CN108871194B - Visual sensor work functions quick recovery method - Google Patents
Visual sensor work functions quick recovery method Download PDFInfo
- Publication number
- CN108871194B CN108871194B CN201810766927.4A CN201810766927A CN108871194B CN 108871194 B CN108871194 B CN 108871194B CN 201810766927 A CN201810766927 A CN 201810766927A CN 108871194 B CN108871194 B CN 108871194B
- Authority
- CN
- China
- Prior art keywords
- coordinate system
- visual sensor
- rotation translation
- robot
- translation relation
- 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
- 230000000007 visual effect Effects 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000006870 function Effects 0.000 title claims abstract description 23
- 238000011084 recovery Methods 0.000 title claims abstract description 16
- 238000013519 translation Methods 0.000 claims abstract description 30
- 238000005259 measurement Methods 0.000 claims abstract description 16
- 230000004438 eyesight Effects 0.000 claims abstract description 14
- 239000003550 marker Substances 0.000 claims description 5
- 230000008569 process Effects 0.000 abstract description 7
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000002407 reforming Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Manipulator (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a kind of visual sensor work functions quick recovery methods, include the following steps: 1) coarse adjustment, and measured object is enabled to be in visual sensor within sweep of the eye；2) pass through method I: hand and eye calibrating method obtains camera coordinates system to the rotation translation relation of flange coordinate systemOr method II: according toRotation translation relation of the calculating camera coordinates system to flange coordinate system3) pass through formulaCalculate the rotation translation relation of workpiece coordinate system and robot coordinate system determined by measured object
Description
Technical field
The present invention relates to the guidance of industry spot robot vision, fields of measurement, and in particular to a kind of visual sensor work
Function quick recovery method.
Background technique
Robot vision is the system for instigating robot to have visual perception function, is the important portion of robot system composition
/ mono-.Robot vision can obtain the image of external environment, measured object by visual sensor, and pass through vision processor
It is analyzed and is explained, and then be converted to symbol, allowed robot that can recognize object, determine position.Due to robot vision system
The automation of system, flexibility feature, in recent years, visual sensor is widely used in industrial robot fields of measurement.
Include workpiece, robot, and be connected to robot for the vision guide of industry spot, the equipment of measurement station
The visual sensor of end.Since robot need to work along the motion profile of high reproducibility in the course of work, entirely grab
Part feeding or the process of measurement, robot need to select standard movement track.In entire motion profile, need to guarantee visual sensing
The relative positional relationship of device and robot end remain unchanged.
Due to industrial environment complexity, the position of visual sensor can be moved because of collision, overhaul of the equipments etc., enable view
Feel that the relative position of sensor and robot end change.Conventional method is marked to the visual sensor after shift in position
It is fixed, and the record that standard trajectory is reformed in track is measured for robot.This process needs continuously attempt to, the measurement of verifier people
Track keeps records of position of the standard trajectory under visual sensor coordinate system after robot measurement track is completely errorless
Confidence breath, whole process is time-consuming more, has seriously dragged slowly industrial production progress.
Summary of the invention
In order to solve the above-mentioned technical problems, the present invention provides a kind of visual sensor work functions quick recovery method,
It, without doing standard movement track again, saves original method multiple authentication robot after visual sensor change in location
Time needed for measuring track, finding record standard track, effectively improve working efficiency.
A kind of visual sensor work functions quick recovery method, includes the following steps:
1) after visual sensor is relative to the position movement of robot end's flange, first with coarse adjustment, measured object is enabled to be in
Visual sensor is within sweep of the eye；
2) pass through method I: hand and eye calibrating method obtains camera coordinates system to the rotation translation relation of flange coordinate system
Or method II: according to the rotation translation relation of following formula calculating camera coordinates system to flange coordinate system
In formula,For the rotation translation relation of camera coordinates system before dynamic camera to flange coordinate system；
For the rotation translation relation of workpiece coordinate system determined by fixed characteristic points before dynamic camera to camera coordinates system；
For the rotation translation relation of workpiece coordinate system determined by fixed characteristic points after dynamic camera to camera coordinates system；
Fixed characteristic points are position multiple characteristic points fixed always, the rotation translation of workpiece coordinate system to camera coordinates system
RelationshipIt is that the two-dimensional coordinate of three-dimensional coordinate and characteristic point in the picture using fixed characteristic points under local Coordinate System is asked
Solution；
3) pass through formulaIt calculates workpiece coordinate system determined by measured object and robot is sat
Mark the rotation translation relation of system
In formula,Indicate that the rotation translation relation of robot coordinate system, it is constant to move camera front and back for flange coordinate system；
It is to utilize two-dimensional coordinate of the characteristic point in the three-dimensional coordinate and picture under local Coordinate System on measured object
It solves.
Because including camera in visual sensor, so camera coordinates system is further understood that visual sensor coordinate
System；
Situation before dynamic camera is situation when visual sensor does not occur mobile relative to robot end's flange position；
Situation after dynamic camera for visual sensor relative to robot end's flange position after mobile.
Further, the fixed characteristic points are 5~15.
Further, the fixed characteristic points are reflective marker point or machined features point.
Further, the fixed characteristic points are fixed in station, and position remains unchanged.
Further,It is obtained using robot kinematics' model.
Further, when the work functions of visual sensor are guided robot grip, measured object is to be grabbed workpiece；
Further, when the work functions of visual sensor are measurement, measured object is measurement object.
Further, in method I hand and eye calibrating method specific explanations be robotic actuator end (crawl arm) coordinate system and
Sensor (for example being used to measure target position and direction in three-dimensional space and be fixed on the video camera on robot) coordinate system
Between correlation, determine the hand and eye calibrating that this transformational relation is just known as in robot field.
Further, camera takes pictures to calibration gridiron pattern from multiple robot poses in the hand and eye calibrating method.
This method advantage: it when visual sensor needs to return to normal condition function, first passes through and position adjustment is calculated
Rotation translation relation of the camera coordinates system to flange coordinate system afterwardsIt recycles formula to calculate workpiece determined by measured object to sit
The rotation translation relation of mark system and robot coordinate systemWithout reforming standard movement track, it is multiple to save original method
Time needed for verifier people measures track, finds record standard track, effectively improve working efficiency.
When this method to be used for the measurement process of auto production line, the time-consuming comparison of different robot vision measurement stations
Table is as follows:
As can be seen from the table: due to needing to carry out standard trajectory record again, when the warehouse compartment of station, vehicle are numerous (i.e.
Zero-bit is more) in the case where, the adjustment duration of position needed for existing method increases at multiple, and only needs half an hour using this method,
Visual sensor is greatly reduced and restores the time used in function again.Assuming that the automobile in 50JPH (/ hour) processes
Line, interior at the same time, this method can at least produce 75 vehicles more, bring great economic benefit for factory.
Detailed description of the invention
Fig. 1 is visual sensor working system diagram in the present invention；
Fig. 2 is the system schematic that visual sensor shooting calibration gridiron pattern carries out hand and eye calibrating in embodiment 1；
Fig. 3 is the system schematic that visual sensor shoots fixed characteristic points in embodiment 2.
Specific embodiment
Embodiment 1
Visual sensor work functions quick recovery method provided by the invention is applied to guidance car door and grabs erector
Make, when visual sensor changes relative to the position of robot end, work functions quick recovery method, including such as
Lower step:
1) after visual sensor is relative to the position movement of robot end's flange, first with coarse adjustment, the spy on car door is enabled
Sign point is in visual sensor within sweep of the eye；
2) rotation translation relation of the camera coordinates system to flange coordinate system after being changed by hand and eye calibrating method acquisition
Specifically, in the vision guide station of the present embodiment, fixed calibration gridiron pattern is installed, camera is from multiple robots
Pose carries out multi-angle to calibration gridiron pattern and takes pictures, and by the calculating to X-comers information, obtains
3) pass through formulaCalculate workpiece coordinate system determined by car door workpiece to be grabbed with
The rotation translation relation of robot coordinate systemThus, it is possible to treat crawl vehicle using the visual sensor after shift in position
Door carries out robot vision bootup process；
In formula,Indicate that the rotation translation relation of robot coordinate system, it is constant to move camera front and back for flange coordinate system；Into
One step,It is obtained using robot kinematics' model.
It is using wait grab the characteristic point on car door two in the three-dimensional coordinate and picture under local Coordinate System
Coordinate is tieed up to solve.
Embodiment 2
Visual sensor work functions quick recovery method provided by the invention is applied to white body and detects work, works as view
When feeling that sensor changes relative to the position of robot end, work functions quick recovery method includes the following steps:
1) it after visual sensor is relative to the position movement of robot end's flange, first with coarse adjustment, enables on white body
Mark point is in visual sensor within sweep of the eye；
2) according to the rotation translation relation of following formula calculating camera coordinates system to flange coordinate system
In formula,For the rotation translation relation of camera coordinates system before dynamic camera to flange coordinate system；
For the rotation translation relation of workpiece coordinate system determined by fixed characteristic points before dynamic camera to camera coordinates system；
For the rotation translation relation of workpiece coordinate system determined by fixed characteristic points after dynamic camera to camera coordinates system；
Specifically: fixed characteristic points are position multiple characteristic points fixed always, and characteristic point quantity is at 5~15, originally
In embodiment, the ground that 15 reflective marker points are fixed on robot vision detection station is chosen, drives position to become by robot
Visual sensor before dynamic takes pictures to 15 reflective marker points, obtains the image comprising 15 characteristic points, anti-using 15
Two-dimensional coordinate of the signal point in the three-dimensional coordinate and image under local Coordinate System solves to obtain
After sensor position changes, robot drives the visual sensor after shift in position to 15 reflective markers again
Point is taken pictures, and the image comprising 15 characteristic points is obtained, and utilizes three-dimensional seat of 15 reflective marker points under local Coordinate System
Two-dimensional coordinate in mark and image solves to obtain
3) pass through formulaCalculate workpiece coordinate system and machine determined by tested white body
The rotation translation relation of people's coordinate systemThus, it is possible to using the visual sensor after shift in position to tested white body into
The measurement of row robot vision；
In formula,Indicate that the rotation translation relation of robot coordinate system, it is constant to move camera front and back for flange coordinate system；Into
One step,It is obtained using robot kinematics' model.
It is to utilize two-dimensional coordinate of the characteristic point in the three-dimensional coordinate and picture under local Coordinate System on measured object
It solves.
This method does not need to re-start the record of standard trajectory data, to save the plenty of time, guarantees that vision passes
Sensor rapidly enters working condition, and measurement station rapidly enters production status.
For ease of explanation and precise definition of the appended claims, term " on ", "lower", "inner" and "outside" be used to refer to
The position of these shown features describes the features of illustrative embodiments in attached drawing.
The description that specific exemplary embodiment of the present invention is presented in front is for the purpose of illustration and description.Front
Description be not intended to become without missing, be not intended to limit the invention to disclosed precise forms, it is clear that root
It is possible for much changing and change all according to above-mentioned introduction.It selects exemplary implementation scheme and is described to be to explain this hair
Bright certain principles and practical application, so that others skilled in the art can be realized and utilize of the invention each
Kind exemplary implementation scheme and its different selection forms and modification.The scope of the present invention be intended to by the appended claims and
Its equivalent form is limited.
Claims (6)
1. a kind of visual sensor work functions quick recovery method, it is characterised in that include the following steps:
1) after visual sensor is relative to the position movement of robot end's flange, first with coarse adjustment, measured object is enabled to be in vision
Sensor is within sweep of the eye；
2) pass through method I: hand and eye calibrating method obtains camera coordinates system to the rotation translation relation of flange coordinate system
Or method II: according to the rotation translation relation of following formula calculating camera coordinates system to flange coordinate system
In formula,For the rotation translation relation of camera coordinates system before dynamic camera to flange coordinate system；
For the rotation translation relation of workpiece coordinate system determined by fixed characteristic points before dynamic camera to camera coordinates system；
For the rotation translation relation of workpiece coordinate system determined by fixed characteristic points after dynamic camera to camera coordinates system；
Fixed characteristic points are position multiple characteristic points fixed always, the rotation translation relation of workpiece coordinate system to camera coordinates systemIt is to be solved using the two-dimensional coordinate of three-dimensional coordinate and characteristic point of the fixed characteristic points under local Coordinate System in the picture；
3) pass through formulaCalculate workpiece coordinate system and robot coordinate system determined by measured object
Rotation translation relation
In formula,Indicate that the rotation translation relation of robot coordinate system, it is constant to move camera front and back for flange coordinate system；
It is to be asked using two-dimensional coordinate of the characteristic point on measured object in the three-dimensional coordinate and picture under local Coordinate System
Solution.
2. visual sensor work functions quick recovery method as described in claim 1, it is characterised in that: the fixed characteristic points
It is 5~15.
3. visual sensor work functions quick recovery method as described in claim 1, it is characterised in that: the fixed characteristic points
For reflective marker point or machined features point.
4. visual sensor work functions quick recovery method as described in claim 1, it is characterised in that: the fixed characteristic points
It is fixed in station, position remains unchanged.
5. visual sensor work functions quick recovery method as described in claim 1, it is characterised in that:Utilize robot
Kinematics model obtains.
6. visual sensor work functions quick recovery method as described in claim 1, it is characterised in that: when visual sensor
When work functions are guided robot grip, measured object is to be grabbed workpiece；
When the work functions of visual sensor are measurement, measured object is measurement object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810766927.4A CN108871194B (en) | 2018-07-13 | 2018-07-13 | Visual sensor work functions quick recovery method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810766927.4A CN108871194B (en) | 2018-07-13 | 2018-07-13 | Visual sensor work functions quick recovery method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108871194A CN108871194A (en) | 2018-11-23 |
| CN108871194B true CN108871194B (en) | 2019-05-24 |
Family
ID=64301396
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810766927.4A Active CN108871194B (en) | 2018-07-13 | 2018-07-13 | Visual sensor work functions quick recovery method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108871194B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110906863B (en) * | 2019-10-30 | 2022-01-28 | 成都绝影智能科技有限公司 | Hand-eye calibration system and calibration method for line-structured light sensor |
| CN111768383A (en) * | 2020-06-29 | 2020-10-13 | 易思维（杭州）科技有限公司 | Three-dimensional target and method for recovering working function of visual sensor by using same |
| CN112793983B (en) * | 2020-12-30 | 2022-04-19 | 易思维（杭州）科技有限公司 | Automatic loading method suitable for clamping groove type material rack |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102062576B (en) * | 2010-11-12 | 2012-11-21 | 浙江大学 | Device for automatically marking additional external axis robot based on laser tracking measurement and method thereof |
| CN107256567B (en) * | 2017-01-22 | 2020-08-07 | 梅卡曼德（北京）机器人科技有限公司 | Automatic calibration device and calibration method for hand-eye camera of industrial robot |
-
2018
- 2018-07-13 CN CN201810766927.4A patent/CN108871194B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108871194A (en) | 2018-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108871194B (en) | Visual sensor work functions quick recovery method | |
| CN109690623B (en) | System and method for recognizing pose of camera in scene | |
| CN106514651B (en) | Measuring device and calibration method | |
| US8244402B2 (en) | Visual perception system and method for a humanoid robot | |
| JP4191080B2 (en) | Measuring device | |
| CN105303560B (en) | Robotic laser scanning type weld seam tracking system calibrating method | |
| CN109693018A (en) | Autonomous mobile robot welding seam traking system and tracking | |
| CN109848951A (en) | Automatic processing equipment and method for large workpiece | |
| JP2004508954A (en) | Positioning device and system | |
| JP2007523334A (en) | Defect position identification method and marking system | |
| CN110017769A (en) | Part detection method and system based on industrial robot | |
| CN113510708B (en) | Contact industrial robot automatic calibration system based on binocular vision | |
| CN110171009A (en) | A kind of robot handheld teaching apparatus based on stereoscopic vision | |
| US20220230348A1 (en) | Method and apparatus for determining a three-dimensional position and pose of a fiducial marker | |
| WO2018223038A1 (en) | Augmented reality application for manufacturing | |
| CN112119188A (en) | Method for controlling a set of one or more intervention tools mounted on a railway intervention vehicle | |
| Ng et al. | Intuitive robot tool path teaching using laser and camera in augmented reality environment | |
| Acuna et al. | Dynamic Markers: UAV landing proof of concept | |
| CN109760107A (en) | A kind of robot localization Accuracy Assessment based on monocular vision | |
| CN110370287B (en) | Subway train inspection robot path planning system and method based on visual guidance | |
| JP7502003B2 (en) | Apparatus and method for acquiring deviation of moving trajectory of moving machine | |
| CN113781558A (en) | Robot vision locating method with decoupled posture and position | |
| CN104075710B (en) | A kind of motor-driven Extended target based on Trajectory Prediction axial attitude real-time estimation method | |
| KR20030026497A (en) | Self-localization apparatus and method of mobile robot | |
| CN112665453A (en) | Target-shooting robot countermeasure system based on binocular recognition |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee after: Yi Si Si (Hangzhou) Technology Co.,Ltd. Address before: Room 495, building 3, 1197 Bin'an Road, Binjiang District, Hangzhou City, Zhejiang Province 310051 Patentee before: ISVISION (HANGZHOU) TECHNOLOGY Co.,Ltd. |