CN104626169B - Robot part grabbing method based on vision and mechanical comprehensive positioning - Google Patents
Robot part grabbing method based on vision and mechanical comprehensive positioning Download PDFInfo
- Publication number
- CN104626169B CN104626169B CN201410817853.4A CN201410817853A CN104626169B CN 104626169 B CN104626169 B CN 104626169B CN 201410817853 A CN201410817853 A CN 201410817853A CN 104626169 B CN104626169 B CN 104626169B
- Authority
- CN
- China
- Prior art keywords
- robot
- processing module
- captured
- coordinate system
- image information
- 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
Abstract
The invention relates to industrial automation control, and provides a novel robot part grabbing method based on vision and mechanical comprehensive positioning. The robot part grabbing method aims at solving the problems that in current industrial control, when a robot grabs parts in a traditional mode, it is required that the placement positions and the placement angles of the parts must be fixed, and different positioning tool devices are required for the different-size parts in different shapes. The method specifically includes the following steps: 1, a vision system of a robot collects digital image information of a to-be-grabbed part and transmits the digital image information to a processing module; 2, the processing module carries out comparing matching on the received digital image information with a pre-stored image matching model of the to-be-grabbed part, and the rotating angle of the to-be-grabbed part and the coordinates of the center point of the part in a world coordinate system are obtained; 3, the processing module adjusts grabbing claws of the robot according to the rotating angle and the coordinates of the center point of the part in the world coordinate system to grab the to-be-grabbed part. The novel robot part grabbing method is suitable for the robot for industrial automation.
Description
Technical field
The present invention relates to industrial automatic control, the robot of more particularly to a kind of view-based access control model and mechanical integrated positioning is grabbed
Take part method.
Background technology
At present, transfer robot is widely used in industrial every field, and the crawl of part is that robot is carried in engineering
An important step.Working method of traditional robot using teaching playback, by teaching planning robot's moving line
With action, the content of teaching is then reproduced.When part is captured using traditional approach require that the putting position of part and angle are necessary
Fixed, the part of different sizes and shapes needs different positioning tool equipment, and high cost, efficiency are low, automaticity is low and soft
Property is low.
The content of the invention
For capturing the deficiency existing for part using conventional machines people, the present invention proposes a kind of view-based access control model with machinery
Method that the robot of comprehensive positioning captures part, the method are comprised the following steps that:
A. the digital image information of robotic vision system acquisition part to be captured it is transferred to processing module;
B. the digital image information of reception and the images match model of the part to be captured for prestoring are carried out right by processing module
Than matching, the coordinate of the anglec of rotation and Central of the parts point of part to be captured in world coordinate system is obtained;
C. Coordinate Adjusting robot of the processing module according to the anglec of rotation and Central of the parts point in world coordinate system
Cleft hand is treated crawl part and is captured.
Specifically, step B obtains the anglec of rotation of part to be captured and comprises the steps:
B1. processing module carries out pretreatment to digital image information, obtains the edge contour of part to be captured;
B2. it is calculated according to the edge contour of the images match model and the part to be captured of part to be captured and waits to grab
Take the anglec of rotation of part.
Specifically, the concrete grammar that step B obtains coordinate of the Central of the parts point in world coordinate system is:
B3. the most parcel rectangle of part is calculated by the edge contour, and the central point for calculating rectangle is sat in image
XY coordinates in mark system;
B4. the XY coordinates according to the central point in image coordinate system, by camera calibration in world coordinate system, adjust
The plan-position of mechanical contact on whole robot cleft hand so as in the surface of Central of the parts;
B5. the height for adjusting mechanical contact makes which contact part, when mechanical contact touches part, on mechanical contact
Sensor produces trigger and trigger is transferred to processing module;
B6. processing module records the height declined by mechanical contact according to trigger, and according to the first of mechanical contact
Beginning position, calculates Z axis coordinate of the part in world coordinate system.
A kind of preferred scheme is that the visual system is photographic head.
The invention has the beneficial effects as follows:Compared with traditional approach, captured by the way of vision with mechanical integrated positioning
Part, without the need for accurate machinery pre-determined bit, reduces the positioning tool equipment of different parts, reduces hardware cost, improve equipment
Automaticity and degree of flexibility.Replace technical grade CCD to realize the two-dimensional localization of part using common camera, reduce hardware
Cost, improves the automaticity and degree of flexibility of equipment.Mechanical contact triggering mode is adopted simultaneously, obtains the height letter of part
The three-dimensional localization to realize part is ceased, the amount of calculation of image processing algorithm is reduced, the stability and positioning precision of equipment is improved.
Description of the drawings
The flow chart that Fig. 1 captures the method for part for the view-based access control model of embodiment with the robot of mechanical integrated positioning.
Specific embodiment
Below in conjunction with the accompanying drawings and embodiment is further described to technical scheme, it is noted that implement
Example just for the sake of helping reader to more fully understand the technology design of the present invention, not to limit the guarantor of the claims in the present invention
Shield scope.
Require part when the present invention captures part for robot in existing Industry Control using traditional approach puts position
Put and angle must be fixed, the part of different sizes and shapes needs different positioning tool equipment, and high cost, efficiency are low, automatic
Change low degree, and flexible low problem, there is provided a kind of new view-based access control model and the robot crawl part of mechanical integrated positioning
Method, the method specifically include following steps:
The digital image information of step one, robotic vision system acquisition part to be captured simultaneously is transferred to processing module;
The images match model of step 2, processing module by the digital image information of reception with the part to be captured for prestoring enters
Row contrast matching, obtains the coordinate of the anglec of rotation and Central of the parts point of part to be captured in world coordinate system;
The Coordinate Adjusting machine of step 3, processing module according to the anglec of rotation and Central of the parts point in world coordinate system
Device people's cleft hand is treated crawl part and is captured.
Embodiment
Technical scheme, the view-based access control model of the present invention and the machine of mechanical integrated positioning are illustrated with an example below
The flow chart of the method for people's crawl part is as shown in Figure 1.
1) first according to part to be captured, crawl item number is set, according to the suitable mechanical claw hand of different choice of item number,
And read the standardized element Matching Model matched with the item number.Standardized element Matching Model is to standard zero under off-line state
Part carries out what off-line training was obtained, standardized element model information is carried out storage after reading standby.
2) start photographic head, gather the digital image information of part to be captured, and by the digital picture for collecting by logical
To computer, the computer in this step is usually to be built in robot to letter port transmission, in particular cases, it is also possible to by machine
Device people and computer separate, but now robot must possess communication function.
3) to step 2) in the digital image information for obtaining carry out pretreatment operation, take out the edge contour of part.
4) the most parcel for calculating part by the edge contour of part is rectangle, calculates the center point coordinate of rectangle
(Xp,Yp), matching primitives are carried out using the standard picture template and image of part, obtain anglec of rotation θ of partp。
5) by camera calibration, by step 4) in the part pixel coordinate that obtains switched to the world in robot coordinate system
Coordinate (Xr,Yr,θr)。
6) according to step 5) two-dimensional coordinate (X of part that obtainsr,Yr), adjusting mechanical contact two dimensional surface position first makes
Which is in the surface of Central of the parts point.Then, the height for adjusting mechanical contact is brought into contact with part, when mechanical contact is touched
During part, the sensor in front of contact produces trigger, after controller receives the trigger of mechanical contact, record machinery
The height Z declined by contacth, according to the initial position of mechanical contact, calculate Z axis coordinate Z of the part in world coordinate systemr。
7) coordinate (X according to partr,Yr,Zr,θr), the pose of mechanical claw hand is adjusted, the accurate crawl of part is realized.
Claims (2)
1. the method that the robot of view-based access control model and mechanical integrated positioning captures part, it is characterised in that comprise the steps:
A. the digital image information of robotic vision system acquisition part to be captured it is transferred to processing module;
B. images match model of the processing module by the digital image information of reception with the part to be captured for prestoring carries out contrast
Match somebody with somebody, obtain the coordinate of the anglec of rotation and Central of the parts point of part to be captured in world coordinate system, specifically include step B1 extremely
B6:
B1. processing module carries out pretreatment to digital image information, obtains the edge contour of part to be captured;
B2. it is calculated according to the edge contour of the images match model and the part to be captured of part to be captured and treats crawl zero
The anglec of rotation of part;
B3. the most parcel rectangle of part is calculated by the edge contour, calculates the central point of rectangle in image coordinate system
In XY coordinates;
B4. the XY coordinates according to the central point in image coordinate system, by camera calibration in world coordinate system, adjust machine
The plan-position of mechanical contact on device people's cleft hand so as in the surface of Central of the parts;
B5. the height for adjusting mechanical contact makes which contact part, the sensing when mechanical contact touches part, on mechanical contact
Device produces trigger and trigger is transferred to processing module;
B6. processing module records the height declined by mechanical contact according to trigger, and according to the initial bit of mechanical contact
Put, calculate Z axis coordinate of the part in world coordinate system;
C. Coordinate Adjusting robot cleft hand of the processing module according to the anglec of rotation and Central of the parts point in world coordinate system
Treat crawl part to be captured.
2. the method that the robot of view-based access control model as claimed in claim 1 and mechanical integrated positioning captures part, its feature exist
In the visual system is photographic head.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410817853.4A CN104626169B (en) | 2014-12-24 | 2014-12-24 | Robot part grabbing method based on vision and mechanical comprehensive positioning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410817853.4A CN104626169B (en) | 2014-12-24 | 2014-12-24 | Robot part grabbing method based on vision and mechanical comprehensive positioning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104626169A CN104626169A (en) | 2015-05-20 |
CN104626169B true CN104626169B (en) | 2017-03-22 |
Family
ID=53205633
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410817853.4A Active CN104626169B (en) | 2014-12-24 | 2014-12-24 | Robot part grabbing method based on vision and mechanical comprehensive positioning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104626169B (en) |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105066984B (en) * | 2015-07-16 | 2019-03-12 | 深圳訾岽科技有限公司 | A kind of vision positioning method and system |
CN105345431B (en) * | 2015-11-25 | 2017-07-28 | 四川长虹电器股份有限公司 | Automatism card machine control system based on industrial robot |
CN106671083B (en) * | 2016-12-03 | 2019-03-19 | 安徽松科智能装备有限公司 | A kind of assembly robot system based on Machine Vision Detection |
CN106845354B (en) * | 2016-12-23 | 2020-01-03 | 中国科学院自动化研究所 | Part view library construction method, part positioning and grabbing method and device |
CN107265129A (en) * | 2017-06-02 | 2017-10-20 | 成都福莫斯智能系统集成服务有限公司 | Using the system of image recognition auxiliary robot stacking |
CN107161392B (en) * | 2017-06-16 | 2023-07-07 | 东莞晶苑毛织制衣有限公司 | Automatic detection and grabbing clothes boxing system and clothes boxing method thereof |
CN107671008A (en) * | 2017-11-13 | 2018-02-09 | 中国科学院合肥物质科学研究院 | A kind of part stream waterline automatic sorting boxing apparatus of view-based access control model |
CN108393676B (en) * | 2018-01-25 | 2020-04-07 | 嘉兴微芒科技有限公司 | Model setting method for automatic makeup assembly |
CN108381549B (en) * | 2018-01-26 | 2021-12-14 | 广东三三智能科技有限公司 | Binocular vision guide robot rapid grabbing method and device and storage medium |
CN108297084A (en) * | 2018-03-16 | 2018-07-20 | 五邑大学 | A kind of intelligent conveyor type mechanical arm system based on image recognition |
CN108711173A (en) * | 2018-04-13 | 2018-10-26 | 深圳安博电子有限公司 | Multiple-target identification method and device |
CN108890636A (en) * | 2018-07-06 | 2018-11-27 | 陕西大中科技发展有限公司 | A kind of crawl localization method of industrial robot |
CN108858202B (en) * | 2018-08-16 | 2020-11-10 | 中国科学院自动化研究所 | Control method of part grabbing device based on alignment, approach and grabbing |
CN109926817B (en) * | 2018-12-20 | 2021-05-07 | 南京理工大学 | Machine vision-based automatic transformer assembling method |
CN110039525A (en) * | 2019-05-25 | 2019-07-23 | 塞伯睿机器人技术(长沙)有限公司 | Robot is used in 6S management |
CN110625644B (en) * | 2019-09-19 | 2022-04-08 | 河海大学常州校区 | Workpiece grabbing method based on machine vision |
CN111932490B (en) * | 2020-06-05 | 2023-05-05 | 浙江大学 | Visual system grabbing information extraction method for industrial robot |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101559600A (en) * | 2009-05-07 | 2009-10-21 | 上海交通大学 | Service robot grasp guidance system and method thereof |
CN102120307B (en) * | 2010-12-23 | 2012-07-04 | 中国科学院自动化研究所 | System and method for grinding industrial robot on basis of visual information |
CN102200780A (en) * | 2011-04-21 | 2011-09-28 | 苏州悦控自动化科技有限公司 | Method for realizing 3H charge coupled device (CCD) visual industrial robot |
JP2013010157A (en) * | 2011-06-29 | 2013-01-17 | Seiko Epson Corp | Robot control system, robot system, and marker processing method |
JP2013066963A (en) * | 2011-09-21 | 2013-04-18 | Seiko Epson Corp | Robot control device, and robot system |
CN104058260B (en) * | 2013-09-27 | 2016-07-20 | 沈阳工业大学 | The robot automatic stacking method that view-based access control model processes |
CN103846606B (en) * | 2014-02-17 | 2015-09-02 | 华南理工大学 | Welding track based on machine vision corrects Special testing device and method |
CN103895042A (en) * | 2014-02-28 | 2014-07-02 | 华南理工大学 | Industrial robot workpiece positioning grabbing method and system based on visual guidance |
-
2014
- 2014-12-24 CN CN201410817853.4A patent/CN104626169B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN104626169A (en) | 2015-05-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104626169B (en) | Robot part grabbing method based on vision and mechanical comprehensive positioning | |
CN111452040B (en) | System and method for associating machine vision coordinate space in a pilot assembly environment | |
CN106041937B (en) | A kind of control method of the manipulator crawl control system based on binocular stereo vision | |
CN105729468B (en) | A kind of robotic workstation based on the enhancing of more depth cameras | |
CN107767423B (en) | mechanical arm target positioning and grabbing method based on binocular vision | |
WO2019114339A1 (en) | Method and device for correcting motion of robotic arm | |
CN107263468B (en) | SCARA robot assembly method using digital image processing technology | |
Nerakae et al. | Using machine vision for flexible automatic assembly system | |
CN106044570B (en) | It is a kind of that automatic identification equipment and method are hung using the coil of strip of machine vision | |
CN110751691B (en) | Automatic pipe fitting grabbing method based on binocular vision | |
CN106272424A (en) | A kind of industrial robot grasping means based on monocular camera and three-dimensional force sensor | |
CN107671008A (en) | A kind of part stream waterline automatic sorting boxing apparatus of view-based access control model | |
CN110293559B (en) | Installation method for automatically identifying, positioning and aligning | |
CN105225225B (en) | A kind of leather system for automatic marker making method and apparatus based on machine vision | |
CN107150032A (en) | A kind of workpiece identification based on many image acquisition equipments and sorting equipment and method | |
CN105345431A (en) | Automatic element inserting machine control system based on industrial robot | |
CN113689509A (en) | Binocular vision-based disordered grabbing method and system and storage medium | |
Gratal et al. | Virtual visual servoing for real-time robot pose estimation | |
JP6424432B2 (en) | Control device, robot system, robot and robot control method | |
CN106926241A (en) | A kind of the tow-armed robot assembly method and system of view-based access control model guiding | |
Lin et al. | Vision based object grasping of industrial manipulator | |
CN206643574U (en) | A kind of automatic connector assembly robot system | |
CN104874692A (en) | One-die double-component vision centering control system for automatic punching line | |
JP2015003348A (en) | Robot control system, control device, robot, control method for robot control system and robot control method | |
CN205552536U (en) | Four -axis parallel robot letter sorting system based on machine vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |