CN108161931A - The workpiece automatic identification of view-based access control model and intelligent grabbing system - Google Patents
The workpiece automatic identification of view-based access control model and intelligent grabbing system Download PDFInfo
- Publication number
- CN108161931A CN108161931A CN201611116892.7A CN201611116892A CN108161931A CN 108161931 A CN108161931 A CN 108161931A CN 201611116892 A CN201611116892 A CN 201611116892A CN 108161931 A CN108161931 A CN 108161931A
- Authority
- CN
- China
- Prior art keywords
- robot
- module
- workpiece
- image
- based access
- 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
- B25J9/02—Programme-controlled manipulators characterised by movement of the arms, e.g. cartesian coordinate type
- B25J9/04—Programme-controlled manipulators characterised by movement of the arms, e.g. cartesian coordinate type by rotating at least one arm, excluding the head movement itself, e.g. cylindrical coordinate type or polar coordinate type
- B25J9/046—Revolute coordinate type
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a kind of workpiece automatic identification of view-based access control model and intelligent grabbing system, which includes：Image capture module, industrial personal computer module and robot module；Wherein, described image acquisition module is connected with the industrial personal computer module；The industrial personal computer module is connected with the robot module.The present invention program provides image coordinate to the transfer algorithm of robot coordinate by establishing the parameterized model of grasping system, the image pre-processing method provided using specific software, secondary development is carried out under designated environment, it realizes target positioning and robot controls two big basic functions, the final crawl that robot is controlled to complete target workpiece.
Description
Technical field
The invention belongs to machine vision positioning fields, are related to a kind of workpiece automatic identification of view-based access control model and intelligent grabbing system
System.
Background technology
Workpiece identification and the important application that crawl is industrial robot on production line, and it is most on production line at present
Industrial robot is to control the robot to perform scheduled instruction action by way of advance teaching or off-line programing, once
Working environment or target object change, and robot cannot adapt to these variations in time, fail so as to cause crawl, therefore,
This working method greatly limits flexibility and the working efficiency of industrial robot.
Machine vision technique has the characteristics that quick and non-contacting, and machine vision technique is introduced industrial robot field,
It the Mission Operations such as captured, carried by vision guide robot, for improving the automatization level of production line, widening machine
The application range of people is all of great significance.
Application publication number discloses one kind for the application for a patent for invention of CN105905560A and " dynamically captures the full-automatic of storage
Control system and its control method ", which realizes a PLC controller and controls more manipulators, and controls simultaneously
Material transportation is moved with material disc, realizes the crawl of dynamic material.But the invention need to use PLC controller, and basis is needed to take pictures
Region operation and control free of discontinuities, required cost is higher, and systematic realizing program is more complicated.
Paper " target identification of binocular stereo vision and positioning, intelligence system journal, 2011,6 (4):303-311, still
Pretty, Ruan Qiuqi, Li little Li " realize target identification and positioning using binocular stereo vision；The Binocular Stereo Vision System mainly wraps
Include camera calibration, image segmentation, Stereo matching and 3 dimension 4 modules of ranging, wherein Stereo matching be binocular visual positioning most
A crucial step, but realize that the accurate Stereo matching of target area is more difficult, and the inaccuracy of Stereo matching will result directly in and be obtained
The depth information taken generates deviation, while its real-time is the ultimate challenge that binocular and more mesh positioning vision system face.
Application publication number is that the application for a patent for invention of CN104369188B discloses one kind " based on machine vision and ultrasonic wave
The workpiece gripper device and method of sensor ", the patent of invention acquire workpiece profile image using monocular camera, use ultrasonic wave
Sensor instrument distance realizes crawl of the robot to workpiece.But its device is hard by camera, sensor, liquid crystal display, PLC etc.
Part is formed, and hardware needed for equipment is more and cost is higher.
Invention content
Present invention aims at a kind of the workpiece automatic identification and intelligent grabbing system of view-based access control model is provided, grabbed by establishing
The parameterized model of system is taken to provide image coordinate to the transfer algorithm of robot coordinate, the image provided using specific software
Preprocess method carries out secondary development under designated environment, realizes target positioning and robot controls two big basic functions, most
Control robot completes the crawl of target workpiece eventually, and working environment or mesh can not be adapted in time by efficiently solving existing robot
Mark object changes, and leads to operation failure, so as to meet the requirement of flexible manufacturing system.
In order to solve the above technical problems, the present invention adopts the following technical scheme that：A kind of workpiece of view-based access control model is known automatically
Not and intelligent grabbing system, the system include：Image capture module, industrial personal computer module and robot module；Wherein, the figure
As acquisition module is connected with the industrial personal computer module；The industrial personal computer module is connected with the robot module.
Further, described image acquisition module is made of camera, camera lens, light source and workpiece, is made an uproar for quick obtaining
Sound is small, precision hi-vision data information.
Further, the industrial personal computer module uses the industrial control computer of Taiwan Yan Hua companies, is responsible for receiving Image Acquisition
The image information of module acquisition simultaneously controls signal to control with robot is converted to after image processing algorithm completion workpiece identification
The physical location of end effector of robot.
Further, the robot module is made of driving device and robot body, for the control according to reception
Instruction performs corresponding operation.
The present invention has following advantageous effect compared with prior art：
The present invention program provides conversion of the image coordinate to robot coordinate by establishing the parameterized model of grasping system
Algorithm, the image pre-processing method provided using specific software carry out secondary development under designated environment, realize target and determine
Position and robot control two big basic functions, the final crawl that robot is controlled to complete target workpiece.
Description of the drawings
Fig. 1 is the workpiece automatic identification of view-based access control model and intelligent grabbing system structure diagram.
Fig. 2 is the workpiece automatic identification of view-based access control model and intelligent grabbing systematic schematic diagram.
Fig. 3 is national forest park in Xiaokeng.
Fig. 4 is the workpiece automatic identification of view-based access control model and intelligent grabbing systematic parameter model.
Specific embodiment
Below in conjunction with the accompanying drawings and specific embodiment the present invention is carried out in further detail with complete explanation.It is appreciated that
It is that specific embodiment described herein is only used for explaining the present invention rather than limitation of the invention.
With reference to Fig. 1, a kind of workpiece automatic identification of view-based access control model of the invention and intelligent grabbing system, the system include：
Image capture module, industrial personal computer module and robot module；Wherein, described image acquisition module and the industrial personal computer module phase
Even；The industrial personal computer module is connected with the robot module.
(1) image capture module is made of camera, camera lens, light source and workpiece, for quick obtaining noise to be small, precision is high
Image data information；Wherein,
Camera uses the industrial CCD camera of Basler companies acA2500-14gm models, using gigabit Ethernet with calculating
Machine communicates, and camera is mounted on right over conveyer belt；
Camera lens is using the tight shot of the M0814-MP2 models of COMPUTAR companies of Japan, focal length 8mm, maximum imaging ruler
Very little 8.8mm × 6.6mm, imaging size meet design requirement；
Light source uses the LED annular light sources of CCS companies, and the LED illumination System response time is fast, and it is right can to obtain high-quality, height
Than degree image.
(2) industrial personal computer module uses the industrial control computer of Taiwan Yan Hua companies, is responsible for receiving the image letter of CCD camera acquisition
It ceases and image processing algorithm is used to be converted to robot control signal after completing workpiece identification to control end effector of robot
Physical location.
(3) robot module is made of driving device and robot body, for performing phase according to the control instruction of reception
The operation answered.Wherein, robot uses the IRB120 humanoid robots of ABB AB of Switzerland, which has 6 rotary joints,
By AC servo machinery driving, end repetitive positioning accuracy 0.01mm, control is simple, and programming is convenient, suitable for being grabbed on production line
It is taken as industry.
With reference to Fig. 2, the video camera of this system is fixedly mounted on above conveyer belt, and conveyer belt is continuously run, and workpiece is from transmission
Band one end enters camera coverage, sets timer, and per 0.5s, triggering camera acquires a frame image, image size for 640 ×
480, the position of form center of workpiece is determined by stencil matching method, by two field pictures workpiece the direction of motion displacement and shooting
The time interval of this two field pictures can calculate the speed of workpiece motion s, pass through Kalman prediction following clock cycle work
The position of part, and the movement locus of planning robot make workpiece motion s to the position of the end effector of robot when capturing station
Appearance is overlapped with object pose, and finally by the inverse solution of robot kinematics, posture information is converted into pass known to industrial robot
Angle and angle control information are saved, so as to fulfill vision guide robot accurately grabbing workpiece is utilized.
Wherein, upper ductility limit is the position that workpiece has just initially entered the robot capture area moment, in order to reduce robot
Stand-by period, as far as possible that the setting of upper ductility limit is more forward, lower ductility limit is the position that workpiece leaves the capture area moment, and workpiece must
It must be crawled by robots in capture area, otherwise this time crawl mission failure, robot abandons tracking the workpiece.
First, the parameterized model of grasping system is established
1st, camera calibration
With reference to Fig. 3, (come from paper for national forest park in Xiaokeng《Robot vision measures and control》, author：Xu De, Tan Min,
Lee original Beijing:National Defense Industry Press, 2011.), coordinate system is established in the optical axis center of video camera, Z axis is along optical axis direction, X
Axis takes image coordinate along the horizontal increased direction of image coordinate, in camera coordinate system OCIn-xyz, the coordinate of the p that sets up an office for (x,
Y, z), it the subpoint P of the plane of delineation coordinate for (X, Y, Z), wherein Z=f, f are the focal lengths of video camera.
Following proportionate relationship is then obtained by pinhole imaging system principle：
By CCD image-forming principles it is found that the picture on imaging plane obtains digital picture by enhanced processing, on imaging plane
Picture point (X, Y) is converted to picture point (u, v), and remember (u0,v0) image coordinate for optical axis center line and imaging plane intersection point, then
Have：
In formula：dx, dyPhysical size of the respectively pixel on X and Y-direction, sx=1/dx, sy=1/dyRespectively X
With the number of pixels of the sample frequency in Y-direction, i.e. unit length.
Substituting into formula (2) and be rewritten into matrix form formula (1) has：
In formula：fx=fsx, fy=fsyIt is respectively defined as X and the equivalent focal length of Y-direction, fx、fy、u0、v0This 4 parameters are only
Related with video camera internal structure, because of the inner parameter of referred to herein as video camera, the outer parameter model of video camera is world coordinate system
Description in camera coordinate system.Coordinate system O-XwYwZwExpression in coordinate system O-xyz forms the outer parameter of video camera
Matrix：
Therefore the relationship of world coordinates and image coordinate is set up by camera coordinate system；Formula (4) is substituted into formula (3)
：
2nd, trick coordinate is demarcated
In this system, video camera is separately mounted to conveyer belt both ends with robot, it is impossible to pass through traditional hand and eye calibrating
Method determines the relative pose between workpiece and robot, therefore establishes two reference frame ref on a moving belt1And ref2,
ref1It establishes in the range of camera coverage, ref2It establishes in the Work Space Range of robot.With reference to Fig. 4, video camera passes through
Plane target standardization calibrates inside and outside parameter, and establishes reference frame ref using wherein one secondary scaling board image1, obtain
ref1With the relative pose between camera coordinate system camcam Href1；ref1With ref2Between only X-direction translation relation,
Position orientation relation is ref1Href2；With the line-of-sight course calibration reference frame ref of similar calibration workpiece coordinate system2With robot base
Position orientation relation between coordinate systembase Href2。
It is set up between camera coordinate system cam and robot base's coordinate system base by this two reference frames
Relationshipbase Hcam=base Href2·ref2Href1·(cam Href1)-1, position to obtain by targetcam Hobj, then target workpiece exist
Pose transition matrix in robot base's coordinate system is：base Hobj=base Hcam·cam Hobj；Thus set up target work
Contacting between part and robot.
2nd, based on the relevant template matching algorithm of gray scale
Feature extraction and template matches are an important links in motion target tracking, the profile of target image, shape,
The criterion of gray value, color histogram when can serve as template matches, and a variety of geometry or gray scale can be comprehensively utilized
Feature is to target into line trace.After target's feature-extraction, suitable search matching algorithm is selected to realize target positioning.In order to full
The higher requirement of real-time during sufficient operation, used image processing algorithm must have sufficiently high arithmetic speed, and right
Illumination variation and environmental factor have enough robustness.
Common template matching algorithm is mainly based upon gray scale correlation and two kinds of template matching algorithms based on geometric properties.
Based on the relevant template matching algorithm of gray scale directly matched using gradation of image value information as characteristic parameter, based on gray scale
Relevant algorithm comparison is ripe, and principle is simple, realization is also relatively easy to.Therefore, the present invention is using based on the relevant template of gray scale
Matching algorithm.
The similarity measurement criterion used all pixels gray value difference between calculation template image and image to be searched
Quadratic sum, i.e. SSD algorithms, if template size is M × N number of pixel, the similarity function of masterplate and image to be matched is：
In formula：T (m, n) and S (i+m, j+n) be respectively template image and image to be searched at (m, n) coordinate and (i+m,
Whether j+n) the gray value at coordinate, similarity function value during by calculating each position determine to have in image and mould
The same or similar target of plate.Above formula is normalized to obtain the normalized-cross-correlation function NCC of template matches：
NCC coefficient magnitudes represent the matching degree of template and image to be searched at (i, j) position, value 0~1 it
Between, NCC=1 expression found in image to be searched with the identical example of template, in image to be searched complete all searches
The position at NCC maximum is found out after rope, which is the target matched.Utilize similarity measurements flow function, template image warp
It crosses and translates and be rotated in one or more examples that template is found in image to be searched, and determine position coordinates and the rotation of example
Angle, the Grasp Planning for subsequent robot provide authentic communication.
3rd, Moving Target Tracking Algorithm
1st, Kalman filtering
The position of moment target on a moving belt of taking pictures is obtained by camera calibration and template matches, but target is transmitting
It is constantly moving to take, and robot realizes that grasping movement is also required to certain time interval, therefore, only pre- in advance
The position that target is likely to occur is measured, and robot is made to move to reach simultaneously with target in advance and could complete workpiece at predicted position
Crawl, the here prediction of object pose (come from paper by Kalman filter《The basic principle of Kalman filtering and application》, make
Person：Peng Ding acute hearing software guides, 2009,11 (8):32~34.) it completes, Kalman filter is a kind of linear filter, i.e.,
As long as knowing that the estimated value of last moment state and the observation of current state calculate the estimated value of current state,
Therefore the historical information of hourly observation or estimation is not needed to.Kalman filter is widely used in Visual Tracking System.
It can accurately estimate the state in moving object future, and then guided robot completes dynamic crawl task.
2nd, the foundation of motion model
Workpiece on conveyer belt generally does linear uniform motion, if the motion state parameters of target are a certain moment target
Position and speed, during tracking, since adjacent two field pictures time interval is shorter, target state variation is smaller,
Target uniform motion in unit interval is assume that, so speed parameter is enough the movement tendency for reflecting target.At this
In with a four-dimensional variable-definition system mode xk, i.e. (xsk,ysk,xvk,yvk) target is represented respectively in the position in x and y directions
And speed, equation are：
Therefore to this system, system model is established as follows：Dt is tk-1With tkTime interval.
It can only observe the position of target in the picture, therefore observation model zkFor：
Detect to take pictures the position (xs of moment workpiece by stencil matching0,ys0), the starting velocity (xv of workpiece0, 0), by
Originate the image that two frames include workpiece, by calculate workpiece centre the displacement of the direction of motion divided by shoot this 2 frame image when
Between obtain, then by the original state of systemWith system initial error covariance matrix P0=
10eye (4) (eye (4) represent 4 rank diagonal matrix) initialized card Thalmann filter, and at the time of record present image, under
Before one frame image carries out pattern match, by calculating the time interval dt between two frames and bringing into status predication equation, obtain
Go out current motion stateEstimated value, and willCentered on ROI of the region as this pattern match
(Region of interest) finds the best match of template, obtains (x in the roi1,y1), and record present image when
It carves.By z1=(x1,y1) observation vector brings state renewal equation into, filter status is updated, obtains each moment moving target
Position and the estimated value of speed.Using the possible position of Kalman filter prediction workpiece in the picture, so as to avoid to whole
Width picture search matches, and greatly accelerates the speed of template matches, improves the real-time of system.- school is estimated by such
Positive process, the position (t after estimating target certain time Δ t with Kalman filter2Moment), and planning robot accordingly
Movement locus and speed, by the control instruction of generation by switch board control robot complete this grasping movement.
The foregoing is merely the preferred embodiment of the present invention, are not intended to restrict the invention, for those skilled in the art
For, the present invention can have various modifications and changes.All any modifications made within spirit and principles of the present invention are equal
Replace, improve etc., it should all be included in the protection scope of the present invention.
Claims (4)
1. the workpiece automatic identification of view-based access control model and intelligent grabbing system, which is characterized in that the system comprises：Image Acquisition mould
Block, industrial personal computer module and robot module；Wherein, described image acquisition module is connected with the industrial personal computer module；The work
Control machine module is connected with the robot module.
2. the workpiece automatic identification of view-based access control model according to claim 1 and intelligent grabbing system, which is characterized in that described
Image capture module is made of camera, camera lens, light source and workpiece, for quick obtaining noise to be small, precision hi-vision data letter
Breath.
3. the workpiece automatic identification of view-based access control model according to claim 1 and intelligent grabbing system, which is characterized in that described
Industrial personal computer module uses the industrial control computer of Taiwan Yan Hua companies, is responsible for receiving the image information and fortune of image capture module acquisition
Robot control signal is converted to after completing workpiece identification with image processing algorithm to control the reality of end effector of robot
Position.
4. the workpiece automatic identification of view-based access control model according to claim 1 and intelligent grabbing system, which is characterized in that described
Robot module is made of driving device and robot body, for performing corresponding operation according to the control instruction of reception.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611116892.7A CN108161931A (en) | 2016-12-07 | 2016-12-07 | The workpiece automatic identification of view-based access control model and intelligent grabbing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611116892.7A CN108161931A (en) | 2016-12-07 | 2016-12-07 | The workpiece automatic identification of view-based access control model and intelligent grabbing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108161931A true CN108161931A (en) | 2018-06-15 |
Family
ID=62526636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611116892.7A Pending CN108161931A (en) | 2016-12-07 | 2016-12-07 | The workpiece automatic identification of view-based access control model and intelligent grabbing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108161931A (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107942949A (en) * | 2017-03-31 | 2018-04-20 | 沈机（上海）智能***研发设计有限公司 | A kind of lathe vision positioning method and system, lathe |
| CN108709621A (en) * | 2018-08-02 | 2018-10-26 | 河北工业大学 | A kind of special-shaped workpiece detection grabbing device based on supersonic array |
| CN108827154A (en) * | 2018-07-09 | 2018-11-16 | 深圳辰视智能科技有限公司 | A kind of robot is without teaching grasping means, device and computer readable storage medium |
| CN108972556A (en) * | 2018-08-14 | 2018-12-11 | 广东工业大学 | Conducting wire grasping system and method on small and special electric machine production line under complex illumination environment |
| CN109015653A (en) * | 2018-08-30 | 2018-12-18 | 黄河科技学院 | Grab control method, device, storage medium and electronic equipment |
| CN109048918A (en) * | 2018-09-25 | 2018-12-21 | 华南理工大学 | A kind of visual guide method of wheelchair arm robot |
| CN109454638A (en) * | 2018-10-31 | 2019-03-12 | 昆山睿力得软件技术有限公司 | A kind of robot grasping system of view-based access control model guidance |
| CN109454501A (en) * | 2018-10-19 | 2019-03-12 | 江苏智测计量技术有限公司 | A kind of lathe on-line monitoring system |
| CN109623821A (en) * | 2018-12-26 | 2019-04-16 | 深圳市越疆科技有限公司 | The visual guide method of mechanical hand crawl article |
| CN109848998A (en) * | 2019-03-29 | 2019-06-07 | 砚山永盛杰科技有限公司 | One kind being used for 3C industry vision four axis flexible robot |
| CN109911549A (en) * | 2019-01-25 | 2019-06-21 | 东华大学 | A kind of the Robotic Dynamic tracking grasping system and method for fragile goods |
| CN110102490A (en) * | 2019-05-23 | 2019-08-09 | 北京阿丘机器人科技有限公司 | The assembly line packages device and electronic equipment of view-based access control model technology |
| CN110480685A (en) * | 2019-05-15 | 2019-11-22 | 青岛科技大学 | A kind of Agricultural vehicle wheel automatic production line vision manipulator |
| CN110509273A (en) * | 2019-08-16 | 2019-11-29 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | The robot mechanical arm of view-based access control model deep learning feature detects and grasping means |
| CN110640739A (en) * | 2018-11-07 | 2020-01-03 | 宁波赛朗科技有限公司 | Grabbing industrial robot with center position recognition function |
| CN110980061A (en) * | 2019-12-12 | 2020-04-10 | 重庆铁马专用车有限公司 | Novel intelligence major possession refuse treatment system |
| CN111112885A (en) * | 2019-11-26 | 2020-05-08 | 福尼斯智能装备(珠海)有限公司 | Welding system with vision system for feeding and discharging workpieces and self-adaptive positioning of welding seams |
| CN111216099A (en) * | 2018-11-27 | 2020-06-02 | 发那科株式会社 | Robot system and coordinate conversion method |
| CN111447366A (en) * | 2020-04-27 | 2020-07-24 | Oppo（重庆）智能科技有限公司 | Transportation method, transportation device, electronic device, and computer-readable storage medium |
| CN111815718A (en) * | 2020-07-20 | 2020-10-23 | 四川长虹电器股份有限公司 | Method for quickly switching stations of industrial screw robot based on vision |
| CN111989540A (en) * | 2018-07-13 | 2020-11-24 | 深圳配天智能技术研究院有限公司 | Workpiece tracking method and system and robot |
| CN112296999A (en) * | 2019-11-12 | 2021-02-02 | 太原科技大学 | Irregular workpiece machining path generation method based on machine vision |
| WO2021042376A1 (en) * | 2019-09-06 | 2021-03-11 | 罗伯特·博世有限公司 | Calibration method and apparatus for industrial robot, three-dimensional environment modeling method and device for industrial robot, computer storage medium, and industrial robot operating platform |
| CN113043334A (en) * | 2021-02-23 | 2021-06-29 | 上海埃奇机器人技术有限公司 | Robot-based photovoltaic cell string positioning method |
| CN113808197A (en) * | 2021-09-17 | 2021-12-17 | 山西大学 | Automatic workpiece grabbing system and method based on machine learning |
| CN114347033A (en) * | 2022-01-27 | 2022-04-15 | 达闼机器人有限公司 | Robot article grabbing method and device, robot and storage medium |
| US20220130066A1 (en) * | 2019-01-25 | 2022-04-28 | Sony Interactive Entertainment Inc. | Robot controlling system |
| CN114454177A (en) * | 2022-03-15 | 2022-05-10 | 浙江工业大学 | Robot tail end position compensation method based on binocular stereo vision |
-
2016
- 2016-12-07 CN CN201611116892.7A patent/CN108161931A/en active Pending
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107942949A (en) * | 2017-03-31 | 2018-04-20 | 沈机（上海）智能***研发设计有限公司 | A kind of lathe vision positioning method and system, lathe |
| CN107942949B (en) * | 2017-03-31 | 2019-01-25 | 沈机（上海）智能***研发设计有限公司 | A kind of lathe vision positioning method and system, lathe |
| CN108827154A (en) * | 2018-07-09 | 2018-11-16 | 深圳辰视智能科技有限公司 | A kind of robot is without teaching grasping means, device and computer readable storage medium |
| CN111989540A (en) * | 2018-07-13 | 2020-11-24 | 深圳配天智能技术研究院有限公司 | Workpiece tracking method and system and robot |
| CN111989540B (en) * | 2018-07-13 | 2022-04-15 | 深圳配天智能技术研究院有限公司 | Workpiece tracking method and system and robot |
| CN108709621A (en) * | 2018-08-02 | 2018-10-26 | 河北工业大学 | A kind of special-shaped workpiece detection grabbing device based on supersonic array |
| CN108709621B (en) * | 2018-08-02 | 2024-04-26 | 河北工业大学 | Abnormal workpiece detection grabbing device based on ultrasonic array |
| CN108972556A (en) * | 2018-08-14 | 2018-12-11 | 广东工业大学 | Conducting wire grasping system and method on small and special electric machine production line under complex illumination environment |
| CN108972556B (en) * | 2018-08-14 | 2021-07-09 | 广东工业大学 | Wire grabbing system and method in complex illumination environment on micro special motor production line |
| CN109015653A (en) * | 2018-08-30 | 2018-12-18 | 黄河科技学院 | Grab control method, device, storage medium and electronic equipment |
| CN109048918A (en) * | 2018-09-25 | 2018-12-21 | 华南理工大学 | A kind of visual guide method of wheelchair arm robot |
| CN109048918B (en) * | 2018-09-25 | 2022-02-22 | 华南理工大学 | Visual guide method for wheelchair mechanical arm robot |
| CN109454501A (en) * | 2018-10-19 | 2019-03-12 | 江苏智测计量技术有限公司 | A kind of lathe on-line monitoring system |
| CN109454638A (en) * | 2018-10-31 | 2019-03-12 | 昆山睿力得软件技术有限公司 | A kind of robot grasping system of view-based access control model guidance |
| CN110640739A (en) * | 2018-11-07 | 2020-01-03 | 宁波赛朗科技有限公司 | Grabbing industrial robot with center position recognition function |
| CN111216099A (en) * | 2018-11-27 | 2020-06-02 | 发那科株式会社 | Robot system and coordinate conversion method |
| CN109623821A (en) * | 2018-12-26 | 2019-04-16 | 深圳市越疆科技有限公司 | The visual guide method of mechanical hand crawl article |
| CN109623821B (en) * | 2018-12-26 | 2022-04-01 | 日照市越疆智能科技有限公司 | Visual guide method for grabbing articles by mechanical arm |
| CN109911549A (en) * | 2019-01-25 | 2019-06-21 | 东华大学 | A kind of the Robotic Dynamic tracking grasping system and method for fragile goods |
| US20220130066A1 (en) * | 2019-01-25 | 2022-04-28 | Sony Interactive Entertainment Inc. | Robot controlling system |
| CN109848998A (en) * | 2019-03-29 | 2019-06-07 | 砚山永盛杰科技有限公司 | One kind being used for 3C industry vision four axis flexible robot |
| CN110480685A (en) * | 2019-05-15 | 2019-11-22 | 青岛科技大学 | A kind of Agricultural vehicle wheel automatic production line vision manipulator |
| CN110102490B (en) * | 2019-05-23 | 2021-06-01 | 北京阿丘机器人科技有限公司 | Assembly line parcel sorting device based on vision technology and electronic equipment |
| CN110102490A (en) * | 2019-05-23 | 2019-08-09 | 北京阿丘机器人科技有限公司 | The assembly line packages device and electronic equipment of view-based access control model technology |
| CN110509273B (en) * | 2019-08-16 | 2022-05-06 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Robot manipulator detection and grabbing method based on visual deep learning features |
| CN110509273A (en) * | 2019-08-16 | 2019-11-29 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | The robot mechanical arm of view-based access control model deep learning feature detects and grasping means |
| CN114390963A (en) * | 2019-09-06 | 2022-04-22 | 罗伯特·博世有限公司 | Calibration method and device for industrial robot, three-dimensional environment modeling method and device, computer storage medium and industrial robot operating platform |
| WO2021042376A1 (en) * | 2019-09-06 | 2021-03-11 | 罗伯特·博世有限公司 | Calibration method and apparatus for industrial robot, three-dimensional environment modeling method and device for industrial robot, computer storage medium, and industrial robot operating platform |
| CN112296999A (en) * | 2019-11-12 | 2021-02-02 | 太原科技大学 | Irregular workpiece machining path generation method based on machine vision |
| CN112296999B (en) * | 2019-11-12 | 2022-07-08 | 太原科技大学 | Irregular workpiece machining path generation method based on machine vision |
| CN111112885A (en) * | 2019-11-26 | 2020-05-08 | 福尼斯智能装备(珠海)有限公司 | Welding system with vision system for feeding and discharging workpieces and self-adaptive positioning of welding seams |
| CN110980061A (en) * | 2019-12-12 | 2020-04-10 | 重庆铁马专用车有限公司 | Novel intelligence major possession refuse treatment system |
| CN111447366A (en) * | 2020-04-27 | 2020-07-24 | Oppo（重庆）智能科技有限公司 | Transportation method, transportation device, electronic device, and computer-readable storage medium |
| CN111815718A (en) * | 2020-07-20 | 2020-10-23 | 四川长虹电器股份有限公司 | Method for quickly switching stations of industrial screw robot based on vision |
| CN113043334A (en) * | 2021-02-23 | 2021-06-29 | 上海埃奇机器人技术有限公司 | Robot-based photovoltaic cell string positioning method |
| CN113808197A (en) * | 2021-09-17 | 2021-12-17 | 山西大学 | Automatic workpiece grabbing system and method based on machine learning |
| CN114347033A (en) * | 2022-01-27 | 2022-04-15 | 达闼机器人有限公司 | Robot article grabbing method and device, robot and storage medium |
| WO2023143408A1 (en) * | 2022-01-27 | 2023-08-03 | 达闼机器人股份有限公司 | Article grabbing method for robot, device, robot, program, and storage medium |
| CN114347033B (en) * | 2022-01-27 | 2023-12-08 | 达闼机器人股份有限公司 | Robot character grabbing method and device, robot and storage medium |
| CN114454177A (en) * | 2022-03-15 | 2022-05-10 | 浙江工业大学 | Robot tail end position compensation method based on binocular stereo vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108161931A (en) | The workpiece automatic identification of view-based access control model and intelligent grabbing system | |
| CN109308693B (en) | Single-binocular vision system for target detection and pose measurement constructed by one PTZ camera | |
| US11117262B2 (en) | Intelligent robots | |
| CN107618030B (en) | Robot dynamic tracking grabbing method and system based on vision | |
| US8244402B2 (en) | Visual perception system and method for a humanoid robot | |
| CN101274432B (en) | Apparatus for picking up objects | |
| CN107471218B (en) | Binocular vision-based hand-eye coordination method for double-arm robot | |
| CN103895042A (en) | Industrial robot workpiece positioning grabbing method and system based on visual guidance | |
| CN110211180A (en) | A kind of autonomous grasping means of mechanical arm based on deep learning | |
| CN108898634B (en) | Method for accurately positioning embroidery machine target needle eye based on binocular camera parallax | |
| CN108399639A (en) | Fast automatic crawl based on deep learning and arrangement method | |
| CN111645074A (en) | Robot grabbing and positioning method | |
| CN109454638A (en) | A kind of robot grasping system of view-based access control model guidance | |
| CN113276106B (en) | Climbing robot space positioning method and space positioning system | |
| CN109940626B (en) | Control method of eyebrow drawing robot system based on robot vision | |
| CN113267452A (en) | Engine cylinder surface defect detection method and system based on machine vision | |
| Fanello et al. | 3D stereo estimation and fully automated learning of eye-hand coordination in humanoid robots | |
| CN112775959A (en) | Method and system for determining grabbing pose of manipulator and storage medium | |
| Gratal et al. | Visual servoing on unknown objects | |
| Hsu et al. | Development of a faster classification system for metal parts using machine vision under different lighting environments | |
| Mišeikis et al. | Two-stage transfer learning for heterogeneous robot detection and 3d joint position estimation in a 2d camera image using cnn | |
| Kragic et al. | Model based techniques for robotic servoing and grasping | |
| Gao et al. | An automatic assembling system for sealing rings based on machine vision | |
| Li et al. | Workpiece intelligent identification and positioning system based on binocular machine vision | |
| CN116206189A (en) | Curved surface graphic identification code and identification method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180615 |