CN107392962A - A kind of robot charging docking system and method based on pattern identification - Google Patents
A kind of robot charging docking system and method based on pattern identification Download PDFInfo
- Publication number
- CN107392962A CN107392962A CN201710691862.7A CN201710691862A CN107392962A CN 107392962 A CN107392962 A CN 107392962A CN 201710691862 A CN201710691862 A CN 201710691862A CN 107392962 A CN107392962 A CN 107392962A
- Authority
- CN
- China
- Prior art keywords
- robot
- charging
- charging pile
- pattern
- distance
- 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
- 238000003032 molecular docking Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title claims description 44
- 238000004364 calculation method Methods 0.000 claims abstract description 9
- 230000003287 optical effect Effects 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 238000013461 design Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
- B25J19/005—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators using batteries, e.g. as a back-up power source
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0007—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0014—Image feed-back for automatic industrial control, e.g. robot with camera
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/60—Rotation of a whole image or part thereof
- G06T3/608—Skewing or deskewing, e.g. by two-pass or three-pass rotation
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
Abstract
The invention provides a kind of robot charging docking system based on pattern identification, it includes robot and charging pile, charging identification icon is provided with the charging pile, camera and central control unit are provided with the robot, the central control unit, image for being photographed to the camera is handled, identify charging identification icon, the distance and angle of the robot and the charging pile are judged according to the charging identification icon, and control the robot to be moved to the charging pile.The robot charging docking system of the present invention can allow heavy-duty machines people height is autonomous, is reliably achieved automatic charging.The present invention also provides a kind of robot charging docking calculation based on pattern identification.
Description
Technical field
The present invention relates to robot field, more particularly to a kind of robot charging docking system and side based on pattern identification
Method.
Background technology
Automatic charging is one of critical function of heavy-duty machines people, and the design method of main flow has two kinds at present, and A is to be based on RF
Scope senses and the scheme of infrared communication technique, and B is the scheme based on laser radar technique.
In A modes, charging pile possesses RF emissivities, and robot produces sensing after certain distance, then by infrared
The communication technology is realized alignment and furthered, final to realize charging.The problem of this mode maximum, is that charging pile is found by robot
Blindness, duration needed for its process is uncontrollable, and practical application assists to enter actual induction scope by manpower more.B modes
Laser reflection characteristic body is provided with charging pile, and the laser radar with robot carries out 360 degree of scannings, to confirm charging pile position
And complete to be aligned.The drawbacks of which, is that laser radar and charging pile characteristic body must be with height, and this is for field with a varied topography
The more difficult application of institute, and it is difficult in adapt to the diverse designs demand of different machines people's trunk.
Therefore, how to allow heavy-duty machines people height is autonomous, is reliably achieved automatic charging, be robot relation technological researching
In the problem that requires study and solve.
The content of the invention
It is an object of the invention to provide a kind of robot charging docking system and method based on pattern identification, so as to real
Now allow heavy-duty machines people height is autonomous, is reliably achieved automatic charging.
In the embodiment of the present invention, there is provided a kind of robot charging docking system based on pattern identification, it includes machine
People and charging pile, charging identification icon is provided with the charging pile, camera is provided with the robot and center controls
Device, the central control unit, the image for being photographed to the camera are handled, and identify charging identification figure
Case, the distance and angle of the robot and the charging pile are judged according to the charging identification icon, and control the machine
Device people moves to the charging pile.
In the embodiment of the present invention, the first charge contact part is additionally provided with the robot and is close in described first and is filled
The first optical alignment part that contact part is set, charging identification icon, the second charge contact are provided with the charging pile
Part and be close in the second optical alignment part that the second charge contact part is set, the first optical alignment part with
The second optical alignment part is engaged, and realizes pair of the first charge contact part and the second charge contact part
Accurate and contact.
In the embodiment of the present invention, the first optical alignment part is infrared/laser pickoff, second optical alignment
Part is infrared/laser pickoff.
In the embodiment of the present invention, the charging identification icon includes three sub-patterns, and each sub-pattern includes being arranged at
The circular contour of periphery and the character graphics being arranged in circular contour, the central control unit identify described three respectively
Sub-pattern, and the length of side of the triangle formed according to the central points of three sub-patterns judges that the robot fills with described
The distance of electric stake.
In the embodiment of the present invention, what the central control unit was further formed according to the central point of three sub-patterns
The length of side of triangle judges the angle of the robot and the charging pile.
In the embodiment of the present invention, a kind of robot charging docking calculation based on pattern identification is additionally provided, it includes:
Image capturing procedure:Revolute simultaneously shoots picture by camera;
Image recognizing step:The image that the central control unit being arranged in the robot photographs to the camera is carried out
Image recognition, judge whether comprising the charging identification icon being arranged on charging pile, be then to enter robot moving step, otherwise
Return to image capturing procedure;
Robot moving step:The central control unit is sentenced according to the size and dimension feature of the charging identification icon photographed
Break and the distance and angle of the robot and the charging pile, control the robot to be moved to the charging pile, Zhi Daosuo
The distance for stating robot and the charging pile is less than the distance more than setting.
In the embodiment of the present invention, methods described also includes:
Charge alignment procedures:When the distance of the robot and the charging pile be less than more than setting apart from when, be arranged at institute
The the first optical alignment part stated in robot is engaged with the second optical alignment part being arranged on the charging pile,
Realize that the robot docks with charging pile charging.
In the embodiment of the present invention, the charging identification icon includes three sub-patterns, and each sub-pattern includes being arranged at
The circular contour of periphery and the character graphics being arranged in circular contour, the central control unit identify described three respectively
Sub-pattern, and according to the central point of three sub-patterns formed triangle the length of side come judge the robot with it is described
The angle of the distance of charging pile and the robot and the charging pile.
In the embodiment of the present invention, the detailed process of described image identification step is as follows:
Picture pre-processes:Picture is smoothed using gaussian pyramid method;
Binaryzation:Binary conversion treatment is carried out to picture using Canny operators;
Circular contour is searched for:To the image after binaryzation, the search of circular contour is carried out using Hough gradient method;
Filtering:Some non-compliant circular contours of radius are filtered out according to the radius of the circular contour searched out;
Figure in extraction circle:Being at 255 points as seed point to the brightness value in the circular contour after binaryzation uses unrestrained water to fill out
Method is filled, the shape of figure is filled out, so as to get the character graphics in circle;
Figure is ajusted:The character graphics is surrounded with a minimum area rectangle, so as to according to minimum area rectangle
Incline direction, ajusted correct position;
Binaryzation, normalization:Binaryzation is carried out to affine transformation content, and binaryzation content picture is cut to just to surround and justified
Character graphics in shape profile, it then will cut binaryzation picture and normalize to uniform height;
Graphic Pattern Matching:Uniform height picture is matched with standard database, best match data storehouse is found according to matching rate
Sample, so as to judge whether described image is charging identification icon.
In the embodiment of the present invention, the detailed process of the robot moving step is as follows:
When judge identification icon distance exceed setting apart from when, according to robot and the relative angle of charging pile, control machine
The charging face of device people faces pattern and approached as far as possible, until the charging face of robot is almost just facing to pattern, then towards figure
Case is advanced to be closing the distance, until distance is less than the distance of setting, then switches to the charging alignment procedures.
Compared with prior art, robot charging docking system and method for the invention based on pattern identification, are used
Pattern identification positions to charging pile, has very strong long range positioning and an ability that furthers;In addition, charging pile identification thing is figure
Case, it is safe using passive design;Pattern identification view-based access control model image recognition technology, the stability having had and anti-interference
Ability.
Brief description of the drawings
Fig. 1 is the structural representation of the charging docking system of the robot based on pattern identification of the present invention.
Fig. 2 is the flow chart of the charging docking calculation of the robot based on pattern identification of the present invention.
Fig. 3 is the particular flow sheet of the image recognizing step in Fig. 2.
In Fig. 4 Fig. 2 is the schematic diagram of charging alignment procedures.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
It is described in detail below in conjunction with realization of the specific embodiment to the present invention,
As shown in figure 1, the embodiment of the present invention provides a kind of robot charging docking system based on pattern identification, including robot
10 and charging pile 20, camera 11 and central control unit 12, the first charge contact part 13 are provided with the robot 10
With the first optical alignment part 14 for being close in the setting of the first charge contact part 13.The camera 11, first charges
The optical alignment part 14 of contact component 13 and first is arranged on the charging face of the robot 10.Set on the charging pile 20
There are charging identification icon 21, the second charge contact part 22 and be close in the second light that the second charge contact part 22 is set
Learn aligning parts 23.
The central control unit 12, the image for being photographed to the camera 11 are handled, and are identified described
Charge identification icon 21, according to it is described charging identification icon 21 judge the robot 10 and the charging pile 20 distance and
Angle, and control the robot 10 to be moved to the charging pile 20.When between the robot 10 and the charging pile 20
Distance be less than setting apart from when, the first charge contact part 13 and second charging are realized by optical alignment
The alignment positioning of contact portion part 22, i.e., by the first optical alignment part 14 and the second optical alignment part 23 to
Close, realize the alignment and contact of the first charge contact part 13 and the second charge contact part 22.
The first optical alignment part 14 is that the infrared/laser for being arranged at the both sides of the first charge contact part 13 connects
Device is received, the second optical alignment part 23 is the infrared/laser pick-off for being arranged at the both sides of the second charge contact part 22
Device.
As a kind of preferable implementation, the charging identification icon 21 includes three sub-patterns, each sub-pattern
Including the character graphics for being arranged at the circular contour of periphery and being arranged in circular contour.The circular contour of periphery, is easy to identify,
Along with the character graphics inside circular contour, the accuracy rate of identification can be improved.The central control unit 12 identifies respectively
Three sub-patterns, and the length of side of the triangle formed according to the central points of three sub-patterns judges the robot
10 with the distance of the charging pile 20.The center control fills 12 and put further to be formed according to the central point of three sub-patterns
The length of side of triangle judge the angle of the robot 10 and the charging pile 20.
As shown in Fig. 2 the embodiment of the present invention provides a kind of robot charging docking calculation based on pattern identification, it includes
Step S1-S4.It is specifically described below.
Step S1, image capturing procedure:Revolute simultaneously shoots picture by camera.
It should be noted that being provided with charging identification icon on charging pile, the robot passes through machine when needing charging
Device people rotates in all directions, and shoots photo, and the picture of shooting is identified in step s 2, to find charging pile
Position.
Step S2, image recognizing step:The central control unit being arranged in the robot is shot to the camera
The image arrived carries out image recognition, judges whether comprising the charging identification icon being arranged on charging pile, is then to enter step S3,
Otherwise return to step S1.
As shown in figure 3, in described image identification step, detailed process is as follows:
Picture pre-processes:In order to reduce influence of the noise to subsequent treatment in picture, picture is smoothed, picture is put down
Sliding processing method has a lot, a lot, gaussian pyramid method is used to picture in the present embodiment, first carries out Gauss gold word to picture
Tower reduces and then is amplified to original size again;
Binaryzation:Binary conversion treatment is carried out to picture using Canny operators in the present embodiment;
Circular contour is searched for:To the image after binaryzation, the search of circular contour is carried out, Hough gradient method is used in the present embodiment
Principle come carry out circle search;
Filtering:Come according to the radius of the circular contour searched out, because our icon sizes are fixed, so
In picture its radius size also within the specific limits, so as to filter out some incongruent circular contours of radius;
Character graphics in extraction circle:In the present embodiment, the charging identification icon includes three sub-patterns, each sub-pattern
All include the character graphics for being arranged at the circular contour of periphery and being arranged in circular contour.Circular icon is by monochromatic background colour
Formed with monochrome graphics in icon, and background color is dark colour.Therefore two are carried out to each circular contour region in original image
Value, circular background value can be 0, and figure is then 255 (assuming that the two-value of binaryzation is 0 and 255).After binaryzation
Circular contour in brightness value used for 255 points as seed point and overflow water fill method, the shape of figure is filled out, from
And get the character graphics in circle;
Figure is ajusted:Because the character graphics extracted in image has different direction of rotation, it is necessary to be rotated to correct
Direction to be contrasted with java standard library.Method for extraction character graphics profile, by profile with a minimum area rectangle by its
Surround, so as to the incline direction according to minimum area rectangle, ajusted correct position;
Binaryzation, normalization:Carrying out binaryzation to affine transformation content, (binaryzation uses adaptive Otsu ' s method herein
Binarization method), and the character graphics picture of binaryzation is cut to and just surrounds character graphics, it then will cut binary picture
Piece normalizes to uniform height;
Images match:Uniform height picture is matched with standard database, best match data storehouse is found according to matching rate
Sample.
It is 32 to draft the big low height of normalized binaryzation picture, is 1 per a line maximum matching rate, therefore total matching rate
Be up to 32, the threshold value of matching rate is set to 26 in the present embodiment, i.e., when a certain graphical information matching rate with java standard library is equal to or
During higher than 26, it is considered as and is effectively matched.And the character graphics after normalizing can occur 180 ° of situation of rotation, thus matching when
The picture of 180 ° of former normalization picture and rotation can be matched simultaneously by waiting.The present embodiment can be to the circular contour that is found in a two field picture
The image in region carries out above-mentioned normalization and than peering, and the result that will match to returns to main program.
Step S3, robot moving step:The central control unit according to photograph charging identification icon size
The distance and angle of the robot and the charging pile are judged with shape facility, controls the robot to the charging pile
It is mobile, until the distance of the robot and the charging pile is less than the distance more than setting.
Specifically, the process that the central control unit controls the robot to be moved to the charging pile is as follows:
Three sub- patterns composition equilateral triangles are placed, i.e. three sub- pattern center lines are an equilateral triangle, the length of side
It is fixed.After catching pattern and processing by camera, the length of side of form intermediate cam shape is can obtain, the distance of its length and machine is in
Existing positive correlation, thus estimates the distance between charging pile and robot.Specific conversion table is as follows:
In the measurement of relative angle, when the camera of robot captures the identification pattern on charging pile, because of relative angle
Difference, the length of side ratio that three sub-patterns form in camera image shows difference.Such as when facing pattern, three
The angular two hypotenuses length of side is almost equal;When both centers tilt, then the length of the hypotenuse of triangle two, which has, significantly differs
Cause.It is the angle that can determine whether machine and pattern in this approach, specific conversion table is as follows:
Drift angle | A left side is more than 45 | A left side is more than 25 | A left side is more than 15 | The right side is more than 15 | The right side is more than 25 | The right side is more than 45 | |
Left and right side ratio P | P>=1.136 | P>=1.111 | P>=1.075 | P= 1 | P<=0.930 | P<=0.900 | P<=0.880 |
In upper table, drift angle unit is degree, and angle is the angle with charging pile plane vertical line.Left and right side ratio P is triangle left side a
With the ratio on the right, P=a/b.
When judge the distance when the robot and the charging pile be more than more than setting apart from when(Set in the present embodiment
It is set to more than 0.7 meter), according to robot and the relative angle of charging pile, control machine people makes it face pattern as far as possible and approach.
For example, when judging pattern in the left front of plane where robot face pattern, first by robot flicker to and pattern
Place plane is nearly parallel, a segment distance of then going ahead, then goes to the right towards pattern, so circulation, until robot is several
Just facing to pattern, then advance towards pattern to be closing the distance, until distance is less than 0.7 meter, then switches to alignment and insert
Enter process.
Step S4, charge alignment procedures:When the distance of the robot and the charging pile is less than the distance more than setting
When, the first optical alignment part for being arranged in the robot and second optical alignment being arranged on the charging pile
Part is engaged, and realizes that the robot docks with charging pile charging.
Connect with it equipped with the two infrared/laser in left and right equipped with the two infrared/generating lasers in left and right, robot on charging pile
Receive device.When robot is close to charging pile, infrared/laser pickoff of robot can detect that charging pile emits red
Outside/laser signal, whether detect that infrared/laser signal makes it come control machine according to the infrared/laser pickoff in left and right two
It is directed at charging pile.
If two infrared remote receivers all detect infrared/laser signal, then it represents that robot is directed at charging pile, and robot will
Advance towards charging pile;If infrared/the laser pickoff on the only left side detects infrared/laser signal, then it represents that charging pile exists
The left side of robot, robot is by flicker, until two infrared remote receivers all detect signal;If only the right is red
Outside/laser pickoff detects infrared/laser signal, then it represents that charging pile on the right side of robot, robot by flicker,
Until two infrared/laser pickoffs all detect signal.Robot is so followed by the simultaneously adjustment direction that so constantly advances
Ring, until robot is aligned and inserts charging pile.
As described in Figure 4, robot is a with horizontal plane angle, for charging pile on the right side of it, robot only has the right side in location A
Side is infrared/and laser pickoff detects to obtain, robot flicker, and it is now b with horizontal sextant angle until both sides detect,
Robot marches forward.When robot advance L1 distance comes B location, robot only have right side it is infrared/laser pickoff inspection
Measure, robot flicker, be now c with horizontal plane angle, robot marches forward until both sides detect.Work as machine
When device people's advance L2 distance comes location of C, robot only has the infrared/laser pickoff in right side to detect to obtain, robot original place
Turn right, until both sides detect, now marched forward with plane-parallel, robot.Finally, robot advance L3 distance,
And insert charging pile.
In summary, compared with prior art, it is of the invention based on pattern identification robot charging docking system and
Method, charging pile is positioned using pattern identification, there is very strong long range positioning and the ability that furthers;In addition, charging pile
Identification thing is pattern, safe using passive design;Pattern identification view-based access control model image recognition technology, the stabilization having had
Property and antijamming capability.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (10)
1. a kind of robot charging docking system based on pattern identification, it is characterised in that described including robot and charging pile
Charging identification icon is provided with charging pile, camera and central control unit, the center control are provided with the robot
Device processed, the image for being photographed to the camera are handled, and identify charging identification icon, are known according to the charging
Other pattern judges the distance and angle of the robot and the charging pile, and controls the robot to be moved to the charging pile
It is dynamic.
2. the robot charging docking system based on pattern identification as claimed in claim 1, it is characterised in that the robot
On be additionally provided with the first charge contact part and be close in the first optical alignment part that the first charge contact part is set,
Charging identification icon, the second charge contact part is provided with the charging pile and is close in the second charge contact part and is set
The the second optical alignment part put, the first optical alignment part are engaged with the second optical alignment part, realize institute
State the alignment and contact of the first charge contact part and the second charge contact part.
3. the robot charging docking system based on pattern identification as claimed in claim 2, it is characterised in that first light
It is the infrared/laser pickoff for being arranged at the first charge contact part both sides to learn aligning parts, second optical alignment
Part is the infrared/laser pickoff for being arranged at the second charge contact part both sides.
4. the robot charging docking system based on pattern identification as claimed in claim 1, it is characterised in that the charging is known
Other pattern includes three sub-patterns, and each sub-pattern includes being arranged at the circular contour of periphery and is arranged in circular contour
Character graphics, the central control unit identify three sub-patterns respectively, and according to the center of three sub-patterns
The length of side for the triangle that point is formed judges the distance of the robot and the charging pile.
5. the robot charging docking system based on pattern identification as claimed in claim 4, it is characterised in that the center control
Device processed further judges the robot and institute according to the length of side of the triangle of the central point of three sub-patterns formation
State the angle of charging pile.
A kind of 6. robot charging docking calculation based on pattern identification, it is characterised in that including:
Image capturing procedure:Revolute simultaneously shoots picture by camera;
Image recognizing step:The image that the central control unit being arranged in the robot photographs to the camera is carried out
Image recognition, judge whether comprising the charging identification icon being arranged on charging pile, be then to enter robot moving step, otherwise
Return to image capturing procedure;
Robot moving step:The central control unit is sentenced according to the size and dimension feature of the charging identification icon photographed
Break and the distance and angle of the robot and the charging pile, control the robot to be moved to the charging pile, Zhi Daosuo
The distance for stating robot and the charging pile is less than the distance more than setting.
7. the robot charging docking calculation based on pattern identification as claimed in claim 6, it is characterised in that methods described is also
Including:
Charge alignment procedures:When the distance of the robot and the charging pile be less than more than setting apart from when, be arranged at institute
The the first optical alignment part stated in robot is engaged with the second optical alignment part being arranged on the charging pile,
Realize that the robot docks with charging pile charging.
8. the robot charging docking calculation based on pattern identification as claimed in claim 6, it is characterised in that the charging is known
Other pattern includes three sub-patterns, and each sub-pattern includes being arranged at the circular contour of periphery and is arranged in circular contour
Character graphics, the central control unit identify three sub-patterns respectively, and according to the center of three sub-patterns
The length of side for the triangle that point is formed judges that the distance of the robot and the charging pile and the robot are filled with described
The angle of electric stake.
9. the robot charging docking calculation based on pattern identification as claimed in claim 8, it is characterised in that described image is known
The detailed process of other step is as follows:
Picture pre-processes:Picture is smoothed using gaussian pyramid method;
Binaryzation:Binary conversion treatment is carried out to picture using Canny operators;
Circular contour is searched for:To the image after binaryzation, the search of circular contour is carried out using Hough gradient method;
Filtering:Some non-compliant circular contours of radius are filtered out according to the radius of the circular contour searched out;
Figure in extraction circle:Being at 255 points as seed point to the brightness value in the circular contour after binaryzation uses unrestrained water to fill out
Method is filled, the shape of figure is filled out, so as to get the character graphics in circle;
Figure is ajusted:The character graphics is surrounded with a minimum area rectangle, so as to according to minimum area rectangle
Incline direction, ajusted correct position;
Binaryzation, normalization:Binaryzation is carried out to affine transformation content, and binaryzation content picture is cut to just to surround and justified
Character graphics in shape profile, it then will cut binaryzation picture and normalize to uniform height;
Graphic Pattern Matching:Uniform height picture is matched with standard database, best match data storehouse is found according to matching rate
Sample, so as to judge whether described image is charging identification icon.
10. the robot charging docking calculation based on pattern identification as claimed in claim 9, it is characterised in that the machine
The detailed process of people's moving step is as follows:
When judge identification icon distance exceed setting apart from when, according to robot and the relative angle of charging pile, control machine
The charging face of device people faces pattern and approached as far as possible, until the charging face of robot is almost just facing to pattern, then towards figure
Case is advanced to be closing the distance, until distance is less than the distance of setting, then switches to the charging alignment procedures.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710691862.7A CN107392962A (en) | 2017-08-14 | 2017-08-14 | A kind of robot charging docking system and method based on pattern identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710691862.7A CN107392962A (en) | 2017-08-14 | 2017-08-14 | A kind of robot charging docking system and method based on pattern identification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107392962A true CN107392962A (en) | 2017-11-24 |
Family
ID=60354782
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710691862.7A Pending CN107392962A (en) | 2017-08-14 | 2017-08-14 | A kind of robot charging docking system and method based on pattern identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107392962A (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108303984A (en) * | 2018-02-27 | 2018-07-20 | 弗徕威智能机器人科技(上海)有限公司 | A kind of autonomous recharging method of mobile robot |
CN108596084A (en) * | 2018-04-23 | 2018-09-28 | 宁波Gqy视讯股份有限公司 | A kind of charging pile automatic identifying method and device |
CN109025175A (en) * | 2018-07-21 | 2018-12-18 | 东莞市史雷帝三维数控科技有限公司 | A kind of bio-robot household lower margin line apparatus |
CN109062207A (en) * | 2018-08-01 | 2018-12-21 | 深圳乐动机器人有限公司 | Localization method, device, robot and the storage medium of cradle |
CN109066861A (en) * | 2018-08-20 | 2018-12-21 | 四川超影科技有限公司 | Intelligent inspection robot charging controller method based on machine vision |
CN109669457A (en) * | 2018-12-26 | 2019-04-23 | 珠海市微半导体有限公司 | A kind of the robot recharging method and chip of view-based access control model mark |
CN109730590A (en) * | 2019-01-30 | 2019-05-10 | 深圳飞科机器人有限公司 | Clean robot and the method for clean robot auto-returned charging |
WO2019109230A1 (en) * | 2017-12-04 | 2019-06-13 | 深圳市沃特沃德股份有限公司 | Visual sweeping robot and recharging method therefor |
CN110334648A (en) * | 2019-07-02 | 2019-10-15 | 北京云迹科技有限公司 | Charging pile identifying system and method suitable for robot |
CN110543178A (en) * | 2019-09-30 | 2019-12-06 | 深圳市银星智能科技股份有限公司 | Robot recharging method and system, robot and charging station |
CN110801181A (en) * | 2019-11-07 | 2020-02-18 | 珠海格力电器股份有限公司 | Sweeping robot system, sweeping robot control method and sweeping robot control device |
WO2020034963A1 (en) * | 2018-08-15 | 2020-02-20 | 杭州萤石软件有限公司 | Charging device identification method, mobile robot and charging device identification system |
CN111605746A (en) * | 2020-05-09 | 2020-09-01 | 湖北隐冠轴业有限公司 | Automatic shipment packaging equipment of assembly line |
CN111987768A (en) * | 2020-08-19 | 2020-11-24 | 创新奇智(重庆)科技有限公司 | Automatic charging equipment and automatic charging method of equipment |
CN112124128A (en) * | 2020-09-24 | 2020-12-25 | 广东杜尼智能机器人工程技术研究中心有限公司 | Automatic alignment charging method depending on vision |
CN112190182A (en) * | 2020-09-24 | 2021-01-08 | 广东杜尼智能机器人工程技术研究中心有限公司 | Method for finishing cleaning task in cluster mode |
WO2021027665A1 (en) * | 2019-08-13 | 2021-02-18 | 北京海益同展信息科技有限公司 | Connection apparatus, mobile robot, and connection method for connection apparatus |
CN112405518A (en) * | 2019-08-23 | 2021-02-26 | 深圳拓邦股份有限公司 | Robot control method, robot and automatic backtracking system of robot |
CN112467828A (en) * | 2020-11-12 | 2021-03-09 | 上海姜歌机器人有限公司 | Robot charging method and device |
CN114364569A (en) * | 2019-05-31 | 2022-04-15 | Abb瑞士股份有限公司 | Device and method for charging an electric vehicle, and method for calibrating a device for charging an electric vehicle |
CN114485671A (en) * | 2022-01-24 | 2022-05-13 | 轮趣科技(东莞)有限公司 | Automatic turning method and device for mobile equipment |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6764373B1 (en) * | 1999-10-29 | 2004-07-20 | Sony Corporation | Charging system for mobile robot, method for searching charging station, mobile robot, connector, and electrical connection structure |
CN1899773A (en) * | 2005-07-22 | 2007-01-24 | Lg电子株式会社 | Moving object capable of recognizing image and moving-object directing system equipped with the same |
CN104298234A (en) * | 2013-11-13 | 2015-01-21 | 沈阳新松机器人自动化股份有限公司 | Dual-booting robot self-charging method |
US20150115876A1 (en) * | 2013-10-31 | 2015-04-30 | Lg Electronics Inc. | Mobile robot, charging apparatus for the mobile robot, and mobile robot system |
CN104792312A (en) * | 2014-01-20 | 2015-07-22 | 广东工业大学 | Indoor automatic transport vehicle positioning system with three fixed balls as visual marker |
CN105242670A (en) * | 2015-10-26 | 2016-01-13 | 深圳拓邦股份有限公司 | Robot having function of automatic return charging, system and corresponding method |
CN105549585A (en) * | 2015-12-07 | 2016-05-04 | 江苏木盟智能科技有限公司 | Robot navigation method and system |
CN105629971A (en) * | 2014-11-03 | 2016-06-01 | 贵州亿丰升华科技机器人有限公司 | Robot automatic charging system and control method therefor |
CN105785988A (en) * | 2015-01-14 | 2016-07-20 | Varram系统有限公司 | Driving robot, and charging station docking method for the driving robot |
CN106026288A (en) * | 2016-07-18 | 2016-10-12 | 旗瀚科技有限公司 | Robot automatic charging system and charging method thereof |
CN106153059A (en) * | 2016-07-01 | 2016-11-23 | 北京云迹科技有限公司 | The method of view-based access control model mark docking charging device |
-
2017
- 2017-08-14 CN CN201710691862.7A patent/CN107392962A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6764373B1 (en) * | 1999-10-29 | 2004-07-20 | Sony Corporation | Charging system for mobile robot, method for searching charging station, mobile robot, connector, and electrical connection structure |
CN1899773A (en) * | 2005-07-22 | 2007-01-24 | Lg电子株式会社 | Moving object capable of recognizing image and moving-object directing system equipped with the same |
US20150115876A1 (en) * | 2013-10-31 | 2015-04-30 | Lg Electronics Inc. | Mobile robot, charging apparatus for the mobile robot, and mobile robot system |
CN104298234A (en) * | 2013-11-13 | 2015-01-21 | 沈阳新松机器人自动化股份有限公司 | Dual-booting robot self-charging method |
CN104792312A (en) * | 2014-01-20 | 2015-07-22 | 广东工业大学 | Indoor automatic transport vehicle positioning system with three fixed balls as visual marker |
CN105629971A (en) * | 2014-11-03 | 2016-06-01 | 贵州亿丰升华科技机器人有限公司 | Robot automatic charging system and control method therefor |
CN105785988A (en) * | 2015-01-14 | 2016-07-20 | Varram系统有限公司 | Driving robot, and charging station docking method for the driving robot |
CN105242670A (en) * | 2015-10-26 | 2016-01-13 | 深圳拓邦股份有限公司 | Robot having function of automatic return charging, system and corresponding method |
CN105549585A (en) * | 2015-12-07 | 2016-05-04 | 江苏木盟智能科技有限公司 | Robot navigation method and system |
CN106153059A (en) * | 2016-07-01 | 2016-11-23 | 北京云迹科技有限公司 | The method of view-based access control model mark docking charging device |
CN106026288A (en) * | 2016-07-18 | 2016-10-12 | 旗瀚科技有限公司 | Robot automatic charging system and charging method thereof |
Cited By (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019109230A1 (en) * | 2017-12-04 | 2019-06-13 | 深圳市沃特沃德股份有限公司 | Visual sweeping robot and recharging method therefor |
CN108303984A (en) * | 2018-02-27 | 2018-07-20 | 弗徕威智能机器人科技(上海)有限公司 | A kind of autonomous recharging method of mobile robot |
CN108596084A (en) * | 2018-04-23 | 2018-09-28 | 宁波Gqy视讯股份有限公司 | A kind of charging pile automatic identifying method and device |
CN109025175A (en) * | 2018-07-21 | 2018-12-18 | 东莞市史雷帝三维数控科技有限公司 | A kind of bio-robot household lower margin line apparatus |
CN109025175B (en) * | 2018-07-21 | 2021-06-04 | 东莞市史雷帝三维数控科技有限公司 | Bionic robot domestic skirting device |
CN109062207A (en) * | 2018-08-01 | 2018-12-21 | 深圳乐动机器人有限公司 | Localization method, device, robot and the storage medium of cradle |
CN109062207B (en) * | 2018-08-01 | 2021-09-24 | 深圳乐动机器人有限公司 | Charging seat positioning method and device, robot and storage medium |
WO2020034963A1 (en) * | 2018-08-15 | 2020-02-20 | 杭州萤石软件有限公司 | Charging device identification method, mobile robot and charging device identification system |
US11715293B2 (en) | 2018-08-15 | 2023-08-01 | Hangzhou Ezviz Software Co., Ltd. | Methods for identifying charging device, mobile robots and systems for identifying charging device |
CN109066861A (en) * | 2018-08-20 | 2018-12-21 | 四川超影科技有限公司 | Intelligent inspection robot charging controller method based on machine vision |
CN109669457B (en) * | 2018-12-26 | 2021-08-24 | 珠海市一微半导体有限公司 | Robot recharging method and chip based on visual identification |
CN109669457A (en) * | 2018-12-26 | 2019-04-23 | 珠海市微半导体有限公司 | A kind of the robot recharging method and chip of view-based access control model mark |
CN109730590B (en) * | 2019-01-30 | 2023-08-25 | 深圳银星智能集团股份有限公司 | Cleaning robot and method for automatically returning and charging same |
CN109730590A (en) * | 2019-01-30 | 2019-05-10 | 深圳飞科机器人有限公司 | Clean robot and the method for clean robot auto-returned charging |
CN114364569B (en) * | 2019-05-31 | 2024-03-15 | Abb电动汽车有限责任公司 | Device and method for charging an electric vehicle, and method for calibrating a device for charging an electric vehicle |
CN114364569A (en) * | 2019-05-31 | 2022-04-15 | Abb瑞士股份有限公司 | Device and method for charging an electric vehicle, and method for calibrating a device for charging an electric vehicle |
CN110334648A (en) * | 2019-07-02 | 2019-10-15 | 北京云迹科技有限公司 | Charging pile identifying system and method suitable for robot |
CN110334648B (en) * | 2019-07-02 | 2022-01-11 | 北京云迹科技有限公司 | Charging pile identification system and method suitable for robot |
WO2021027665A1 (en) * | 2019-08-13 | 2021-02-18 | 北京海益同展信息科技有限公司 | Connection apparatus, mobile robot, and connection method for connection apparatus |
CN112405518A (en) * | 2019-08-23 | 2021-02-26 | 深圳拓邦股份有限公司 | Robot control method, robot and automatic backtracking system of robot |
CN110543178A (en) * | 2019-09-30 | 2019-12-06 | 深圳市银星智能科技股份有限公司 | Robot recharging method and system, robot and charging station |
CN110801181A (en) * | 2019-11-07 | 2020-02-18 | 珠海格力电器股份有限公司 | Sweeping robot system, sweeping robot control method and sweeping robot control device |
CN111605746A (en) * | 2020-05-09 | 2020-09-01 | 湖北隐冠轴业有限公司 | Automatic shipment packaging equipment of assembly line |
CN111987768B (en) * | 2020-08-19 | 2022-06-07 | 创新奇智(重庆)科技有限公司 | Automatic charging equipment and automatic charging method of equipment |
CN111987768A (en) * | 2020-08-19 | 2020-11-24 | 创新奇智(重庆)科技有限公司 | Automatic charging equipment and automatic charging method of equipment |
CN112190182B (en) * | 2020-09-24 | 2021-07-27 | 广东杜尼智能机器人工程技术研究中心有限公司 | Method for finishing cleaning task in cluster mode |
CN112190182A (en) * | 2020-09-24 | 2021-01-08 | 广东杜尼智能机器人工程技术研究中心有限公司 | Method for finishing cleaning task in cluster mode |
CN112124128A (en) * | 2020-09-24 | 2020-12-25 | 广东杜尼智能机器人工程技术研究中心有限公司 | Automatic alignment charging method depending on vision |
CN112467828A (en) * | 2020-11-12 | 2021-03-09 | 上海姜歌机器人有限公司 | Robot charging method and device |
CN114485671A (en) * | 2022-01-24 | 2022-05-13 | 轮趣科技(东莞)有限公司 | Automatic turning method and device for mobile equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107392962A (en) | A kind of robot charging docking system and method based on pattern identification | |
US11361469B2 (en) | Method and system for calibrating multiple cameras | |
WO2021114508A1 (en) | Visual navigation inspection and obstacle avoidance method for line inspection robot | |
US7376262B2 (en) | Method of three dimensional positioning using feature matching | |
CN106826815A (en) | Target object method of the identification with positioning based on coloured image and depth image | |
CN105701492B (en) | A kind of machine vision recognition system and its implementation | |
CN110450129B (en) | Carrying advancing method applied to carrying robot and carrying robot thereof | |
WO2015096507A1 (en) | Method for recognizing and locating building using constraint of mountain contour region | |
CN110569861B (en) | Image matching positioning method based on point feature and contour feature fusion | |
CN111738320B (en) | Shielded workpiece identification method based on template matching | |
CN104102909B (en) | Vehicle characteristics positioning and matching process based on lenticular information | |
CN109815822A (en) | Inspection figure components target identification method based on Generalized Hough Transform | |
CN111582118A (en) | Face recognition method and device | |
KR20140087485A (en) | Method of estimating the location of mobile robot using ray-tracing technique | |
CN112116637B (en) | Automatic power tower detection method and system based on unmanned aerial vehicle 3D laser scanning technology | |
KR102031946B1 (en) | System and method for surveillance of underside of vehicles | |
Han et al. | Target positioning method in binocular vision manipulator control based on improved canny operator | |
CN104715250A (en) | Cross laser detection method and device | |
CN111145254B (en) | Door valve blank positioning method based on binocular vision | |
CN107145820B (en) | Binocular positioning method based on HOG characteristics and FAST algorithm | |
Lijing et al. | A warped document image mosaicing method based on registration and TRS transform | |
CN111127542A (en) | Image-based non-cooperative target docking ring extraction method | |
CN110738098A (en) | target identification positioning and locking tracking method | |
Otepka et al. | Algorithm developments for automated off-line vision metrology | |
US11568683B2 (en) | Facial biometrics system and method using digital fingerprints |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171124 |
|
RJ01 | Rejection of invention patent application after publication |