CN108890636A - A kind of crawl localization method of industrial robot - Google Patents
A kind of crawl localization method of industrial robot Download PDFInfo
- Publication number
- CN108890636A CN108890636A CN201810734793.8A CN201810734793A CN108890636A CN 108890636 A CN108890636 A CN 108890636A CN 201810734793 A CN201810734793 A CN 201810734793A CN 108890636 A CN108890636 A CN 108890636A
- Authority
- CN
- China
- Prior art keywords
- coordinate system
- image
- industrial robot
- working area
- coordinate
- 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.)
- Pending
Links
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
- B25J9/10—Programme-controlled manipulators characterised by positioning means for manipulator elements
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a kind of crawl localization methods of industrial robot comprising：Plane coordinate system is established, two extreme coordinates in material working area are marked in plane coordinate system；Image Acquisition is carried out to material working area, obtains the first image；Visual coordinate system is established according to the first image, the transition matrix between Calculation Plane coordinate system and visual coordinate system；Image segmentation is carried out to the first image, obtains the material image of each material in material working area；The material image of each material is compared with the material Matching Model prestored and is matched, the edge contour of each material is obtained；According to the edge contour of material, the centre coordinate of each material is obtained by transform matrix calculations；Control industrial robot is successively moved to the centre coordinate of each material since an extreme coordinates, and material is grabbed at each centre coordinate, until industrial robot is moved to another extreme coordinates.The present invention can be positioned for different material, improve stability and positioning accuracy.
Description
Technical field
The present invention relates to Industrial Robot Technology fields, more particularly to a kind of crawl localization method of industrial robot.
Background technique
Robot vision mainly simulates the visual performance of people with computer, is not merely the simple extension of human eye, more
It is important that the part of functions with human brain.Information is extracted from the image of objective things, handled and is understood, most
Eventually for actually detected, measurement and control.The maximum feature of machine vision is that speed is fast, contain much information, function is more.
Industrial robot and vision technique are combined, help industrial robot to be competent at more intelligentized work,
Through a kind of trend for becoming industrial robot application field.The real training combined at present applied to progress robot of school and vision
Equipment is for the important teaching equipment of industrial robot training for industry engineering talent.
Require the placement position of material and angle that must fix when currently, Practical training equipment is using traditional approach crawl material,
The material of different sizes and shapes needs different positioning tool equipment, and there are at high cost, low efficiency, the degree of automation are low, flexible
Low disadvantage.
Summary of the invention
The invention mainly solves the technical problem of providing a kind of crawl localization methods of industrial robot, can be for not
It is positioned with material, improves stability and positioning accuracy.
In order to solve the above technical problems, one technical scheme adopted by the invention is that：A kind of grabbing for industrial robot is provided
Localization method is taken, is included the following steps：Plane coordinate system is established, two of material working area are marked in the plane coordinate system
Extreme coordinates, wherein the material working area is strip；Image Acquisition is carried out to the material working area, obtains the first figure
Picture；Visual coordinate system is established according to the first image, the transition matrix between Calculation Plane coordinate system and visual coordinate system；It is right
The first image carries out image segmentation, obtains the material image of each material in the material working area；By each material
Material image is compared with the material Matching Model prestored and is matched, and obtains the edge contour of each material；According to the material
Edge contour, obtain the centre coordinate of each material by transform matrix calculations；The industrial robot is controlled to hold from one
Point coordinate starts the centre coordinate for being successively moved to each material, and material is grabbed at each centre coordinate, until the work
Industry robot is moved to another extreme coordinates.
Preferably, the edge contour according to the material obtains the center of each material by transform matrix calculations
The step of coordinate, specifically includes：The most parcel rectangle that each material is calculated according to the edge contour of the material, calculates square
Coordinate of the central point of shape in visual coordinate system；According to coordinate of the central point in visual coordinate system, by converting square
Battle array calibration obtains the centre coordinate of each material into plane coordinate system.
The beneficial effects of the invention are as follows：It is in contrast to the prior art, the present invention only needs discharge of materials temporary in material
Area is deposited, without providing the size and shape of material, each material is positioned by the way of vision positioning, is not necessarily to machinery positioning,
Industrial robot is moved and is grabbed according to the positioning of each material, so as to be positioned for different material, is improved
The intelligence and efficiency of industrial robot can be improved in stability and positioning accuracy.
Detailed description of the invention
Fig. 1 is the flow diagram of the crawl localization method of the industrial robot of the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that the described embodiments are merely a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, being the flow diagram of the crawl localization method of the industrial robot of the embodiment of the present invention.This implementation
The crawl localization method of example includes the following steps：
S1：Plane coordinate system is established, two extreme coordinates in material working area are marked in plane coordinate system, wherein object
Material working area is strip.
Wherein, industrial robot is to move in a plane other than clamping material and stacking material at work
, by establishing plane coordinate system, it can be convenient the position coordinates for obtaining industrial robot.Two endpoints in material working area are sat
It is designated as the origin coordinates and end coordinate of the length direction in material working area.Material working area is, for example, a strip groove, material
The length direction along material working area can be placed on to be emitted in strip groove.
S2：Image Acquisition is carried out to material working area, obtains the first image.
S3：Visual coordinate system is established according to the first image, the conversion square between Calculation Plane coordinate system and visual coordinate system
Battle array.
The embodiment of the present invention can use line-of-sight course, with the relationship of 3 computation vision coordinate systems and plane coordinate system,
Think that this 3 points of values under visual coordinate system are：
Value under plane coordinate system is：
Use R1For point as reference, the relationship foundation of visual coordinate system and plane coordinate system is as follows：
It is the transition matrix between plane coordinate system and visual coordinate system.As long as seat of the target under visual coordinate system
Mark is identified, so that it may calculate its coordinate under plane coordinate system.
S4：Image segmentation is carried out to the first image, obtains the material image of each material in material working area.
Wherein, image segmentation is for extracting a part of feature from an image.Different image segmentation sides is used
Method, such as thresholding method, domain division method, edge split plot design etc..Thresholding method is used in the present embodiment, due to material
The feature of image in working area other than material is almost consistent, thus according to the threshold value of material region, it is carried out
Binaryzation, obtained highlighted region are the image segmentation region to be obtained.
S5：The material image of each material is compared with the material Matching Model prestored and is matched, each material is obtained
Edge contour.
Wherein, the material Matching Model prestored is to carry out off-line training to various materials under off-line state to obtain, and is read
Material Matching Model store after taking spare.
S6：According to the edge contour of material, the centre coordinate of each material is obtained by transform matrix calculations.
Wherein, after the edge contour for obtaining material, the coordinate of marginal point is assured that.Here select 4 limit points (+
X ,+Y are maximum, and-X ,-Y are minimum), obtaining this 4 points is：
S1(x1, y1), x1=max (x1, x2, x3, x4…xn)；
S2(x2, y2), y2=max (y1, y2, y3, y4…yn)；
S3(x3, y3), x3=min (x1, x2, x3, x4…xn)；
S4(x4, y4), y4=min (y1, y2, y3, y4…yn)；
The midpoint coordinates of this four points is the centre coordinate of target：
S0(x0, y0)=center [S1, S2, S3, S4]。
S7：Control industrial robot is successively moved to the centre coordinate of each material since an extreme coordinates, and
Material is grabbed at each centre coordinate, until industrial robot is moved to another extreme coordinates.
It wherein, can be from control starting of the industrial robot from material working area after the centre coordinate of each material determines
Coordinate starts to be moved to first centre coordinate, after carrying out corresponding operating after crawl material, then is moved to second centre coordinate,
After carrying out corresponding operating after continuation material, then it is moved to next centre coordinate, until being moved to from the last one centre coordinate
End coordinate.
In the present embodiment, step S6 is specifically included：
The most parcel rectangle that each material is calculated according to the edge contour of material, calculates the central point of rectangle in vision
Coordinate in coordinate system；
According to coordinate of the central point in visual coordinate system, through transition matrix calibration into plane coordinate system, obtain every
The centre coordinate of a material.
By the above-mentioned means, the crawl localization method of the industrial robot of the embodiment of the present invention only needs discharge of materials in object
Expect that working area positions each material without providing the size and shape of material by the way of vision positioning, without mechanical fixed
Position, industrial robot are moved and are grabbed according to the positioning of each material, so as to be positioned for different material, are mentioned
The intelligence and efficiency of industrial robot can be improved in high stability and positioning accuracy.
The above description is only an embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (2)
1. a kind of crawl localization method of industrial robot, which is characterized in that include the following steps：
Plane coordinate system is established, two extreme coordinates in material working area are marked in the plane coordinate system, wherein the object
Material working area is strip；
Image Acquisition is carried out to the material working area, obtains the first image；
Visual coordinate system is established according to the first image, the transition matrix between Calculation Plane coordinate system and visual coordinate system；
Image segmentation is carried out to the first image, obtains the material image of each material in the material working area；
The material image of each material is compared with the material Matching Model prestored and is matched, the edge wheel of each material is obtained
It is wide；
According to the edge contour of the material, the centre coordinate of each material is obtained by transform matrix calculations；
The centre coordinate that the industrial robot is successively moved to each material since an extreme coordinates is controlled, and each
Material is grabbed at centre coordinate, until the industrial robot is moved to another extreme coordinates.
2. crawl localization method according to claim 1, which is characterized in that the edge contour according to the material,
The step of obtaining the centre coordinate of each material by transform matrix calculations specifically includes：
The most parcel rectangle that each material is calculated according to the edge contour of the material, calculates the central point of rectangle in vision
Coordinate in coordinate system；
According to coordinate of the central point in visual coordinate system, through transition matrix calibration into plane coordinate system, obtain every
The centre coordinate of a material.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810734793.8A CN108890636A (en) | 2018-07-06 | 2018-07-06 | A kind of crawl localization method of industrial robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810734793.8A CN108890636A (en) | 2018-07-06 | 2018-07-06 | A kind of crawl localization method of industrial robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108890636A true CN108890636A (en) | 2018-11-27 |
Family
ID=64348476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810734793.8A Pending CN108890636A (en) | 2018-07-06 | 2018-07-06 | A kind of crawl localization method of industrial robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108890636A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109926817A (en) * | 2018-12-20 | 2019-06-25 | 南京理工大学 | Transformer automatic assembly method based on machine vision |
| CN110202560A (en) * | 2019-07-12 | 2019-09-06 | 易思维（杭州）科技有限公司 | A kind of hand and eye calibrating method based on single feature point |
| CN110465944A (en) * | 2019-08-09 | 2019-11-19 | 琦星智能科技股份有限公司 | Calculation method based on the industrial robot coordinate under plane visual |
| CN111380457A (en) * | 2018-12-29 | 2020-07-07 | 上海葩弥智能科技有限公司 | Positioning method and system for material tray |
| CN111421528A (en) * | 2020-03-24 | 2020-07-17 | 广州市轻工职业学校 | Industrial robot's automated control system |
| CN111546335A (en) * | 2020-04-28 | 2020-08-18 | 西安航天精密机电研究所 | Visual positioning method for automatic grabbing of special-shaped catheter robot |
| CN112356057A (en) * | 2020-09-21 | 2021-02-12 | 埃夫特智能装备股份有限公司 | State planning method of matrix sucker based on multiple complex sheet metal parts |
| CN112777346A (en) * | 2020-12-23 | 2021-05-11 | 深圳市旗众智能科技有限公司 | Mobile phone accessory feeding identification method based on industrial camera |
| CN113479640A (en) * | 2021-06-16 | 2021-10-08 | 苏州博杰智能科技有限公司 | Sucker clamp control system and control method based on visual detection technology |
| CN113516720A (en) * | 2021-07-07 | 2021-10-19 | 广东拓斯达科技股份有限公司 | Automatic material loading stacking method and system based on visual positioning |
| CN113847868A (en) * | 2021-08-05 | 2021-12-28 | 乐歌人体工学科技股份有限公司 | Positioning method and system of material bearing device with rectangular support legs |
| CN115816460A (en) * | 2022-12-21 | 2023-03-21 | 苏州科技大学 | Manipulator grabbing method based on deep learning target detection and image segmentation |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5350269A (en) * | 1989-03-27 | 1994-09-27 | Canon Kabushiki Kaisha | Work pick-up apparatus |
| CN103464383A (en) * | 2013-09-27 | 2013-12-25 | 沈阳工业大学 | Industrial robot sorting system and method |
| CN103706571A (en) * | 2013-12-27 | 2014-04-09 | 西安航天精密机电研究所 | Visual positioning sorting method |
| CN104331894A (en) * | 2014-11-19 | 2015-02-04 | 山东省科学院自动化研究所 | Robot unstacking method based on binocular stereoscopic vision |
| CN104626169A (en) * | 2014-12-24 | 2015-05-20 | 四川长虹电器股份有限公司 | Robot part grabbing method based on vision and mechanical comprehensive positioning |
| CN105046271A (en) * | 2015-06-25 | 2015-11-11 | 哈尔滨工业大学 | MELF (Metal Electrode Leadless Face) component positioning and detecting method based on match template |
-
2018
- 2018-07-06 CN CN201810734793.8A patent/CN108890636A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5350269A (en) * | 1989-03-27 | 1994-09-27 | Canon Kabushiki Kaisha | Work pick-up apparatus |
| CN103464383A (en) * | 2013-09-27 | 2013-12-25 | 沈阳工业大学 | Industrial robot sorting system and method |
| CN103706571A (en) * | 2013-12-27 | 2014-04-09 | 西安航天精密机电研究所 | Visual positioning sorting method |
| CN104331894A (en) * | 2014-11-19 | 2015-02-04 | 山东省科学院自动化研究所 | Robot unstacking method based on binocular stereoscopic vision |
| CN104626169A (en) * | 2014-12-24 | 2015-05-20 | 四川长虹电器股份有限公司 | Robot part grabbing method based on vision and mechanical comprehensive positioning |
| CN105046271A (en) * | 2015-06-25 | 2015-11-11 | 哈尔滨工业大学 | MELF (Metal Electrode Leadless Face) component positioning and detecting method based on match template |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109926817A (en) * | 2018-12-20 | 2019-06-25 | 南京理工大学 | Transformer automatic assembly method based on machine vision |
| CN111380457A (en) * | 2018-12-29 | 2020-07-07 | 上海葩弥智能科技有限公司 | Positioning method and system for material tray |
| CN111380457B (en) * | 2018-12-29 | 2024-02-06 | 上海晨兴希姆通电子科技有限公司 | Positioning method and system for material tray |
| CN110202560A (en) * | 2019-07-12 | 2019-09-06 | 易思维（杭州）科技有限公司 | A kind of hand and eye calibrating method based on single feature point |
| CN110465944A (en) * | 2019-08-09 | 2019-11-19 | 琦星智能科技股份有限公司 | Calculation method based on the industrial robot coordinate under plane visual |
| CN110465944B (en) * | 2019-08-09 | 2021-03-16 | 琦星智能科技股份有限公司 | Method for calculating coordinates of industrial robot based on plane vision |
| CN111421528A (en) * | 2020-03-24 | 2020-07-17 | 广州市轻工职业学校 | Industrial robot's automated control system |
| CN111546335A (en) * | 2020-04-28 | 2020-08-18 | 西安航天精密机电研究所 | Visual positioning method for automatic grabbing of special-shaped catheter robot |
| CN111546335B (en) * | 2020-04-28 | 2021-05-14 | 西安航天精密机电研究所 | Visual positioning method for automatic grabbing of special-shaped catheter robot |
| CN112356057B (en) * | 2020-09-21 | 2022-05-31 | 埃夫特智能装备股份有限公司 | State planning method of matrix sucker based on multiple complex sheet metal parts |
| CN112356057A (en) * | 2020-09-21 | 2021-02-12 | 埃夫特智能装备股份有限公司 | State planning method of matrix sucker based on multiple complex sheet metal parts |
| CN112777346A (en) * | 2020-12-23 | 2021-05-11 | 深圳市旗众智能科技有限公司 | Mobile phone accessory feeding identification method based on industrial camera |
| CN113479640A (en) * | 2021-06-16 | 2021-10-08 | 苏州博杰智能科技有限公司 | Sucker clamp control system and control method based on visual detection technology |
| CN113516720A (en) * | 2021-07-07 | 2021-10-19 | 广东拓斯达科技股份有限公司 | Automatic material loading stacking method and system based on visual positioning |
| CN113516720B (en) * | 2021-07-07 | 2024-04-09 | 广东拓斯达科技股份有限公司 | Automatic stacking method and system for material on shelf based on visual positioning |
| CN113847868A (en) * | 2021-08-05 | 2021-12-28 | 乐歌人体工学科技股份有限公司 | Positioning method and system of material bearing device with rectangular support legs |
| CN113847868B (en) * | 2021-08-05 | 2024-04-16 | 乐仓信息科技有限公司 | Positioning method and system for material bearing device with rectangular support legs |
| CN115816460A (en) * | 2022-12-21 | 2023-03-21 | 苏州科技大学 | Manipulator grabbing method based on deep learning target detection and image segmentation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108890636A (en) | A kind of crawl localization method of industrial robot | |
| CN105234943B (en) | A kind of industrial robot teaching device and method of view-based access control model identification | |
| CN107292927B (en) | Binocular vision-based symmetric motion platform pose measurement method | |
| CN110116411B (en) | Robot 3D vision hand-eye calibration method based on spherical target | |
| US9457470B2 (en) | Robot system and method for calibration | |
| CN106462140B (en) | Method for demarcating the tool center point of industrial robot system | |
| CN109702738A (en) | A kind of mechanical arm hand and eye calibrating method and device based on Three-dimension object recognition | |
| CN103632366A (en) | Parameter identification method for elliptical target | |
| CN110570480B (en) | Sketch drawing method of drawing robot, electronic equipment and storage medium | |
| CN110666805A (en) | Industrial robot sorting method based on active vision | |
| CN105217324A (en) | A kind of novel de-stacking method and system | |
| CN104766309A (en) | Plane feature point navigation and positioning method and device | |
| CN106845710A (en) | Mission area automatic division method and system, flight course planning method and system | |
| CN104760812B (en) | Product real-time positioning system and method on conveyer belt based on monocular vision | |
| CN111037561A (en) | Space registration method and device | |
| CN110238820A (en) | Hand and eye calibrating method based on characteristic point | |
| CN108942918A (en) | A kind of solid locating method based on line-structured light | |
| CN110202560A (en) | A kind of hand and eye calibrating method based on single feature point | |
| CN108994832A (en) | A kind of robot eye system and its self-calibrating method based on RGB-D camera | |
| CN106403924B (en) | Robot based on depth camera quickly positions and Attitude estimation method | |
| CN110136211A (en) | A kind of workpiece localization method and system based on active binocular vision technology | |
| CN110555894B (en) | Intelligent robot painting method, electronic equipment and storage medium | |
| CN112958960B (en) | Robot hand-eye calibration device based on optical target | |
| CN110433467A (en) | Picking up table tennis ball robot operation method and equipment based on binocular vision and ant group algorithm | |
| CN110962127B (en) | Auxiliary calibration device for tail end pose of mechanical arm and calibration method thereof |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181127 |