the invention
Fig. 1 is a kind of robot self-localization method based on single industrial camera in particularly preferred embodiment of the invention
System composition schematic diagram;
Fig. 2 is six positioning point images of robot shooting in particularly preferred embodiment of the invention, and the positioning extracted
Point image coordinate;
Wherein, 1- processing tool rack, 2- workpiece to be processed, 3- industrial robot, 3-1- robot ring flange, 3-2-
Industrial camera, 4- robot motion guide rail, 5- world coordinate system, 6- anchor point.
Specific embodiment
It is clear to keep the purpose of the present invention, technical solution and effect clearer, be exemplified below example to the present invention into
One step is described in detail.It should be understood that specific implementation described herein is not used to limit this hair only to explain the present invention
It is bright.
As shown in Figure 1, including industrial robot 3 in self locating device of the invention, the industrial robot 3 includes
End flange 3-1, the front end robot ring flange 3-1 are connected industrial camera 3-2.
3 lower end of industrial robot is provided with robot motion's guide rail 4 in the embodiment of the present invention, in world coordinate system 5
There are 6 distinguishable in visual pattern and not conllinear anchor points.6 anchor points are located at processing tool rack 1 in the present embodiment
On, workpiece to be processed 2 is further fixedly arranged on the processing tool rack 1.Single industrial camera 3-2 is fixed on robot
On ring flange;Industrial camera 3-2 is perspective imaging camera;The imaging parameters of industrial camera 3-2 and the industrial camera coordinate
It is OCWith robot ring flange 3-1 coordinate system OFBetween 4 × 4 transformation matrixsIt is calibrated.
In this embodiment, industrial camera is the GC2450M model camera and Schneider of AVT company, Germany production
The KREUZNACH APO-XENOPLAN 1.4/23-0903 model camera lens of company's production, image resolution ratio are 2448 × 2050,
Effective viewing field 71mm × 59mm, image have been subjected to distortion correction, camera Intrinsic Matrix
Hand-eye relational matrix has been subjected to calibration, is
In this embodiment, the artificial KUKA-KR30 articulated arm industrial robot of machine, on processing tool rack
There are six the concentric round sensation target of black and white, the center of circle of white circular is the positioning in the present embodiment on each sensation target
Point, six anchor points are in world coordinate system OWUnder coordinate it is known that being denoted as Pi=(Xi,Yi,Zi)T, i=1,2, L, 6, it is specific to sit
Scale value is as shown in Table 1.In practical engineering applications, anchor point generally can be in the anchor point spread in workpiece and its tooling
The heart, three-dimensional coordinate are set in the design phase, and guarantee the position precision of positioning dot center by process.
Table one
In the present embodiment, method for self-locating is carried out using industrial robot 3 comprising the steps of:
Step 1: controlling robot end's movement by robot interactive tutorial function, make the contained industry of robot end
Camera 3-2 is successively reached can be to the position of the independent blur-free imaging of corresponding anchor point, under each position above six anchor points
It controls the industrial camera and shoots the image of corresponding anchor point, and record robot ring flange coordinate system O under the positionFOrigin
Opposed robots' basis coordinates system ORTranslation vector between originAnd the Eulerian angles α of robot ring flangei,βi,γi, i
=1,2, L, 6, six robot motion's parameter physical record results in the present embodiment are as shown in Table 2;
Table two
Step 2: robot ring flange coordinate system O when calculating i-th of anchor point of shooting using formula (1)FRelative to machine
Device people's basis coordinates system ORSpin matrix
Robot ring flange coordinate system O when indicating to shoot i-th of anchor point using formula (2)FRelative to robot basis coordinates
It is ORTransformation matrix
Step 3: extracting the image coordinate of i-th of anchor point in the image of i-th shooting, being denoted as (ui,vi), i
=1,2, L, 6;
Step 4: solving world coordinates using formula (3) according to transformation relation and camera imaging model between coordinate system
It is OWRelative to robot basis coordinates system ORTransformation relationComplete positioning of the robot in world coordinate system:
In formula (3), λiFor proportionality coefficient, K is the Intrinsic Matrix of calibrated industrial camera;
As shown in Fig. 2, the present embodiment is in step 1, the contained industrial camera of robot end successively reaches six
Anchor point top position shoots image, image coordinate (u of six anchor points in six captured width imagesi,vi), i=1,
2, L, 6, the different location for being distributed in the industrial camera plane of delineation as discrete as possible, specific six anchor points are in image
It is as shown in Table 3 that position coordinates in plane extract result.
Table three
Further, formula (3) are utilized to solve in step 4Method, the present embodiment comprises the steps of:
4.1, for known quantityIt enables
Wherein m1 i, m2 i, m3 iIt is three-dimensional row vector, m14 i, m24 i, m34 iFor scalar value;Note
It is obtained according to formula (3):
According to (4) formula, formed system of linear equations (5)
System of linear equations (5) are solved with least square method, obtain world coordinate system O to be solvedWRelative to robot base
Coordinate system ORTransformation relationIn spin matrix and translation vector primary Calculation result
With
4.2, by singular value decomposition method solve so thatFrobenius Norm minimum unit just
Hand over matrix
4.3, system of linear equations (6) are solved
It obtains
4.4, withWithFor world coordinate system O to be solvedWRelative to robot basis coordinates system ORTransformation close
SystemIn spin matrix and translation vector initial value, by nonlinear optimization method solve formula (7) obtainMost termination
Fruit:
Wherein
Finally find out
For the accuracy of comparative illustration this patent methods and results, using additional independent commercial measuring system to this reality
It applies the robot basis coordinates in example and the transformation relation between world coordinate system is measured.Using independent commercial measurement system
The result that unified test measures is denoted asSpecially
The result that the method for the present invention obtainsWith the positioning result of commercial measuring systemCompare, corresponding spin moment
The Frobenius norm of battle arrayIt is 0.008, the Frobenius norm of corresponding translation vectorFor
4.952.As it can be seen that the result that result and commercial measuring system that the method for robot self-localization obtains obtain is smaller compared to deviation,
It is the effective ways of robot self poisoning.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (4)
1. a kind of robot self-localization method based on single industrial camera, including industrial robot (3), world coordinate system (5),
It is characterized in that, the industrial robot (3) includes robot ring flange (3-1), before the robot ring flange (3-1)
End is fixed with industrial camera (3-2);There are n anchor points (6) distinguishable in visual pattern in world coordinate system (5), n >=6,
And n anchor point be not conllinear;Industrial robot (3) self-positioning method is carried out using industrial camera (3-2), includes following step
It is rapid:
Step 1: control industrial robot (3) is mobile, so that the contained industrial camera of robot end (3-2) is successively reached i-th and determine
The figure of the anchor point can be shot to the position of the anchor point blur-free imaging, i=1,2, L, n, control industrial camera above site
Picture, and record robot ring flange (3-1) coordinate system O under the positionFOrigin is with respect to industrial robot (3) basis coordinates system OROrigin
Between translation vectorAnd the Eulerian angles α of robot ring flange (3-1)i,βi,γi;
Step 2: robot ring flange coordinate system O when calculating i-th of anchor point of shooting using formula (1)FRelative to robot base
Coordinate system ORSpin matrixI=1,2, L, n:
Robot ring flange coordinate system O when indicating to shoot i-th of anchor point using formula (2)FRelative to robot basis coordinates system OR's
Transformation matrixI=1,2, L, n,
Step 3: in the image of i-th shooting, the image coordinate of i-th of anchor point is extracted, (u is denoted asi,vi);
Step 4: according to the transformation relation and camera imaging model between coordinate system, world coordinate system O is solved using formula (3)WPhase
For robot basis coordinates system ORTransformation relationComplete positioning of the robot in world coordinate system:
In formula (3), λiFor proportionality coefficient, K is the Intrinsic Matrix of industrial camera,
Wherein αx, αy, s, u0, v0For the camera imaging parameter calibrated.
2. a kind of robot self-localization method based on single industrial camera according to claim 1, which is characterized in that institute
The industrial camera (3-2) stated is perspective imaging camera;The imaging parameters and coordinate system O of the industrial camera (3-2)CWith method
Blue disk (3-1) coordinate system OFBetween 4 × 4 transformation matrixsIt is calibrated;N anchor point is in world coordinate system OWUnder
Coordinate is it is known that be denoted as Pi=(Xi,Yi,Zi)T, i=1,2, L, n.
3. a kind of robot self-localization method based on single industrial camera according to claim 1, which is characterized in that institute
The contained industrial camera in industrial robot (3) end (3-2) successively reaches n anchor point top position shooting figure in the step of stating one
Picture, image coordinate (u of the n anchor point in captured n width imagei,vi), i=1,2, L, n are discrete to be distributed in institute
State the different location of the industrial camera plane of delineation.
4. a kind of robot self-localization method based on single industrial camera according to claim 1, which is characterized in that institute
It is solved in the step of stating four using formula (3)Method comprise the steps of:
4.1, for known quantityI=1,2, L, n are enabled
Wherein m1 i, m2 i, m3 iIt is three-dimensional row vector, m14 i, m24 i, m34 iFor scalar value;Note:
It is obtained according to formula (3):
According to (4) formula, formed system of linear equations (5)
System of linear equations (5) are solved with least square method, obtain world coordinate system O to be solvedWRelative to industrial robot (3)
Basis coordinates system ORTransformation relationIn spin matrix and translation vector primary Calculation result
With
4.2, solve so thatFrobenius Norm minimum unit orthogonal matrix
4.3, system of linear equations (6) are solved
It obtains
4.4, withWithFor world coordinate system O to be solvedWRelative to industrial robot (3) basis coordinates system ORTransformation close
SystemIn spin matrix and translation vector initial value, by nonlinear optimization method solve formula (7) obtainMost termination
Fruit:
Wherein
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910666397.0A CN110533727B (en) | 2019-07-23 | 2019-07-23 | Robot self-positioning method based on single industrial camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910666397.0A CN110533727B (en) | 2019-07-23 | 2019-07-23 | Robot self-positioning method based on single industrial camera |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110533727A true CN110533727A (en) | 2019-12-03 |
CN110533727B CN110533727B (en) | 2023-07-11 |
Family
ID=68661843
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910666397.0A Active CN110533727B (en) | 2019-07-23 | 2019-07-23 | Robot self-positioning method based on single industrial camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110533727B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112157284A (en) * | 2020-09-29 | 2021-01-01 | 蒙美兰 | Industrial robot automatic drilling system and use method |
CN112833883A (en) * | 2020-12-31 | 2021-05-25 | 杭州普锐视科技有限公司 | Indoor mobile robot positioning method based on multiple cameras |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108827154A (en) * | 2018-07-09 | 2018-11-16 | 深圳辰视智能科技有限公司 | A kind of robot is without teaching grasping means, device and computer readable storage medium |
CN109059755A (en) * | 2018-06-11 | 2018-12-21 | 天津科技大学 | A kind of robot high-precision hand and eye calibrating method |
CN109389642A (en) * | 2017-08-04 | 2019-02-26 | 惠州市阿图达机电有限公司 | Vision system is to the scaling method of robot, system and has store function device |
CN109807937A (en) * | 2018-12-28 | 2019-05-28 | 北京信息科技大学 | A kind of Robotic Hand-Eye Calibration method based on natural scene |
-
2019
- 2019-07-23 CN CN201910666397.0A patent/CN110533727B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109389642A (en) * | 2017-08-04 | 2019-02-26 | 惠州市阿图达机电有限公司 | Vision system is to the scaling method of robot, system and has store function device |
CN109059755A (en) * | 2018-06-11 | 2018-12-21 | 天津科技大学 | A kind of robot high-precision hand and eye calibrating method |
CN108827154A (en) * | 2018-07-09 | 2018-11-16 | 深圳辰视智能科技有限公司 | A kind of robot is without teaching grasping means, device and computer readable storage medium |
CN109807937A (en) * | 2018-12-28 | 2019-05-28 | 北京信息科技大学 | A kind of Robotic Hand-Eye Calibration method based on natural scene |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112157284A (en) * | 2020-09-29 | 2021-01-01 | 蒙美兰 | Industrial robot automatic drilling system and use method |
CN112833883A (en) * | 2020-12-31 | 2021-05-25 | 杭州普锐视科技有限公司 | Indoor mobile robot positioning method based on multiple cameras |
CN112833883B (en) * | 2020-12-31 | 2023-03-10 | 杭州普锐视科技有限公司 | Indoor mobile robot positioning method based on multiple cameras |
Also Published As
Publication number | Publication date |
---|---|
CN110533727B (en) | 2023-07-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111775146B (en) | Visual alignment method under industrial mechanical arm multi-station operation | |
KR102280663B1 (en) | Calibration method for robot using vision technology | |
CN108399639A (en) | Fast automatic crawl based on deep learning and arrangement method | |
CN110450163A (en) | The general hand and eye calibrating method based on 3D vision without scaling board | |
CN110276799B (en) | Coordinate calibration method, calibration system and mechanical arm | |
CN107590835A (en) | Mechanical arm tool quick change vision positioning system and localization method under a kind of nuclear environment | |
CN109848951A (en) | Automatic processing equipment and method for large workpiece | |
CN109877840A (en) | A kind of double mechanical arms scaling method based on camera optical axis constraint | |
CN112833792B (en) | Precision calibration and verification method for six-degree-of-freedom mechanical arm | |
TWI699264B (en) | Correction method of vision guided robotic arm | |
CN112958960B (en) | Robot hand-eye calibration device based on optical target | |
CN114643578B (en) | Calibration device and method for improving robot vision guiding precision | |
CN110533727A (en) | A kind of robot self-localization method based on single industrial camera | |
CN110202560A (en) | A kind of hand and eye calibrating method based on single feature point | |
CN109059755B (en) | High-precision hand-eye calibration method for robot | |
CN111145272A (en) | Manipulator and camera hand-eye calibration device and method | |
CN111482964A (en) | Novel robot hand-eye calibration method | |
CN114654465A (en) | Welding seam tracking and extracting method based on line laser structure optical vision sensing | |
CN110962127B (en) | Auxiliary calibration device for tail end pose of mechanical arm and calibration method thereof | |
CN206633018U (en) | Integrated apparatus is assembled in flexible on-line measurement for shaft hole matching | |
CN112238453B (en) | Vision-guided robot arm correction method | |
CN215037637U (en) | Camera external parameter calibration device for visual guidance of industrial robot | |
CN112598752A (en) | Calibration method based on visual identification and operation method | |
CN116619350A (en) | Robot error calibration method based on binocular vision measurement | |
CN211699034U (en) | Hand-eye calibration device for manipulator and camera |
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 |