CN108190418A - Material loading platform and workpiece feeding method - Google Patents
Material loading platform and workpiece feeding method Download PDFInfo
- Publication number
- CN108190418A CN108190418A CN201711490216.0A CN201711490216A CN108190418A CN 108190418 A CN108190418 A CN 108190418A CN 201711490216 A CN201711490216 A CN 201711490216A CN 108190418 A CN108190418 A CN 108190418A
- Authority
- CN
- China
- Prior art keywords
- workpiece
- feeding
- rendering
- treat
- posture
- 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
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
- B65G47/74—Feeding, transfer, or discharging devices of particular kinds or types
- B65G47/90—Devices for picking-up and depositing articles or materials
Abstract
The invention discloses a kind of material loading platform and workpiece feeding method, including:Rack upper conveyor is set to, is used for transmission and treats feeding workpiece;The manipulator of the side of conveying device is set to, for capturing the workpiece in conveying device;The binocular camera of the side of conveying device is set to, the 3D rendering pair of feeding workpiece left-right format and the azimuth information of 3D rendering pair are treated in the conveying device in front of collection machinery hand;Visual analysis device is treated feeding workpiece for the 3D rendering pair according to left-right format and the azimuth information of 3D rendering pair and is modeled, determines the type of workpiece and existing posture;Controller, for the type according to workpiece and existing posture, control machinery hand will treat feeding workpiece transfer to corresponding operating area, and workpiece will be adjusted to preset posture.The present invention can analyze the type and posture of workpiece, control machinery arm transfer workpiece and the posture for adjusting workpiece in real time according to workpiece image, so as to improve the efficiency of workpiece feeding.
Description
Technical field
The present invention relates to a kind of material loading platform and charging methods, and in particular to a kind of material loading platform based on binocular camera
And workpiece feeding method.
Background technology
In the prior art, choosing or feeding are plucked or using manual sorting or for every for the workpiece of different size
The workpiece of a specification designs a set of dedicated mold, of high cost in this way, and efficiency is low, and compatibility is also poor.
Invention content
To solve the deficiencies in the prior art, the purpose of the present invention is to provide a kind of material loading platform and workpiece feeding method,
The type and posture of workpiece can be analyzed in real time according to workpiece image, control machinery arm is by workpiece transfer to corresponding operation area
Domain, and workpiece is adjusted to preset posture, improve workpiece feeding efficiency.
In order to realize above-mentioned target, the present invention adopts the following technical scheme that:A kind of material loading platform, which is characterized in that packet
Including rack, conveying device, manipulator, binocular camera, visual analysis device and controller, wherein:
Conveying device is set in rack, is used for transmission and is treated feeding workpiece;
Manipulator is set to the side of conveying device, for capturing the workpiece in conveying device;
Binocular camera is set to the side of conveying device, including left camera and right camera, for collection machinery hand
The 3D rendering pair of feeding workpiece left-right format and the azimuth information of 3D rendering pair are treated in the conveying device in front, and is sent to vision
Analytical equipment;
Visual analysis device, for the 3D rendering pair according to left-right format and the azimuth information of 3D rendering pair to conveying device
On treat that feeding workpiece is modeled, determine to treat the type of feeding workpiece and existing posture;
Controller, for according to the type of feeding workpiece and existing posture is treated, control machinery hand will to treat feeding workpiece transfer
To corresponding operating area, and it will treat that feeding workpiece is adjusted to preset posture.
Further, the material loading platform further includes storage device, and storage device is used to store the 3D of different type workpiece
Model and the corresponding preset posture of different type workpiece and operating area.
Further, the visual analysis device includes:Depth image generation module treats feeding workpiece or so for basis
The 3D rendering pair of form and the azimuth information generation depth image of 3D rendering pair;
3D modeling module, for rebuilding the 3D models of workpiece according to the depth image;
Characteristic point computing module, for the 3D rendering pair of workpiece left-right format and 3D models to be carried out characteristic point calculating and side
Edge detects;
Concatenation module, for by the 3D rendering repeatedly obtained to the multi-faceted 3D models of generation according to characteristic point and side
Position information, which is weighted, is spliced to form split-join model.
Further, the visual analysis device further includes workpiece type and posture analysis module, for according to splicing mould
Type determines to treat the type of feeding workpiece and according to the 3D rendering of the left-right format repeatedly obtained to determining to treat that feeding workpiece shows
There is posture.
A kind of workpiece feeding method, which is characterized in that the method is realized by material loading platform, is included the following steps:
Step 1, binocular camera obtain the 3D rendering that feeding workpiece left-right format is treated in the conveying device in front of manipulator
Information, and 3D rendering information is sent to visual analysis device;
Step 2, visual analysis device treats the split-join model of feeding workpiece according to the generation of 3D rendering information, and determines to treat
Expect the type of workpiece and existing posture, the type for treating feeding workpiece and existing attitude information are sent to controller;
Step 3, controller will treat feeding workpiece transfer to corresponding work according to the Type Control manipulator for treating feeding workpiece
Industry area, while will treat that feeding workpiece is adjusted to preset posture.
Further, treat that the 3D rendering information of feeding workpiece left-right format includes treating feeding workpiece or so described in step 1
The azimuth information of the 3D rendering pair of form and the 3D rendering pair.
Further, visual analysis device described in step 2 treats the splicing mould of feeding workpiece according to the generation of 3D rendering information
The step of type, includes:
By the 3D rendering of the left-right format to generating depth image;
The 3D models of workpiece are rebuild according to the depth image;
3D rendering pair and the 3D models to the left-right format carry out characteristic point calculating and edge detection;
By the 3D rendering repeatedly obtained to the multi-faceted 3D models of generation according to the characteristic point and the azimuth information into
Row weighting is spliced to form split-join model.
Further, it determines to treat that the type of feeding workpiece and the method for existing posture are described in step 2:
Visual analysis device is by the different type workpiece for treating to prestore in feeding workpiece split-join model and storage device of generation
3D models be compared, determine to treat the type of feeding workpiece;
Visual analysis device determines to treat feeding workpiece according to the 3D rendering pair for treating feeding workpiece left-right format repeatedly obtained
Existing posture.
Further, controller described in step 3 will treat feeding workpiece according to the Type Control manipulator for treating feeding workpiece
The method for being transferred to corresponding operation area is:Controller transfers pair to prestore in storage device according to the type for treating feeding workpiece
Operating area is answered, control machinery hand will treat feeding workpiece transfer to the operating area.
Further, controller control machinery hand described in step 3 will treat that feeding workpiece is adjusted to the method for preset posture
For:Controller transfers corresponding preset posture information according to the type for treating feeding workpiece from storage device, will treat feeding workpiece
Existing posture and the preset posture as input, using neural network model and genetic algorithm, export workpiece from existing
To the regulating step of preset posture, manipulator adjusts workpiece to preset posture according to regulating step pose adjustment.
The invention has the beneficial effects that:
Material loading platform proposed by the present invention using the left-right format 3D rendering of binocular camera acquisition workpiece, and is built in real time
The split-join model of vertical workpiece, so as to fulfill quick identification workpiece type and the purpose of posture, the platform structure is simple, and identification is accurate
Property it is high, and using artificial neural network and genetic algorithms, can quickly export the step of manipulator adjusts workpiece posture, significantly improve
Response speed, and then improve the efficiency of workpiece feeding.
Description of the drawings
Fig. 1 is the structure diagram of the material loading platform of one embodiment of the invention;
Fig. 2 is the schematic diagram of the visual analysis device of one embodiment of the invention;
Fig. 3 is the flow diagram of the workpiece feeding method of one embodiment of the invention.
Specific embodiment
Make specific introduce to the present invention below in conjunction with the drawings and specific embodiments.
With reference to shown in Fig. 1, a kind of material loading platform of the present invention, including rack, conveying device 10, manipulator 20, binocular camera shooting
First 30, visual analysis device 40 and controller 50.Wherein:
Conveying device 10 is set in rack, is used for transmission and is treated feeding workpiece 60.Conveying device 10 can be nowadays industrial
Common assembly line or other conveyer belt devices in production.
Manipulator 20 is set to the side of conveying device 10, for capturing the workpiece 60 in conveying device 10.Manipulator 20
Grabbing workpiece can be adsorbed with vacuum cup, or gripper grabbing workpiece, and after 20 grabbing workpiece 60 of manipulator,
Workpiece 60 can be freely rotated in space, so as to fulfill the purpose of adjustment 60 posture of workpiece.
Binocular camera 30 is set to the side of conveying device 10, including left camera and right camera, for harvester
The 3D rendering pair of 60 left-right format of feeding workpiece and the azimuth information of 3D rendering pair are treated in the conveying device 10 in 20 front of tool hand, and
Above- mentioned information is sent to visual analysis device 40.Can multiple binocular cameras 30 be set in the side of conveying device 10, just
In obtaining about treating 60 more complete image information of feeding workpiece.Binocular camera 30 can be based on double visible image capturings
Head or visible image capturing head and infrared laser projectoscope.Double visible image capturing head rangings utilize principle of parallax, and processing is different
The two images to Same Scene obtained under visual angle, so as to recover the three-dimensional geometric information of object, and measure space length.
Visual analysis device 40 fills conveying for the 3D rendering pair according to left-right format and the azimuth information of 3D rendering pair
It puts and treats that feeding workpiece 60 is modeled, and determine to treat the type of feeding workpiece 60 and existing posture on 10.
Controller 50, for according to the type of feeding workpiece 60 and existing posture is treated, control machinery hand 20 will to treat feeding work
Part 60 is transferred to corresponding operating area, and will treat that feeding workpiece 60 is adjusted to preset posture.
In addition, the material loading platform can also include storage device 70, storage device 70 is used to store different type workpiece
3D models and the corresponding preset posture of different type workpiece and operating area.
In one embodiment of the invention, with reference to shown in Fig. 2, the visual analysis device 40 is according to the 3D of left-right format
The azimuth information of image pair and 3D rendering pair is established the 3D models for treating feeding workpiece, is specifically included with lower module:
Depth image generation module 41 treats the 3D rendering pair of feeding workpiece left-right format and the side of 3D rendering pair for basis
Position information generation depth image.
3D modeling module 42, for rebuilding the 3D models of workpiece according to the depth image.
Characteristic point computing module 43, for by the 3D rendering pair of workpiece left-right format and 3D models carry out characteristic point calculate and
Edge detection.
Concatenation module 44, for by the 3D rendering repeatedly obtained to the multi-faceted 3D models of generation according to characteristic point and
Azimuth information, which is weighted, is spliced to form split-join model.
In addition, visual analysis device is additionally operable to the type for determining to treat feeding workpiece and existing posture, the function is by workpieces
Type and posture analysis module are realized.The workpiece type and posture analysis module determine to treat feeding workpiece according to split-join model
Type and according to the 3D rendering of the left-right format repeatedly obtained to determining to treat the existing posture of feeding workpiece.
With reference to shown in Fig. 3, the invention also provides a kind of workpiece feeding method, the method is based on binocular by aforementioned
What the material loading platform of camera was realized, specifically include following steps:
S10, binocular camera obtain the 3D rendering letter that feeding workpiece left-right format is treated in the conveying device in front of manipulator
Breath, and 3D rendering information is sent to visual analysis device.The 3D rendering information for treating feeding workpiece left-right format includes treating
The 3D rendering pair of feeding workpiece left-right format and the azimuth information of the 3D rendering pair.When conveying device will treat that feeding workpiece transmits
In front of to manipulator during certain distance, the left-right format 3D rendering pair of binocular camera continuous several times acquisition workpiece and acquisition 3D
The azimuth information of image pair.
S20, visual analysis device treats the split-join model of feeding workpiece according to the generation of 3D rendering information, and determines to treat feeding work
The type for treating feeding workpiece and existing attitude information are sent to controller by the type of part and existing posture.
Wherein, the split-join model of feeding workpiece is treated in generation, is included the following steps:
By the 3D rendering of the left-right format to generating depth image.Depth image generation module obtains the 3D of left-right format
Image pair, the depth information that the left-right format 3D rendering pair is obtained using a series of algorithms such as binocular measure and matchings form depth
Degree figure is 3D depth images.Wherein, the depth of field refer to can to obtain before camera lens or other imagers clear image into
As the subject longitudinal separation range measured, after the completion of focusing, can be formed clearly in the range before and after focus
Picture, this distance range one in front and one in back is the depth of field.
The 3D models of workpiece are rebuild according to the depth image.Depth image simulates human eye to the near big remote of real space
Visual experience small, that nearby clear distant place obscures.In order to restore the parallax of image, it is necessary to carry out Surface interpolating reconstruction, utilize scape
Deep image carries out data reconstruction and establishes the 3D model images for completing workpiece.
3D rendering pair and the 3D models to the left-right format carry out characteristic point calculating and edge detection, characteristic point
With the point chosen in edge 3D models are formed as vertex, then according to certain algorithm.For example, it can most represent different type workpiece
Such position is used characteristic point and edge by certain positions of feature, the profile point of characteristic point and workpiece including protruding parts
Point composition, you can the model as identification object.
By the 3D rendering repeatedly obtained to the multi-faceted 3D models of generation according to the characteristic point and the azimuth information into
Row weighting is spliced to form split-join model.Binocular camera obtains the 3D rendering of the left-right format of plurality of workpieces, obtains multi-faceted
The 3D rendering pair of left-right format, to obtain more completely modeling object information, and then by concatenation module, for what is repeatedly generated
3D models first carry out Feature Points Matching, and the characteristic point after matching is weighted splicing according to orientation, establishes as same point
More true 3D models.
The method of the type for determining to treat feeding workpiece and existing posture is:
Visual analysis device is by the different type workpiece for treating to prestore in feeding workpiece split-join model and storage device of generation
3D models be compared, determine to treat the type of feeding workpiece.
Visual analysis device determines to treat feeding workpiece according to the 3D rendering pair for treating feeding workpiece left-right format repeatedly obtained
Existing posture.
S30, controller will treat feeding workpiece transfer to corresponding operation according to the Type Control manipulator for treating feeding workpiece
Area, while will treat that feeding workpiece is adjusted to preset posture.
Specifically, controller is transferred the correspondence operating area to prestore in storage device, is controlled according to the type for treating feeding workpiece
Manipulator processed will treat feeding workpiece transfer to the operating area.
To treat that feeding workpiece is adjusted to the method for preset posture is:Controller is filled according to the type for treating feeding workpiece from storage
Corresponding preset posture information is transferred in putting, using the existing posture for treating feeding workpiece and the preset posture as inputting, is applied
Neural network model and genetic algorithm export the regulating step from existing pose adjustment to preset posture, manipulator root by workpiece
Workpiece is adjusted to preset posture according to regulating step.
The basic principles, main features and advantages of the invention have been shown and described above.The technical staff of the industry should
Understand, the invention is not limited in any way above-described embodiment, all to be obtained by the way of equivalent substitution or equivalent transformation
Technical solution is all fallen in protection scope of the present invention.
Claims (10)
1. a kind of material loading platform, which is characterized in that including rack, conveying device, manipulator, binocular camera, visual analysis dress
It puts and controller, wherein:
Conveying device is set in rack, is used for transmission and is treated feeding workpiece;
Manipulator is set to the side of conveying device, for capturing the workpiece in conveying device;
Binocular camera is set to the side of conveying device, including left camera and right camera, in front of collection machinery hand
Conveying device on treat the 3D rendering pair of feeding workpiece left-right format and the azimuth information of 3D rendering pair, and be sent to visual analysis
Device;Visual analysis device, for the 3D rendering pair according to left-right format and the azimuth information of 3D rendering pair to conveying device
Treat that feeding workpiece is modeled, determine to treat the type of feeding workpiece and existing posture;
Controller, for according to treating the type of feeding workpiece and existing posture, control machinery hand will treat feeding workpiece transfer to right
The operating area answered, and will treat that feeding workpiece is adjusted to preset posture.
2. material loading platform according to claim 1, which is characterized in that the material loading platform further includes storage device, storage
Device is used to store the 3D models of different type workpiece and the corresponding preset posture of different type workpiece and operating area.
3. material loading platform according to claim 1, which is characterized in that the visual analysis device includes:Depth image is given birth to
Into module, for generating depth image according to the 3D rendering pair and the azimuth information of 3D rendering pair for the treatment of feeding workpiece left-right format;
3D modeling module, for rebuilding the 3D models of workpiece according to the depth image;
Characteristic point computing module, for the 3D rendering pair of workpiece left-right format and 3D models to be carried out characteristic point calculating and edge inspection
It surveys;Concatenation module, for the 3D rendering repeatedly obtained to believe the multi-faceted 3D models of generation according to characteristic point and orientation
Breath, which is weighted, is spliced to form split-join model.
4. material loading platform according to claim 3, which is characterized in that the visual analysis device further include workpiece type and
Posture analysis module, for being determined to treat the type of feeding workpiece and according to the left-right format repeatedly obtained according to split-join model
3D rendering to determining to treat the existing posture of feeding workpiece.
5. the workpiece feeding method of material loading platform described in claim 1, which is characterized in that include the following steps:
Step 1, binocular camera obtain the 3D rendering letter that feeding workpiece left-right format is treated in the conveying device in front of manipulator
Breath, and 3D rendering information is sent to visual analysis device;
Step 2, visual analysis device treats the split-join model of feeding workpiece according to the generation of 3D rendering information, and determines to treat feeding work
The type for treating feeding workpiece and existing attitude information are sent to controller by the type of part and existing posture;
Step 3, controller will treat feeding workpiece transfer to corresponding operation according to the Type Control manipulator for treating feeding workpiece
Area, while will treat that feeding workpiece is adjusted to preset posture.
6. workpiece feeding method according to claim 5, which is characterized in that feeding workpiece or so lattice are treated described in step 1
The 3D rendering information of formula includes treating the 3D rendering pair of feeding workpiece left-right format and the azimuth information of the 3D rendering pair.
7. workpiece feeding method according to claim 6, which is characterized in that visual analysis device described in step 2 according to
The step of split-join model of feeding workpiece is treated in the generation of 3D rendering information includes:
By the 3D rendering of the left-right format to generating depth image;
The 3D models of workpiece are rebuild according to the depth image;
3D rendering pair and the 3D models to the left-right format carry out characteristic point calculating and edge detection;
The 3D rendering repeatedly obtained adds the multi-faceted 3D models of generation according to the characteristic point and the azimuth information
Power is spliced to form split-join model.
8. workpiece feeding method according to claim 7, which is characterized in that determine to treat feeding workpiece described in step 2
The method of type and existing posture is:
Visual analysis device is by the 3D of different type workpiece for treating to prestore in feeding workpiece split-join model and storage device of generation
Model is compared, and determines to treat the type of feeding workpiece;
Visual analysis device determines to treat showing for feeding workpiece according to the 3D rendering pair for treating feeding workpiece left-right format repeatedly obtained
There is posture.
9. workpiece feeding method according to claim 8, which is characterized in that controller described in step 3 is according to treating feeding
The method for treating feeding workpiece transfer to corresponding operation area is by the Type Control manipulator of workpiece:Controller is according to treating feeding work
The type of part, transfers the correspondence operating area to prestore in storage device, and control machinery hand will treat feeding workpiece transfer to the work
Industry region.
10. workpiece feeding method according to claim 8, which is characterized in that controller control machinery described in step 3
Hand will treat that feeding workpiece is adjusted to the method for preset posture:Controller is adjusted according to the type for treating feeding workpiece from storage device
Corresponding preset posture information is taken, using the existing posture for treating feeding workpiece and the preset posture as inputting, using nerve net
Network model and genetic algorithm export the regulating step from existing pose adjustment to preset posture by workpiece, and manipulator is according to adjusting
Step adjusts workpiece to preset posture.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711490216.0A CN108190418A (en) | 2017-12-29 | 2017-12-29 | Material loading platform and workpiece feeding method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711490216.0A CN108190418A (en) | 2017-12-29 | 2017-12-29 | Material loading platform and workpiece feeding method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108190418A true CN108190418A (en) | 2018-06-22 |
Family
ID=62587184
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711490216.0A Pending CN108190418A (en) | 2017-12-29 | 2017-12-29 | Material loading platform and workpiece feeding method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108190418A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111250409A (en) * | 2020-01-19 | 2020-06-09 | 上海发那科机器人有限公司 | Automatic sorting and feeding system for robot rubber plugs and working method of automatic sorting and feeding system |
CN114408532A (en) * | 2022-02-25 | 2022-04-29 | 宝钢湛江钢铁有限公司 | Method, device and system for adjusting code bits of impact sample blank |
CN115229770A (en) * | 2022-09-23 | 2022-10-25 | 佛山隆深机器人有限公司 | Robot vision device and control method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2576005A1 (en) * | 1985-01-15 | 1986-07-18 | Realisa Indles Et | Automatic method and device for depalletising |
CN1834582A (en) * | 2005-03-15 | 2006-09-20 | 欧姆龙株式会社 | Image processing method, three-dimensional position measuring method and image processing apparatus |
CN103934211A (en) * | 2014-04-30 | 2014-07-23 | 重庆环视科技有限公司 | Stereoscopic vision-based three-dimensional product size sorting system |
CN104599317A (en) * | 2014-12-18 | 2015-05-06 | 深圳市亿思达科技集团有限公司 | Mobile terminal and method for achieving 3D (three-dimensional) scanning modeling function |
CN106733687A (en) * | 2016-12-22 | 2017-05-31 | 河北省自动化研究所 | A kind of precise part sorting equipment |
CN106969706A (en) * | 2017-04-02 | 2017-07-21 | 聊城大学 | Workpiece sensing and three-dimension measuring system and detection method based on binocular stereo vision |
-
2017
- 2017-12-29 CN CN201711490216.0A patent/CN108190418A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2576005A1 (en) * | 1985-01-15 | 1986-07-18 | Realisa Indles Et | Automatic method and device for depalletising |
CN1834582A (en) * | 2005-03-15 | 2006-09-20 | 欧姆龙株式会社 | Image processing method, three-dimensional position measuring method and image processing apparatus |
CN103934211A (en) * | 2014-04-30 | 2014-07-23 | 重庆环视科技有限公司 | Stereoscopic vision-based three-dimensional product size sorting system |
CN104599317A (en) * | 2014-12-18 | 2015-05-06 | 深圳市亿思达科技集团有限公司 | Mobile terminal and method for achieving 3D (three-dimensional) scanning modeling function |
CN106733687A (en) * | 2016-12-22 | 2017-05-31 | 河北省自动化研究所 | A kind of precise part sorting equipment |
CN106969706A (en) * | 2017-04-02 | 2017-07-21 | 聊城大学 | Workpiece sensing and three-dimension measuring system and detection method based on binocular stereo vision |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111250409A (en) * | 2020-01-19 | 2020-06-09 | 上海发那科机器人有限公司 | Automatic sorting and feeding system for robot rubber plugs and working method of automatic sorting and feeding system |
CN111250409B (en) * | 2020-01-19 | 2021-10-01 | 上海发那科机器人有限公司 | Automatic sorting and feeding system for robot rubber plugs and working method of automatic sorting and feeding system |
CN114408532A (en) * | 2022-02-25 | 2022-04-29 | 宝钢湛江钢铁有限公司 | Method, device and system for adjusting code bits of impact sample blank |
CN115229770A (en) * | 2022-09-23 | 2022-10-25 | 佛山隆深机器人有限公司 | Robot vision device and control method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ling et al. | Dual-arm cooperation and implementing for robotic harvesting tomato using binocular vision | |
US11304374B2 (en) | Selective automated blossom thinning | |
CN107186708B (en) | Hand-eye servo robot grabbing system and method based on deep learning image segmentation technology | |
CN113524194B (en) | Target grabbing method of robot vision grabbing system based on multi-mode feature deep learning | |
CN109702741B (en) | Mechanical arm vision grasping system and method based on self-supervision learning neural network | |
CN105137973B (en) | A kind of intelligent robot under man-machine collaboration scene hides mankind's method | |
CN111151463B (en) | Mechanical arm sorting and grabbing system and method based on 3D vision | |
CN110509281A (en) | The apparatus and method of pose identification and crawl based on binocular vision | |
Zou et al. | Fault-tolerant design of a limited universal fruit-picking end-effector based on vision-positioning error | |
CN110751691B (en) | Automatic pipe fitting grabbing method based on binocular vision | |
CN108190418A (en) | Material loading platform and workpiece feeding method | |
CN107671008A (en) | A kind of part stream waterline automatic sorting boxing apparatus of view-based access control model | |
DE102015101710A1 (en) | A method of calibrating a moveable gripping member using a remote digital camera | |
CN112862878B (en) | Mechanical arm blank repairing method based on 3D vision | |
CN106003036A (en) | Object grabbing and placing system based on binocular vision guidance | |
CN112775959A (en) | Method and system for determining grabbing pose of manipulator and storage medium | |
US20160184998A1 (en) | Robot identification system | |
CN111998862B (en) | BNN-based dense binocular SLAM method | |
Long et al. | Potato volume measurement based on RGB-D camera | |
CN107030693A (en) | A kind of hot line robot method for tracking target based on binocular vision | |
CN107300100A (en) | A kind of tandem type mechanical arm vision guide approach method of Online CA D model-drivens | |
CN112070782A (en) | Method and device for identifying scene contour, computer readable medium and electronic equipment | |
CN107067018A (en) | A kind of hot line robot bolt recognition methods based on random Hough transformation and SVM | |
CN110428464A (en) | Multi-class out-of-order workpiece robot based on deep learning grabs position and orientation estimation method | |
CN107610086A (en) | Industrial parallel robot rapid visual detection algorithm based on bionic compound eye structure |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 215000 No. 38 North Guandu Road, Yuexi Street, Wuzhong District, Suzhou City, Jiangsu Province Applicant after: SUZHOU DCCK MEASUREMENT AND CONTROL TECHNOLOGY CO., LTD. Address before: 215000 5th Floor, Block B3, Jinqiao Auto Parts Industrial Park, 1258 Jinfeng South Road, Wuzhong District, Suzhou City, Jiangsu Province Applicant before: SUZHOU DCCK MEASUREMENT AND CONTROL TECHNOLOGY CO., LTD. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180622 |