CN107471218A - A kind of tow-armed robot hand eye coordination method based on multi-vision visual - Google Patents
A kind of tow-armed robot hand eye coordination method based on multi-vision visual Download PDFInfo
- Publication number
- CN107471218A CN107471218A CN201710802484.5A CN201710802484A CN107471218A CN 107471218 A CN107471218 A CN 107471218A CN 201710802484 A CN201710802484 A CN 201710802484A CN 107471218 A CN107471218 A CN 107471218A
- Authority
- CN
- China
- Prior art keywords
- mtd
- target object
- mtr
- msub
- mechanical arm
- 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.)
- Granted
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
- B25J9/16—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)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of tow-armed robot hand eye coordination method based on multi-vision visual, belong to robot vision field, target positioning is carried out using mesh camera more than two, the mechanical arm nearer from target object is chosen to be captured, and the repositioning to target object is carried out simultaneously, so as to which target object crawl is delivered into FX.The tow-armed robot hand eye coordination method based on multi-vision visual of the present invention, solve in existing scheme the problem of only single camera photographs object in binocular camera, can not realize binocular ranging localization, improve the precision of mechanical arm crawl target object.
Description
Technical field
The present invention relates to robot vision field, and in particular to a kind of tow-armed robot hand eye coordination based on multi-vision visual
Method.
Background technology
Computer vision refers to replace human eye that target is identified, tracks with camera and measured, as presently the most
The study hotspot in forward position, the robot technology based on computer vision are widely used in robot control field.Binocular solid
Vision is to utilize two images of the imaging device from different position acquisition testees, by calculating the position between image corresponding points
Deviation is put, to obtain the method for object dimensional geological information.Vision can provide abundant environment and target information for robot, be
The judgement decision-making of robot provides foundation.
In actual mechanical process, existed using the ranging of parallel fixed binocular stereo vision and the crawl of manipulator each
The problem of kind of various kinds, wherein common situation have target object be blocked or its be present in outside the visual field cause shooting less than or
It is incomplete, and can not be accurately positioned and capture.Such as " binocular distance-finding method, device and Panorama Mosaic method and its it is in patent
In system ", it describes the principle of binocular ranging in detail.But in the ranging process of reality, often exist to target object
The vision dead zone problem of seizure, i.e. binocular camera can not capture target object simultaneously, so as to mechanical arm crawl failure.
The content of the invention
The present invention proposes a kind of tow-armed robot hand eye coordination method based on multi-vision visual.
Realize that technical solution of the invention is:A kind of tow-armed robot hand eye coordination method based on multi-vision visual,
Concretely comprise the following steps:
Step 1, two binocular cameras are mounted respectively on the mechanical arm of tow-armed robot, and calibrate shooting respectively
Head is arrived equipped with the transfer matrix of mechanical arm tail end of the camera, the transformation matrix of mechanical arm end to the pedestal and two
Transformation matrix between mechanical arm pedestal;
Step 2, the movement of control machinery arm, by binocular camera searching target object, and preserve the feature of target object,
Until at least two monocular cams photograph target object, the search to target object is completed;
Step 3, host computer extract and handled two images when scanning terminates with target signature, obtain target object
Three-dimensional coordinate information, complete the positioning to target object;
Step 4, the three-dimensional information based on target object, control machinery arm are captured, and complete the crawl to target object;
Step 5, target object is moved to FX, mechanical arm returns to original state, completes crawl task.
Compared with prior art, its remarkable advantage is the present invention:
The present invention is shot using mesh camera more than two, can solve the problem that existing binocular camera and monocular shooting
The vision dead zone problem of head, the probability that camera successfully catches target is greatly improved, and during mechanical arm captures, it is double
Mesh camera also to target carry out captured in real-time, constantly obtain target position, the three-dimensional coordinate of continuous updating target, while
It has been correspondingly improved the precision of mechanical arm crawl.
Further detailed description is done to the present invention below in conjunction with the accompanying drawings.
Brief description of the drawings
Fig. 1 is the two-dimensional coordinate transition diagram of the present invention.
Fig. 2 is the transition diagram of image coordinate system of the present invention and gray scale coordinate system.
Fig. 3 is camera coordinate system of the present invention, world coordinate system, the relation schematic diagram of image coordinate system.
Fig. 4 is that target object of the present invention positions schematic diagram.
Fig. 5 is the flow chart of one embodiment of the invention.
Embodiment
A kind of tow-armed robot hand eye coordination method based on multi-vision visual, is concretely comprised the following steps:
Step 1, two binocular cameras are mounted respectively on the mechanical arm of tow-armed robot, and calibrate shooting respectively
Head is arrived equipped with the transfer matrix of mechanical arm tail end of the camera, the transformation matrix of mechanical arm end to the pedestal and two
Transformation matrix between mechanical arm pedestal;
Step 2, the movement of control machinery arm, by binocular camera searching target object, and preserve the feature of target object,
Until at least two monocular cams photograph target object, the search to target object is completed, is concretely comprised the following steps:
Step 2-1, control any one mechanical arm pedestal steering wheel slowly to rotate, drive binocular camera to enter target object
Row scanning and detection;
Step 2-2, the feature of target object is preserved;
Step 2-3, pedestal steering wheel is controlled to keep original scanning direction to be rotated further 30 °, when angle rotatable is less than 30 °
When, rotated by angle rotatable;
Step 2-4, judge whether two on the mechanical arm cameras all photograph target object, if on the mechanical arm
Two cameras all photograph target object, then stop scanning;If there was only a shooting in two cameras on the mechanical arm
Head photographs target object, then controls another mechanical arm to drive binocular camera to be scanned and detect target object, weight
Multiple step 2-2, step 2-3, until at least two monocular cams photograph target object, complete to search target object
Seek.
Step 3, host computer extract and handled two images when scanning terminates with target signature, obtain target object
Three-dimensional coordinate information, the positioning to target object is completed, concretely comprise the following steps:
Step 3-1, two width of extraction have the image of target signature, obtain target object respectively in the image coordinate of two width figures
Pixel coordinate (u, v) in system;
Step 3-2, according to length in coordinate system and the relation of pixel, obtain target object and sat respectively in the image of two width figures
Length coordinate (x, y) in mark system, it is specially:
In formula, dx,dyThe length and height of a pixel, u are represented respectively0,v0Represent that the image projection point of target object is sat
Mark;
Step 3-3, according to the relation of image coordinate system and camera coordinate system, obtain target object and shooting two width respectively
Three-dimensional coordinate x in the camera coordinate system of figurec,yc,zc, it is specially:
Step 3-4, the three-dimensional coordinate x according to target object in two camera coordinate systems are photographedc,yc,zc, obtain
Three-dimensional coordinate x of the target object in world coordinate systemw,yw,zw, it is specially:
In formula, matrix M represents camera to the transfer matrix of world coordinate system origin.
Step 4, the three-dimensional information based on target object, control machinery arm are captured, and complete the crawl to target object,
Concretely comprise the following steps:
Step 4-1, according to the three-dimensional coordinate information of the target object of acquisition, control to the minimum machinery of target object distance
Arm is captured;
Step 4-2, binocular camera captured in real-time target object, the new three-dimensional coordinate information of target object is obtained;
Step 4-3, repeat step 4-1, step 4-2, until mechanical arm grabs target object, step 5 is carried out.
Step 5, target object is moved to FX, mechanical arm returns to original state, completes crawl task.
Binocular stereo vision is to be shot with two video cameras in different positions, obtains surrounding scenery, analyzes two
The common portion of camera vision, the three-dimensional information of common portion is just derived by principle geometrically and principle of parallax.
For quantitative description video camera imaging process, it is necessary to use the relevant knowledge and three kinds of coordinates of coordinate system conversion
System:Image coordinate system, camera coordinate system and world coordinate system.
1st, the conversion of two-dimensional coordinate system
Obtain, rotate plus translation as shown in figure 1, new coordinate system O-X ' Y ' are rotated by original coordinate system O-XY coordinate systems
Angle be θ, with any point (x in original two dimensional coordinate system O-XY0,y0) origin as new coordinate system O-X ' Y ', can be with
Obtain different coordinates arbitrary coordinate transformation relation:
2nd, the conversion of three-dimensional system of coordinate
It is similar with two dimension, the angle of tri- reference axis rotations of xyz of three-dimensional system of coordinate is designated as α β γ respectively.
By abbreviation, transfer matrix can be obtained:
Either two dimension or three-dimensional, when relation between knowing two coordinate systems, same object is in two seats
Coordinate in mark system all can be changed mutually.
3rd, image coordinate system
With reference to shown in Fig. 2, the image that video camera is clapped is transferred to host computer according to digital form, in the form of m × n array
In the presence of each element value in array is the gray scale of pixel, i.e. image, and the array is designated as into gray scale coordinate system O-UV, (u, v) table
Show any point in the coordinate system, but the coordinate unit of the coordinate system is pixel.In order to facilitate calculating, with target object
Image projection point O1(u0,v0) on establish reference axis parallel to u, v image coordinate system O1- XY, any point in the coordinate system
Coordinate is (x, y), and its unit is mm.
Now, a pixel is in image coordinate system O1Length in-XY coordinate systems is designated as dx, dy, then the seat of any point
(u, v) is marked in coordinate system O1Coordinate under-XY is:
4th, camera coordinate system
As shown in figure 3, O-XcYcZcCoordinate system is camera coordinate system, i.e., with video camera photocentre OcThe position at place is original
The coordinate system that point is established.
5th, world coordinate system
As shown in figure 4, world coordinate system is the absolute coordinate of objective world, be in order to describe the specific position of video camera and
Introduce, the position of any object in space can world coordinate system represent, world coordinate system O-XwYwZwTable
Show, the origin of world coordinate system is the end of mechanical arm in the present invention.
Coordinates of the target object p in the gray scale coordinate system for the image that video camera photographs is (u, v), then the point is in image
Coordinate in coordinate system is:
Coordinates of the target object p under two camera coordinate systems is (xc,yc,zc)T, target object p is in image coordinate system
And the relation between camera coordinate system is:
In formula, f represents the focal length of video camera.
If absolute coordinates of the p under world coordinate system is (xw,yw,zw)T, then have coordinate transform:
In formula, matrix M represents camera to the transfer matrix of world coordinate system origin.But only by a width picture numerical value simultaneously
Specific coordinate value is not can determine that, and the two images at least photographed with two cameras could be realized.Now there are two kinds of situations,
A kind of situation is that two images are shot by two monocular cams on same mechanical arm, and also a kind of situation is two width figures
As being shot respectively by a monocular cam on two mechanical arms.
When two images by same mechanical arm two monocular cams shoot when, using the mechanical arm tail end as
The origin of world coordinate system, matrix M are transfer matrix M of the camera to the mechanical arm tail end1, by installation mechanical arm and can take the photograph
Demarcate to obtain during camera.
When two images are shot by a monocular cam on two mechanical arms respectively, with any one machinery
Camera on the mechanical arm of origin of the arm end as world coordinate system, wherein piece image by establishing world coordinate system is clapped
Take the photograph, matrix M is transfer matrix M of the camera to the mechanical arm tail end1;Other piece image is by taking the photograph on another mechanical arm
Picture head is shot, then matrix M=M2T1T2T3, wherein, T1Represent the transformation matrix of another-bar mechanical arm end to the pedestal, T2
Represent the transformation matrix between two mechanical arm pedestals, T3Represent that the robot base for establishing world coordinate system is last to the manipulator
The transformation matrix at end, M2Represent the camera established on the mechanical arm of world coordinate system to the transfer matrix of mechanical arm tail end, T1、
T2、T3And M2It can all be obtained by demarcation.
So that a kind of tow-armed robot hand eye coordination method based on multi-vision visual disclosed by the invention, integrated use are more
The hand eye coordination method of mesh information, binocular range measurement principle and mechanical arm control, is captured to object.It the method overcome wall scroll
There is vision dead zone so as to lead to not accurately be captured in mechanical arm, improve machine when carrying out ranging to target object
The crawl efficiency of tool arm.
It is described in more detail with reference to embodiment.
Embodiment 1
As shown in figure 4, establishing the model of the stereoscopic vision of two random cameras of position, two single cameras are put at random
Put.In traditional biocular systems, world coordinate system is scheduled on a camera coordinates and fastened, to reduce amount of calculation, but in this hair
It is unknown that the camera of image is collected in bright, thus by world coordinate system origin be scheduled on camera coordinates fasten it is nonsensical, because
And the present invention establishes world coordinate system using the end of any one mechanical arm as origin.
The two images with target signature used in the present embodiment are shot by two cameras on same mechanical arm,
Using the mechanical arm tail end as the origin of world coordinate system, then according to target object p respectively in the image coordinate system of two images
In coordinate (x, y), respectively obtain coordinate (xs of the target object p in two camera coordinate systemsc,yc,zc)T, now, shooting
The transfer matrix M of head to world coordinate system origin is transfer matrix M of the camera on mechanical arm to the mechanical arm tail end1,
So as to the relation according to camera coordinate system and world coordinate system:
Obtain absolute coordinate (x of the target object in world coordinate systemw,yw,zw)T。
Embodiment 2
The two images with target signature used in the present embodiment are shot by the camera on two mechanical arms respectively
Obtain, the video camera shooting wherein on mechanical arm of the piece image by establishing world coordinate system, then target object is in the video camera
The relation of the coordinate system in coordinate and world coordinate system in coordinate system is:
Other width figure comes from another mechanical arm, now matrix M=M2T1T2T3, in formula, T1Represent another machinery
Arm end is to the transformation matrix of the pedestal, T2Represent the transformation matrix between two mechanical arm pedestals, T3World's seat is established in expression
The robot base of system is marked to the transformation matrix of the arm end, M2Represent the shooting established on the mechanical arm of world coordinate system
Head arrives the transfer matrix of mechanical arm tail end, then the seat in coordinate and world coordinate system of the target object in the camera coordinate system
Marking the relation for being is:
With reference to two relational expressions, three-dimensional coordinate information (x of the target object in world coordinate system just can be obtainedw,yw,zw
)T。
Claims (5)
- A kind of 1. tow-armed robot hand eye coordination method based on multi-vision visual, it is characterised in that concretely comprise the following steps:Step 1, two binocular cameras are mounted respectively on the mechanical arm of tow-armed robot, and calibrate camera respectively and arrive The transfer matrix of mechanical arm tail end equipped with the camera, the transformation matrix of mechanical arm end to the pedestal and two machineries Transformation matrix between arm pedestal;Step 2, the movement of control machinery arm, by binocular camera searching target object, and preserve the feature of target object, until At least two monocular cams photograph target object, complete the search to target object;Step 3, host computer extract and handled two images when scanning terminates with target signature, obtain the three-dimensional of target object Coordinate information, complete the positioning to target object;Step 4, the three-dimensional information based on target object, control machinery arm are captured, and complete the crawl to target object;Step 5, target object is moved to FX, mechanical arm returns to original state, completes crawl task.
- 2. the tow-armed robot hand eye coordination method according to claim 1 based on multi-vision visual, it is characterised in that step Control machinery arm moves in 2, by binocular camera searching target object, and the feature of target object is preserved, until at least Two monocular cams photograph target object, complete the search to target object, concretely comprise the following steps:Step 2-1, control any one mechanical arm pedestal steering wheel slowly to rotate, drive binocular camera to sweep target object Retouch and detect;Step 2-2, the feature of target object is preserved;Step 2-3, pedestal steering wheel is controlled to keep original scanning direction to be rotated further 30 °, when angle rotatable is less than 30, by can Rotational angle is rotated;Step 2-4, judge whether two on the mechanical arm cameras all photograph target object, if two on the mechanical arm Camera all photographs target object, then stops scanning;If only have a camera to clap in two cameras on the mechanical arm Target object is taken the photograph, then controls another mechanical arm to drive binocular camera to be scanned and detect target object, repeats to walk Rapid 2-2, step 2-3, until at least two monocular cams photograph target object, complete the search to target object.
- 3. the tow-armed robot hand eye coordination method according to claim 1 based on multi-vision visual, it is characterised in that step Host computer extracts and handled two images when scanning terminates with target signature in 3, extracts and handles with target signature Preceding two images.
- 4. the tow-armed robot hand eye coordination method according to claim 1 based on multi-vision visual, it is characterised in that step Host computer extracts and handled image when scanning terminates with target signature in 3, obtains target object in world coordinate system Three-dimensional coordinate, the positioning to target object is completed, is concretely comprised the following steps:Step 3-1, two width of extraction have the image of target signature, obtain target object respectively in the image coordinate system of two width figures Pixel coordinate (u, v);Step 3-2, according to length in coordinate system and the relation of pixel, target object is obtained respectively in the image coordinate system of two width figures In length coordinate (x, y), be specially:<mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mi>x</mi> <mo>=</mo> <mi>u</mi> <mi>d</mi> <mi>x</mi> <mo>-</mo> <msub> <mi>u</mi> <mn>0</mn> </msub> <mi>d</mi> <mi>x</mi> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mi>y</mi> <mo>=</mo> <mi>v</mi> <mi>d</mi> <mi>y</mi> <mo>-</mo> <msub> <mi>v</mi> <mn>0</mn> </msub> <mi>d</mi> <mi>y</mi> </mrow> </mtd> </mtr> </mtable> </mfenced>In formula, dx,dyThe length and height of a pixel, u are represented respectively0,v0Represent the image projection point coordinates of target object;Step 3-3, according to the relation of image coordinate system and camera coordinate system, obtain target object and shooting two width figures respectively Three-dimensional coordinate x in camera coordinate systemc,yc,zc, it is specially:<mrow> <msub> <mi>z</mi> <mi>c</mi> </msub> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mi>x</mi> </mtd> </mtr> <mtr> <mtd> <mi>y</mi> </mtd> </mtr> <mtr> <mtd> <mn>1</mn> </mtd> </mtr> </mtable> </mfenced> <mo>=</mo> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <mi>f</mi> </mtd> <mtd> <mn>0</mn> </mtd> <mtd> <mn>0</mn> </mtd> <mtd> <mn>0</mn> </mtd> </mtr> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <mi>f</mi> </mtd> <mtd> <mn>0</mn> </mtd> <mtd> <mn>0</mn> </mtd> </mtr> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <mn>0</mn> </mtd> <mtd> <mn>1</mn> </mtd> <mtd> <mn>0</mn> </mtd> </mtr> </mtable> </mfenced> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <msub> <mi>x</mi> <mi>c</mi> </msub> </mtd> </mtr> <mtr> <mtd> <msub> <mi>y</mi> <mi>c</mi> </msub> </mtd> </mtr> <mtr> <mtd> <msub> <mi>z</mi> <mi>c</mi> </msub> </mtd> </mtr> <mtr> <mtd> <mn>1</mn> </mtd> </mtr> </mtable> </mfenced> </mrow>Step 3-4, the three-dimensional coordinate x according to target object in two camera coordinate systems are photographedc,yc,zc, obtain target Three-dimensional coordinate x of the object in world coordinate systemw,yw,zw, it is specially:<mrow> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <msub> <mi>x</mi> <mi>c</mi> </msub> </mtd> </mtr> <mtr> <mtd> <msub> <mi>y</mi> <mi>c</mi> </msub> </mtd> </mtr> <mtr> <mtd> <msub> <mi>z</mi> <mi>c</mi> </msub> </mtd> </mtr> <mtr> <mtd> <mn>1</mn> </mtd> </mtr> </mtable> </mfenced> <mo>=</mo> <mi>M</mi> <mfenced open = "[" close = "]"> <mtable> <mtr> <mtd> <msub> <mi>x</mi> <mi>w</mi> </msub> </mtd> </mtr> <mtr> <mtd> <msub> <mi>y</mi> <mi>w</mi> </msub> </mtd> </mtr> <mtr> <mtd> <msub> <mi>z</mi> <mi>w</mi> </msub> </mtd> </mtr> <mtr> <mtd> <mn>1</mn> </mtd> </mtr> </mtable> </mfenced> </mrow>In formula, matrix M represents camera to the transfer matrix of world coordinate system origin.
- 5. the tow-armed robot hand eye coordination method according to claim 1 based on multi-vision visual, it is characterised in that step Three-dimensional information based on target object in 4, control machinery arm are captured, and are completed the crawl to target object and are concretely comprised the following steps:Step 4-1, according to the three-dimensional coordinate information of the target object of acquisition, control to the minimum mechanical arm of target object distance Row crawl;Step 4-2, binocular camera captured in real-time target object, the new three-dimensional coordinate information of target object is obtained;Step 4-3, repeat step 4-1, step 4-2, until mechanical arm grabs target object, step 5 is carried out.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710802484.5A CN107471218B (en) | 2017-09-07 | 2017-09-07 | Binocular vision-based hand-eye coordination method for double-arm robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710802484.5A CN107471218B (en) | 2017-09-07 | 2017-09-07 | Binocular vision-based hand-eye coordination method for double-arm robot |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107471218A true CN107471218A (en) | 2017-12-15 |
CN107471218B CN107471218B (en) | 2020-09-11 |
Family
ID=60583694
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710802484.5A Active CN107471218B (en) | 2017-09-07 | 2017-09-07 | Binocular vision-based hand-eye coordination method for double-arm robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107471218B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109129483A (en) * | 2018-08-31 | 2019-01-04 | 厦门理工学院 | A kind of method, apparatus and robot based on multi-robot Cooperation under cloud platform |
CN109341718A (en) * | 2018-09-27 | 2019-02-15 | 北京伟景智能科技有限公司 | Scaling method and device based on multi-vision visual |
CN109986541A (en) * | 2019-05-06 | 2019-07-09 | 深圳市恒晟智能技术有限公司 | Manipulator |
CN110340901A (en) * | 2019-06-28 | 2019-10-18 | 深圳盈天下视觉科技有限公司 | A kind of control method, control device and terminal device |
CN110605714A (en) * | 2019-08-06 | 2019-12-24 | 华中科技大学 | Hand-eye coordination grabbing method based on human eye fixation point |
CN110640748A (en) * | 2019-11-07 | 2020-01-03 | 南京工程学院 | Binocular vision-based coordinated control method for double-arm robot |
CN110825088A (en) * | 2019-11-29 | 2020-02-21 | 燕山大学 | Multi-view vision guiding ship body cleaning robot system and cleaning method |
CN111340878A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Image processing method and device |
CN111823223A (en) * | 2019-08-19 | 2020-10-27 | 北京伟景智能科技有限公司 | Robot arm grabbing control system and method based on intelligent stereoscopic vision |
CN111932448A (en) * | 2020-09-09 | 2020-11-13 | 南昌虚拟现实研究院股份有限公司 | Data processing method, device, storage medium and equipment |
CN112060083A (en) * | 2020-08-20 | 2020-12-11 | 中国农业大学 | Binocular stereoscopic vision system for mechanical arm and measuring method thereof |
CN113804106A (en) * | 2021-08-18 | 2021-12-17 | 南京理工大学 | Double-arm cooperative assembly method based on twice calibration of vision |
CN114589698A (en) * | 2022-04-07 | 2022-06-07 | 北京信息科技大学 | Mechanical arm model-free real-time calibration method and device based on multi-target visual measurement and machine learning |
CN115008477A (en) * | 2022-08-09 | 2022-09-06 | 苏州华兴源创科技股份有限公司 | Manipulator movement compensation method, manipulator movement compensation device and computer-readable storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150217450A1 (en) * | 2014-02-05 | 2015-08-06 | Quanta Storage Inc. | Teaching device and method for robotic arm |
CN105157680A (en) * | 2015-08-28 | 2015-12-16 | 北京控制工程研究所 | Vision measurement system and method based on combination of global feature and local feature |
CN105537824A (en) * | 2016-01-27 | 2016-05-04 | 华南理工大学 | Automatic welding control method based on hand-eye coordination of mechanical arm |
CN106003036A (en) * | 2016-06-16 | 2016-10-12 | 哈尔滨工程大学 | Object grabbing and placing system based on binocular vision guidance |
CN106426186A (en) * | 2016-12-14 | 2017-02-22 | 国网江苏省电力公司常州供电公司 | Electrified operation robot autonomous operation method based on multi-sensor information fusion |
CN106695748A (en) * | 2016-12-09 | 2017-05-24 | 南京理工大学 | Hot-line robot with double mechanical arms |
-
2017
- 2017-09-07 CN CN201710802484.5A patent/CN107471218B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150217450A1 (en) * | 2014-02-05 | 2015-08-06 | Quanta Storage Inc. | Teaching device and method for robotic arm |
CN105157680A (en) * | 2015-08-28 | 2015-12-16 | 北京控制工程研究所 | Vision measurement system and method based on combination of global feature and local feature |
CN105537824A (en) * | 2016-01-27 | 2016-05-04 | 华南理工大学 | Automatic welding control method based on hand-eye coordination of mechanical arm |
CN106003036A (en) * | 2016-06-16 | 2016-10-12 | 哈尔滨工程大学 | Object grabbing and placing system based on binocular vision guidance |
CN106695748A (en) * | 2016-12-09 | 2017-05-24 | 南京理工大学 | Hot-line robot with double mechanical arms |
CN106426186A (en) * | 2016-12-14 | 2017-02-22 | 国网江苏省电力公司常州供电公司 | Electrified operation robot autonomous operation method based on multi-sensor information fusion |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109129483A (en) * | 2018-08-31 | 2019-01-04 | 厦门理工学院 | A kind of method, apparatus and robot based on multi-robot Cooperation under cloud platform |
CN109341718A (en) * | 2018-09-27 | 2019-02-15 | 北京伟景智能科技有限公司 | Scaling method and device based on multi-vision visual |
CN109341718B (en) * | 2018-09-27 | 2020-12-29 | 北京伟景智能科技有限公司 | Calibration method and device based on multi-view vision |
CN109986541A (en) * | 2019-05-06 | 2019-07-09 | 深圳市恒晟智能技术有限公司 | Manipulator |
CN110340901A (en) * | 2019-06-28 | 2019-10-18 | 深圳盈天下视觉科技有限公司 | A kind of control method, control device and terminal device |
CN110605714B (en) * | 2019-08-06 | 2021-08-03 | 华中科技大学 | Hand-eye coordination grabbing method based on human eye fixation point |
CN110605714A (en) * | 2019-08-06 | 2019-12-24 | 华中科技大学 | Hand-eye coordination grabbing method based on human eye fixation point |
CN111823223B (en) * | 2019-08-19 | 2023-12-29 | 北京伟景智能科技有限公司 | Robot arm grabbing control system and method based on intelligent stereoscopic vision |
CN111823223A (en) * | 2019-08-19 | 2020-10-27 | 北京伟景智能科技有限公司 | Robot arm grabbing control system and method based on intelligent stereoscopic vision |
CN110640748A (en) * | 2019-11-07 | 2020-01-03 | 南京工程学院 | Binocular vision-based coordinated control method for double-arm robot |
CN110825088A (en) * | 2019-11-29 | 2020-02-21 | 燕山大学 | Multi-view vision guiding ship body cleaning robot system and cleaning method |
CN110825088B (en) * | 2019-11-29 | 2021-10-01 | 燕山大学 | Multi-view vision guiding ship body cleaning robot system and cleaning method |
CN111340878A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Image processing method and device |
CN112060083A (en) * | 2020-08-20 | 2020-12-11 | 中国农业大学 | Binocular stereoscopic vision system for mechanical arm and measuring method thereof |
CN112060083B (en) * | 2020-08-20 | 2021-10-29 | 中国农业大学 | Binocular stereoscopic vision system for mechanical arm and measuring method thereof |
CN111932448B (en) * | 2020-09-09 | 2021-03-26 | 南昌虚拟现实研究院股份有限公司 | Data processing method, device, storage medium and equipment |
CN111932448A (en) * | 2020-09-09 | 2020-11-13 | 南昌虚拟现实研究院股份有限公司 | Data processing method, device, storage medium and equipment |
CN113804106A (en) * | 2021-08-18 | 2021-12-17 | 南京理工大学 | Double-arm cooperative assembly method based on twice calibration of vision |
CN114589698A (en) * | 2022-04-07 | 2022-06-07 | 北京信息科技大学 | Mechanical arm model-free real-time calibration method and device based on multi-target visual measurement and machine learning |
CN114589698B (en) * | 2022-04-07 | 2023-06-06 | 北京信息科技大学 | Model-free real-time calibration method and device for mechanical arm based on multi-target vision measurement and machine learning |
CN115008477A (en) * | 2022-08-09 | 2022-09-06 | 苏州华兴源创科技股份有限公司 | Manipulator movement compensation method, manipulator movement compensation device and computer-readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107471218B (en) | 2020-09-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107471218A (en) | A kind of tow-armed robot hand eye coordination method based on multi-vision visual | |
CN110728715B (en) | Intelligent inspection robot camera angle self-adaptive adjustment method | |
CN108109174B (en) | Robot monocular guidance method and system for randomly sorting scattered parts | |
CN106041937B (en) | A kind of control method of the manipulator crawl control system based on binocular stereo vision | |
CN110815213B (en) | Part identification and assembly method and device based on multi-dimensional feature fusion | |
CN110751691B (en) | Automatic pipe fitting grabbing method based on binocular vision | |
CN104018850B (en) | Section of jurisdiction based on the duct piece assembling machine of binocular vision positions and grasping system | |
US11100671B2 (en) | Image generation apparatus, image generation system, image generation method, and image generation program | |
CN108399639A (en) | Fast automatic crawl based on deep learning and arrangement method | |
CN107590835A (en) | Mechanical arm tool quick change vision positioning system and localization method under a kind of nuclear environment | |
CN103971375B (en) | A kind of panorama based on image mosaic stares camera space scaling method | |
CN110211180A (en) | A kind of autonomous grasping means of mechanical arm based on deep learning | |
CN108648237A (en) | A kind of space-location method of view-based access control model | |
CN104552341B (en) | Mobile industrial robot single-point various visual angles pocket watch position and attitude error detection method | |
CN106530276A (en) | Manipulator positioning method and system for grabbing of non-standard component | |
CN109739239A (en) | A kind of planing method of the uninterrupted Meter recognition for crusing robot | |
CN109459984A (en) | A kind of positioning grasping system and its application method based on three-dimensional point cloud | |
CN108154536A (en) | The camera calibration method of two dimensional surface iteration | |
CN108839035A (en) | A method of it takes and borrows books | |
CN109472778B (en) | Appearance detection method for towering structure based on unmanned aerial vehicle | |
CN107092905A (en) | A kind of instrument localization method to be identified of electric inspection process robot | |
CN106846385B (en) | Multi-sensing remote sensing image matching method, device and system based on unmanned aerial vehicle | |
CN108470165A (en) | A kind of picking robot fruit vision collaboratively searching method | |
CN110514114A (en) | A kind of small objects space position calibration method based on binocular vision | |
Muffert et al. | The estimation of spatial positions by using an omnidirectional camera system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |