CN107945233A - Vision sweeping robot and its recharging method - Google Patents
Vision sweeping robot and its recharging method Download PDFInfo
- Publication number
- CN107945233A CN107945233A CN201711260465.0A CN201711260465A CN107945233A CN 107945233 A CN107945233 A CN 107945233A CN 201711260465 A CN201711260465 A CN 201711260465A CN 107945233 A CN107945233 A CN 107945233A
- Authority
- CN
- China
- Prior art keywords
- sweeping robot
- image
- recharging
- seat
- ambient image
- 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
-
- 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
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1417—2D bar codes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Toxicology (AREA)
- Electromagnetism (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Manipulator (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
Present invention is disclosed a kind of vision sweeping robot and its recharging method, wherein recharging method includes step：Ambient image is gathered in cleaning process；When recharging by the ambient image of storage with it is default recharge an image compared with；Select the highest ambient image of similarity and return to the position for the ambient image of taking pictures；Alignment recharges seat insertion charging.The present invention make sweeping robot in charging fast searching to the position for recharging seat.
Description
Technical field
The present invention relates to sweeping robot field, especially relates to a kind of vision sweeping robot and its side of recharging
Method.
Background technology
With the continuous development of scientific technology, sweeping robot progresses into human lives and plays positive work
With.Power technology is the key technology of sweeping robot, is the guarantee for realizing the long-term autonomous work of machine.Since mobile power is deposited
In capacity limit, it is often necessary to which artificial charges for machine, and at present, the main thought for solving sweeper power issue is certainly
Main to return to charging, most common technological means is to return to cradle based on infrared signal guiding sweeper to carry out docking charging.
Although this method and system can realize that sweeper independently recharges electricity, infrared sensor launch angle is small, transmitting encoded signal
Distance it is short, somewhat block, infrared signal cannot shape completely penetrating, at this moment if cleaning environment using sweeper
Space is bigger, and sweeper side walks frontier inspection and survey infrared this time of guiding signal just to become very long, it is more likely that sweeper occurs
Pedestal can not be returned to, electricity exhausts the stranded situation in the way.
The content of the invention
The main object of the present invention allows sweeping robot fast to provide a kind of recharging method of vision sweeping robot
Fast accurately find recharges seat and charges.
The present invention proposes a kind of recharging method of vision sweeping robot, including step：
S1, the floor sweeper people shoot in cleaning process and store the ambient image of its surrounding environment；
S2, when recharging, the ambient image of the storage is compared with the image that recharges to prestore；
S3, when the similarity highest that the ambient image recharges an image with described, the robot is current according to its
Positional information and the highest environment scene image information of the similarity recharge a charge position described in being moved to；
S4, repeat the above steps S2, S3, until reaching preset condition.
Further, the preset condition is, the robot, which can identify, described recharges the identification marking set on seat；
It is described to be moved to the step of recharging charge position and include：
Identification marking on seat is recharged described in S31, identification, using the identification marking as reference, is moved to and described recharges seat
Charge position.
Further, the identification marking is Quick Response Code.
Further, the identification marking on seat is recharged described in the identification, using the identification marking as reference, is moved to institute
State and recharge a charge position and include：
S311, by the pixel of similar gradient information on identification marking be merged into line segment；
S312, by the line segment of merging connect and compose polygon；
S313, the visual sensor internal reference according to the vision sweeping robot, be calculated the sweeping robot with
The relative position relation of the identification marking；
S314, recharge a charge position according to being moved to the relative position relation.
Further, the identification marking set on seat is recharged described in the identification, it is mobile using the identification marking as reference
To including the step of recharging charge position：
Using charging electrode as symmetrically arranged two identification markings of symmetry axis on S315, the identification cradle.
Further, the ambient image that the floor sweeper people stores its surrounding environment in cleaning process includes：
S11, the characteristic point for extracting the ambient image and storage.
Further, the ambient image of the storage is included with a step of image is compared that recharge to prestore：
S21, using characteristic matching method by the characteristic point of the ambient image of the storage with it is described prestore recharge seat
The characteristic point of image is matched；
Count out in S22, calculating, generate matching value.
Further, the sweeping robot obtains its current location information and includes：
S32, the floor sweeper people sweep the floor in cleaning process using described in visual sensor or laser sensor acquisition
The posture at robot each moment and storage.
Further, the sweeping robot is according to its current location information and the highest environment scene figure of the similarity
A step of charge position is recharged as described in being moved to information includes：
S33, the mark sweeping robot current location, it is not labeled nearby to the sweeping robot current location
Position be extended, generate child node；
S34, to each child node Calculation Estimation functional value, and mark the child node of evaluation function value minimum；
If S35, the child node of the evaluation function value minimum are destination node, stop extension, institute is markd most
Boy's node connection generates path；
S36, be moved to according to this path and described recharge a charge position.
The present invention also proposes a kind of vision sweeping robot, including：
Taking module, shoots in cleaning process for the floor sweeper people and stores the ambient image of its surrounding environment；
Comparing module, during for recharging, the ambient image of the storage is compared with the image that recharges to prestore；
Mobile module, for recharge an image with described when the ambient image similarity highest when, the robot
A charge position is recharged according to being moved to its current location information and the highest environment scene image information of the similarity；
Condition module, for calling comparing module and mobile module, until reaching fore condition.
Further, the preset condition is, the robot, which can identify, described recharges the identification marking set on seat；
The mobile module includes：
Charhing unit, for identifying the identification marking recharged on seat, using the identification marking as reference, is moved to institute
State and recharge a charge position.
Further, the identification marking is Quick Response Code.
Further, the charhing unit includes：
Line segment subelement, for the pixel of similar gradient information on identification marking to be merged into line segment；
Polygon subelement, for the line segment of merging to be connected and composed polygon；
Computation subunit, according to the visual sensor internal reference of the vision sweeping robot, is calculated the sweeper
Device people and the relative position relation of the identification marking；
Subelement is recharged, for recharging a charge position described in being moved to according to the relative position relation.
Further, the charhing unit includes：
Charge subelement, for identifying on the cradle using charging electrode as symmetrically arranged two knowledges of symmetry axis
Do not identify.
Further, the taking module includes：
Feature dot element, for extracting characteristic point and the storage of the image.
Further, the comparing module includes：
Matching unit, for by the characteristic point of the ambient image of the storage and the feature for recharging an image to prestore
Point is matched；
Value cell is matched, for counting out in calculating, generates matching value.
Further, the mobile module further includes：
Storage unit, is obtained for the floor sweeper people in cleaning process using visual sensor or laser sensor
The posture at sweeping robot each moment and storage.
Further, the mobile module further includes：
Expanding element, marks the sweeping robot current location, does not have nearby to the sweeping robot current location
Labeled position is extended, and generates child node；
Value cell is evaluated, for each child node Calculation Estimation functional value, and marks the son of evaluation function value minimum
Node；
Path unit, if the child node for institute's evaluation values minimum is destination node, stops extension, by all marks
Minimum child node be coupled generation path；
Mobile unit, described a charge position is recharged for being moved to according to this path.
Compared with prior art, the beneficial effects of the invention are as follows：Sweeping robot is during sweeping the floor by gathering environment
Image, which can be found, recharges seat, improves the speed for finding and recharging seat.Utilize the charging electrode of being symmetricly set on recharged on seat
Two Quick Response Codes, make sweeping robot to recharge the electric signal of seat transmitting ready for insertion into recharging seat.
Brief description of the drawings
Fig. 1 is the step schematic diagram of the recharging method of the vision sweeping robot of one embodiment of the invention；
Fig. 2 is the step schematic diagram of the recharging method of the vision sweeping robot of one embodiment of the invention；
Fig. 3 is the step schematic diagram of the recharging method of the vision sweeping robot of one embodiment of the invention；
Fig. 4 is the step schematic diagram of the recharging method of the vision sweeping robot of one embodiment of the invention；
Fig. 5 is the step schematic diagram of the recharging method of the vision sweeping robot of one embodiment of the invention；
Fig. 6 is the step schematic diagram of the recharging method of the vision sweeping robot of one embodiment of the invention；
Fig. 7 is the structure diagram of the vision sweeping robot of one embodiment of the invention；
Fig. 8 is the structure diagram of the vision sweeping robot of one embodiment of the invention；
Fig. 9 is the structure diagram of the vision sweeping robot of one embodiment of the invention；
Figure 10 is the structure diagram of the vision sweeping robot of one embodiment of the invention；
Figure 11 is the structure diagram of the vision sweeping robot of one embodiment of the invention；
Figure 12 is the structure diagram of the vision sweeping robot of one embodiment of the invention；
Figure 13 is the structure diagram of the vision sweeping robot of one embodiment of the invention；
Figure 14 is the structure diagram of the vision sweeping robot of one embodiment of the invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Reference Fig. 1, proposes the recharging method of the vision sweeping robot of one embodiment of the invention, including step：
S1, the floor sweeper people shoot in cleaning process and store the ambient image of its surrounding environment；
S2, when recharging, the ambient image of the storage is compared with the image that recharges to prestore；
S3, when the similarity highest that the ambient image recharges an image with described, the robot is current according to its
Positional information and the highest environment scene image information of the similarity recharge a charge position described in being moved to；
S4, repeat the above steps S2 and S3, until reaching preset condition.
In the present embodiment, sweeping robot is not necessarily from recharging seat, it may be possible to user when starting to sweep the floor
Start what is cleaned after directly putting it into a certain room, it is also possible to be that sweeping robot is opened from some corner in room
Begin what is cleaned.When sweeping robot is cleaned according to track as defined in default logical algorithm, the vision of sweeping robot passes
Sensor, such as camera, also collection surrounding environment image, part sweeping robot surrounding have camera, can also be at this time at the same time
The camera of the surrounding of sweeping robot gathers ambient image at the same time, while ambient image is gathered, also records at this time
The position of ambient image is gathered, records the position of sweeping robot, is recorded by reference of the starting point of sweeping robot, such as
The displacement and direction, sweeping robot walked from starting point to the point of collection ambient image can be recorded to record in real time during cleaning
The movement locus of itself.The preset rules for gathering ambient image can be gathered once or often move at regular intervals
Dynamic a distance collection is once.Generation recharges order, can be that the electricity of sweeping robot is less than default threshold value, or connect
Receive generate after the order that the end that user sends cleans recharge order.When vision sweeping robot starts to recharge, it will gather
Ambient image and user be previously stored in sweeping robot or sweeping robot is photographed and stored in charge position
The image that recharges to get up compares, and finds out and recharge the highest ambient image of similarity of an image, and then passage path is planned
The position corresponding to the similarity highest ambient image is moved to, is repeated the above steps, until corresponding to the ambient image
The identification marking for recharging and being set on seat can be recognized at position.The identification mark that sweeping robot is then set with recharging on seat at this time
Know with reference to exactitude position is carried out, to facilitate the robot alignment charging electrode, charge.
It should be noted that the ambient image of the storage is compared with the image that recharges to prestore in the present invention
In, the image that recharges to prestore includes user and will recharge an image in advance and be stored in vision sweeping robot, also including vision
What sweeping robot shot and stored when recharging seat and putting charging recharges an image.In addition, the vision sweeping robot is returning
Update that it is stored when filling shift in position recharges an image.
With reference to Fig. 2, further, the preset condition is, the robot, which can identify, described recharges what is set on seat
Identification marking；It is described to be moved to the step of recharging charge position and include：
Identification marking on seat is recharged described in S31, identification, using the identification marking as reference, is moved to and described recharges seat
Charge position.
In the present embodiment, recognize after recharging seat, according to recharging the mark that is set on seat, when robot and recharge seat away from
From less than preset value, this judgement can be taken pictures according to the camera distance value measured or range sensor orientation
The judgement of the distance between seat is measured and recharges, using identification marking as the specific location that seat is recharged with reference to confirmation, sweeping robot
It is moved to the charge position for recharging seat.
Further, the identification marking is Quick Response Code.
In the present embodiment, Quick Response Code is chequered with black and white picture, and identification is high, is made simple.It is placed on as identification marking
Recharge on seat, facilitate sweeping robot to identify and be aligned.
With reference to Fig. 3, further, the identification marking on seat is recharged described in the identification, using the identification marking as reference,
Recharging a charge position described in being moved to includes：
S311, by the pixel of similar gradient information on identification marking be merged into line segment；
S312, by the line segment of merging connect and compose polygon；
S313, the visual sensor internal reference according to the vision sweeping robot, be calculated the sweeping robot with
The relative position relation of the identification marking；
S314, recharge a charge position according to being moved to the relative position relation.
In the present embodiment, the gradient direction and gradient magnitude of each pixel in the image of acquisition are calculated, then utilizes pixel
The similarity measurement of point gradient, the adjacent pixel with similar gradient information are merged into an entirety.Using similar
The method that figure is cut, the node of figure is a pixel, and the weight on side is the gradient similitude of two pixels (region).Then will
The line detected connects and composes polygon by the adjacent criterion in space, by the limitation to polygonal side length and to polygon institute structure
Into the number of angle point the quantity of polygon is limited, obtain quadrangle, the adjacent quadrangle in space is then merged into new
Quadrangle, finally obtains a big quadrangle for including many 0,1 coding (0,1 represents small quadrangle).Detecting four sides
After shape, by the coding to big quadrangle and type of coding comparing calculation distance set in advance, obtain more accurately examining
Survey target.Calculate homography matrix and outer ginseng：Homography matrix represents the 2D spot projections on Quick Response Code coordinate system and is sat to camera
Secondly what mark system was carried out converts, can pass through direct linear change method (DirectLinear Transform algorithm)
To try to achieve.Camera internal reference is represented with P, including camera focus, centre deviation.Outer ginseng is represented with E.Then homography matrix can be written as
Following form：
Wherein, Rij (i, j=0,1,2) represents rotation parameter, and Tk (k=x, y, z) represents translation parameters.
Since the row of spin matrix must be unit-sized, further according to Quick Response Code directional information corresponding with camera
(Quick Response Code is appeared in before camera), can obtain size and the direction of s.3rd row of spin matrix can pass through calculating
The crossed product of two pivot columns recovers, because rotating column matrix must be orthogonal.It is hereby achieved that Quick Response Code phase
For the relative position relation of camera.Then it is moved to according to relative position relation and recharges the charge position of seat and charge.
With reference to Fig. 4, further, the identification marking set on seat is recharged described in the identification, using the identification marking as
Reference, being moved to the step of recharging charge position includes：
Using charging electrode as symmetrically arranged two identification markings of symmetry axis on S315, the identification cradle.
In the present embodiment, on seat is recharged set two identification markings, two identification markings be located at sustained height and symmetrically
It is distributed in the both sides of charging electrode；Sweeping robot is moved on the axis of symmetry of two identification markings；Sweeper constantly adjusts
On the symmetry axis being located on floor in two identification markings, to be so directed at the precision higher of charging electrode.Alignment charging
After electrode, straight-line travelling is kept, then can smoothly be inserted into charging or wait recharging after seat is sent a telegram here and charge at once.
With reference to Fig. 5, further, the floor sweeper people stores the ambient image bag of its surrounding environment in cleaning process
Include：
S11, the characteristic point for extracting the ambient image and storage.
In the present embodiment, ambient image is subjected to feature extraction, can reduce the memory of image, when preservation more saves sky
Between, and be compared when compare characteristic point, the workload of comparison can be reduced.
With reference to Fig. 6, further, the ambient image of the storage is recharged into a step of image is compared with what is prestored
Including：
S21, using characteristic matching method by the characteristic point of the ambient image of the storage with it is described prestore recharge seat
The characteristic point of image is matched；
Count out in S22, calculating, generate matching value.
In the present embodiment, the characteristic point for the ambient image extraction that sweeping robot gathers during sweeping the floor recharges seat with this
Characteristic point be compared, the characteristic point of the ambient image of the collection of extraction is carried out with the default characteristic point for recharging seat one by one
Compare, matched using the method for characteristic matching；Interior point refers to the characteristic point for having one-to-one relationship in two images, two width
Image is more similar, and interior point is more, and the matching value of corresponding generation is higher.The highest ambient image of similarity is selected in subsequent,
That is the highest ambient image of matching value.Confirm that the object corresponding to the highest characteristic point of matching value is exactly to recharge seat.
Further, the sweeping robot obtains its current location information and includes：
S32, the floor sweeper people sweep the floor in cleaning process using described in visual sensor or laser sensor acquisition
The posture at robot each moment and storage.
In the present embodiment, visual sensor refers to obtain sweeping robot position on the move using the internal reference of camera
Put, obtain the posture of sweeping robot in real time, sweeping robot is recognized oneself location in the environment.Laser sensing
Device determines the posture of sweeping robot by detecting with the distance of surrounding objects, and the posture that each moment obtains is stored in and is swept the floor
In robot.
Further, the sweeping robot is according to its current location information and the highest environment scene figure of the similarity
A step of charge position is recharged as described in being moved to information includes：
S33, the mark sweeping robot current location, it is not labeled nearby to the sweeping robot current location
Position be extended, generate child node；
S34, to each child node Calculation Estimation functional value, and mark the child node of evaluation function value minimum；
If S35, the child node of the evaluation function value minimum are destination node, stop extension, institute is markd most
Boy's node connection generates path；
S36, be moved to according to this path and described recharge seat.
In the present embodiment, when sweeping robot returns to the position of collection ambient image, path planning is carried out, is calculated using A*
Method finds shortest path, is also A-Star algorithms, is to solve the most effective direct search method of shortest path in a kind of static road network,
Vertex ticks is carried out to sweeping robot initial position first, to being extended without labeled child node for it, child node
It is the position that sweeping robot gathers ambient image in cleaning process, then to each child node Calculation Estimation functional value,
Arranged by the size of evaluation of estimate, find out the node of evaluation of estimate minimum, and marked to it, if present node is exactly target
Node needs the position for having collected the image for recharging seat returned to, then stops search.Specifically calculation procedure is：
A) first determine whether that whether 8 nodes have barrier point around start node, exclude first if having, then from except barrier point
The node of Least-cost is solved in node in addition, and is added to the results list.
B) and then solution node, according to the evaluation function f (n) of A* algorithms=g (n)+h (n).Wherein g (n) is from starting point
The cost paid to present node n, h (n) are the cost estimations from present node n to destination node.Present node and starting
For node when in same horizontal line or vertical curve, the cost between each node is 10, i.e. g (n)=10；Present node is with rising
For beginning node when on same diagonal, the cost between each node is 14, i.e. g (n)=14.H (n)=(present node and mesh
Mark the ordinate lattice number of abscissa lattice number+between present node and destination node between node) * 10,8 sections on present node periphery
Point solves h (n) with destination node respectively.
C) 8 h (n) solved every time, compare size, and the node for selecting minimum is continued search for as start node.Directly
Just terminate to search for destination node is run into, solve optimal path.
After obtaining optimal path, returned to according to the path and recharge seat and charge.
In conclusion the recharging method of the vision sweeping robot of the present invention, makes sweeping robot lead to during sweeping the floor
Cross collection ambient image and can find and recharge seat, improve the speed for finding and recharging seat.Using recharging being symmetricly set on seat
Two Quick Response Codes of charging electrode, make sweeping robot to recharge the electric signal of seat transmitting ready for insertion into recharging seat.
With reference to Fig. 7, the present invention also proposes a kind of vision sweeping robot, including：
Taking module 1, shoots in cleaning process for the floor sweeper people and stores the ambient image of its surrounding environment；
Comparing module 2, during for recharging, the ambient image of the storage is compared with the image that recharges to prestore；
Mobile module 3, for recharge an image with described when the ambient image similarity highest when, the robot
A charge position is recharged according to being moved to its current location information and the highest environment scene image information of the similarity；
Condition module 4, for calling comparing module and mobile module, until reaching fore condition.
In the present embodiment, sweeping robot is not necessarily from seat is recharged as starting point, having can when starting to sweep the floor
Can start to clean after user directly puts it into a certain room, it is also possible to be some corner of sweeping robot from room
In set out start clean.When sweeping robot is cleaned according to track as defined in default logical algorithm, sweeping robot
Taking module 1 also gathers surrounding environment image at the same time, and part sweeping robot surrounding has camera, can also be to sweep the floor at this time
The camera of the surrounding of robot gathers ambient image at the same time, while ambient image is gathered, also records and gathers at this time
The position of ambient image, records the position of sweeping robot, using the starting point of sweeping robot as with reference to being recorded, such as can be with
Record the displacement and direction, sweeping robot walked from starting point to the point of collection environment picture and record itself in real time during cleaning
Movement locus.The preset rules of collection ambient image can gather once or often move one section at regular intervals
Distance collection is once.Generation recharges order, can be that the electricity of sweeping robot is less than default threshold value, or receive use
What is generated after the order that the end that family is sent cleans recharges order.When vision sweeping robot starts to recharge, comparing module 2 will adopt
The ambient image of collection and user be placed in advance in sweeping robot recharge the image of seat compared with, find out to recharging the similar of seat
Highest ambient image is spent, then 3 passage path of mobile module planning is moved to corresponding to the similarity highest ambient image
Position, repeats above-mentioned comparing module 2 and mobile module 3, until can be recognized back at the position corresponding to the ambient image
Fill the identification marking set on seat.The identification marking that sweeping robot is then set using recharging on seat at this time is accurate right with reference to carrying out
Position, facilitates the robot alignment charging electrode, charges.
It should be noted that the ambient image of the storage is compared with the image that recharges to prestore in the present invention
In, the image that recharges to prestore includes user and will recharge an image in advance and be stored in vision sweeping robot, also including vision
What sweeping robot shot and stored when recharging seat and putting charging recharges an image.In addition, the vision sweeping robot is returning
Update that it is stored when filling shift in position recharges an image.
With reference to Fig. 8, further, the preset condition is, the robot, which can identify, described recharges what is set on seat
Identification marking；The mobile module 3 further includes：
Charhing unit 31, for identify it is described recharge the identification marking set on seat, using the identification marking as reference, move
Move to described and recharge a charge position.
In the present embodiment, recognize after recharging seat, according to the mark recharged on seat, when robot and the distance that recharges seat are small
In preset value, this judgement can be taken pictures according to the camera distance value measured or range sensor orientation survey
With recharging the judgement of the distance between seat, charhing unit 31 is swept the floor using identification marking as the specific location that seat is recharged with reference to confirmation
Robot is moved to the charge position for recharging seat.
Further, the identification marking is Quick Response Code.
In the present embodiment, Quick Response Code is chequered with black and white picture, and identification is high, is made simple.It is placed on as identification marking
Recharge on seat, facilitate sweeping robot to identify and be aligned.
With reference to Fig. 9, further, the charhing unit 31 includes：
Line segment subelement 311, for the pixel of similar gradient information on identification marking to be merged into line segment；
Polygon subelement 312, for the line segment of merging to be connected and composed polygon；
Computation subunit 313, according to the visual sensor internal reference of the vision sweeping robot, is calculated described sweep the floor
The relative position relation of robot and the identification marking；
Subelement 314 is recharged, for recharging a charge position described in being moved to according to the relative position relation.
In the present embodiment, line segment subelement 313 calculates the gradient direction and gradient magnitude of each pixel in the image obtained,
Then utilize pixel gradient similarity measurement, have similar gradient information adjacent pixel be merged into one it is whole
Body.The method cut using similar figure, the node of figure is a pixel, and the weight on side is the gradient phase of two pixels (region)
Like property.Then the line detected is connected and composed polygon by polygon subelement 312 by the adjacent criterion in space, by polygon
The number of the limitation of the shape length of side and the angle point formed to polygon limits the quantity of polygon, obtains quadrangle, empty
Between adjacent quadrangle be then merged into new quadrangle, finally obtaining one, (0,1 represents four small sides comprising many 0,1 coding
Shape) big quadrangle.After quadrangle is detected, computation subunit 313 is by the coding to big quadrangle and presets
Type of coding comparing calculation distance, obtain more accurately detecting target.Calculate homography matrix and outer ginseng：Homography matrix
Represent the 2D spot projections on Quick Response Code coordinate system secondly to convert to what camera coordinate system was carried out, can be become by directly linear
Change method (DirectLinear Transform algorithm) is tried to achieve.Camera internal reference is represented with P, including camera focus, in
Heart deviation.Outer ginseng is represented with E.Then homography matrix can be written as following form：
Wherein, Rij (i, j=0,1,2) represents rotation parameter, and Tk (k=x, y, z) represents translation parameters.
Since the row of spin matrix must be unit-sized, further according to Quick Response Code directional information corresponding with camera
(Quick Response Code is appeared in before camera), can obtain size and the direction of s.3rd row of spin matrix can pass through calculating
The crossed product of two pivot columns recovers, because rotating column matrix must be orthogonal.It is hereby achieved that Quick Response Code phase
For the relative position relation of camera.Then recharge subelement 313 and control the sweeping robot according to relative position relation
It is moved to and recharges the charge position of seat and charge.
With reference to Figure 10, further, the charhing unit 31 includes：
Charge subelement 315, for identifying on the cradle using charging electrode as symmetrically arranged two institutes of symmetry axis
State identification marking.
In the present embodiment, on seat is recharged set two identification markings, two identification markings be located at sustained height and symmetrically
It is distributed in the both sides of charging electrode；Sweeping robot is moved on the axis of symmetry of two identification markings；Charging subelement 315 is controlled
Sweeping robot processed is constantly adjusted on the symmetry axis being located on floor in two identification markings, to be so directed at charging electrode
Precision higher.After being directed at charging electrode, straight-line travelling is kept, then can smoothly be inserted into charging.Or wait recharges seat and has
Charge at once after electricity.If the power supply failed for family, seat is recharged without electricity, charging electrode can also be inserted into, after waiting family to send a telegram here, recharge
Seat has electricity, and sweeping robot charges at once.
With reference to Figure 11, further, the taking module 1 includes：
Feature dot element 11, for extracting characteristic point and the storage of the image.
In the present embodiment, ambient image is carried out feature extraction by feature dot element 11, can reduce the memory of image, is preserved
Shi Gengjia saves space, and be compared when compares characteristic point, can reduce the workload of comparison.
With reference to Figure 12, further, the comparing module 2 includes：
Matching unit 21, for by the characteristic point of the ambient image of the storage and the spy for recharging an image to prestore
Sign point is matched；
Value cell 22 is matched, for counting out in calculating, generates matching value.
In the present embodiment, the characteristic point for the ambient image extraction that sweeping robot gathers during sweeping the floor recharges seat with this
Characteristic point be compared, matching unit 21 to the characteristic point of the ambient image of the collection of extraction one by one with the default seat that recharges
Characteristic point is compared, and is matched using the method for characteristic matching；Interior point refers to there is one-to-one relationship in two images
Characteristic point, two images are more similar, and interior point is more, and the matching value that matching value cell 22 generates is higher.It is subsequent select it is similar
Spend highest ambient image, the i.e. highest ambient image of matching value.Object corresponding to the confirmation highest characteristic point of matching value is just
It is to recharge seat.
With reference to Figure 13, further, the mobile module 3 further includes：
Storage unit 32, is obtained for the floor sweeper people in cleaning process using visual sensor or laser sensor
Take the posture at the sweeping robot each moment and storage.
In the present embodiment, visual sensor refers to obtain sweeping robot position on the move using the internal reference of camera
Put, obtain the posture of sweeping robot in real time, sweeping robot is recognized oneself location in the environment.Laser sensing
Device determines the posture of sweeping robot, the posture that storage unit 32 obtains each moment by detecting with the distance of surrounding objects
It is stored in sweeping robot.
With reference to Figure 14, further, the mobile module 3 further includes：
Expanding element 33, marks the sweeping robot current location, does not have nearby to the sweeping robot current location
There is labeled position to be extended, generate child node；
Value cell 34 is evaluated, for each child node Calculation Estimation functional value, and marks evaluation function value minimum
Child node；
Path unit 35, if the child node for institute's evaluation values minimum is destination node, stops extension, by all marks
The minimum child node of note is coupled generation path；
Mobile unit 36, described a charge position is recharged for being moved to according to this path.
In the present embodiment, when sweeping robot returns to the position of collection ambient image, path planning is carried out, is calculated using A*
Method finds shortest path, is also A-Star algorithms, is to solve the most effective direct search method of shortest path in a kind of static road network,
Expanding element 33 carries out vertex ticks to sweeping robot initial position first, to expanding without labeled child node for it
Exhibition, child node is the position that sweeping robot gathers ambient image in cleaning process, then evaluates value cell 34 to each
Child node Calculation Estimation functional value, is arranged by the size of evaluation of estimate, finds out the node of evaluation of estimate minimum, and mark to it
Note, needs the position for having collected the image for recharging seat that returns to, to stop search if present node is exactly destination node.
Specifically calculation procedure is：
A) first determine whether that whether 8 nodes have barrier point around start node, exclude first if having, then from except barrier point
The node of Least-cost is solved in node in addition, and is added to the results list.
B) and then solution node, according to the evaluation function f (n) of A* algorithms=g (n)+h (n).Wherein g (n) is from starting point
The cost paid to present node n, h (n) are the cost estimations from present node n to destination node.Present node and starting
For node when in same horizontal line or vertical curve, the cost between each node is 10, i.e. g (n)=10；Present node is with rising
For beginning node when on same diagonal, the cost between each node is 14, i.e. g (n)=14.H (n)=(present node and mesh
Mark the ordinate lattice number of abscissa lattice number+between present node and destination node between node) * 10,8 sections on present node periphery
Point solves h (n) with destination node respectively.
C) 8 h (n) solved every time, compare size, and the node for selecting minimum is continued search for as start node.Directly
Just terminate to search for destination node is run into, path unit 35 solves optimal path.After obtaining optimal path, mobile unit 36 according to
Returned to according to the path and recharge seat and charge.
In conclusion the vision sweeping robot of the present invention, makes sweeping robot during sweeping the floor by gathering environment
Image, which can be found, recharges seat, improves the speed for finding and recharging seat.Utilize the charging electrode of being symmetricly set on recharged on seat
Two Quick Response Codes, make sweeping robot to recharge the electric signal of seat transmitting ready for insertion into recharging seat.
The foregoing is merely the preferred embodiment of the present invention, is not intended to limit the scope of the invention, every utilization
The equivalent structure or equivalent flow shift that description of the invention and accompanying drawing content are made, it is related to be directly or indirectly used in other
Technical field, be included within the scope of the present invention.
Claims (10)
1. a kind of recharging method of vision sweeping robot, it is characterised in that including step：
S1, the floor sweeper people shoot in cleaning process and store the ambient image of its surrounding environment；
S2, when recharging, the ambient image of the storage is compared with the image that recharges to prestore；
S3, when the similarity highest that the ambient image recharges an image with described, the robot is according to its current location
Information and the highest environment scene image information of the similarity recharge a charge position described in being moved to；
S4, repeat the above steps S2, S3, until reaching preset condition.
2. the recharging method of vision sweeping robot as claimed in claim 1, it is characterised in that the preset condition is institute
State robot and can identify and described recharge the identification marking set on seat；It is described to be moved to the step of recharging charge position and wrap
Include：
The identification marking on seat is recharged described in S31, identification, using the identification marking as reference, the seat that recharges is moved to and charges
Position.
3. the recharging method of vision sweeping robot as claimed in claim 2, it is characterised in that recharge seat described in the identification
The identification marking of upper setting, using the identification marking as reference, being moved to the step of recharging charge position includes：
Using charging electrode as symmetrically arranged two identification markings of symmetry axis on S315, the identification cradle.
4. the recharging method of vision sweeping robot as claimed in claim 1, it is characterised in that the floor sweeper people is cleaning
During store the ambient image of its surrounding environment and include：
S11, the characteristic point for extracting the ambient image and storage.
5. the recharging method of vision sweeping robot as claimed in claim 4, it is characterised in that by the environment map of the storage
As including with a step of image is compared that recharge to prestore：
S21, using characteristic matching method by the characteristic point of the ambient image of the storage with it is described prestore recharge an image
Characteristic point matched；
Count out in S22, calculating, generate matching value.
A kind of 6. vision sweeping robot, it is characterised in that including：
Taking module, shoots in cleaning process for the floor sweeper people and stores the ambient image of its surrounding environment；
Comparing module, during for recharging, the ambient image of the storage is compared with the image that recharges to prestore；
Mobile module, for recharge an image with described when the ambient image similarity highest when, the robot according to
Its current location information and the highest environment scene image information of the similarity recharge a charge position described in being moved to；
Condition module, for calling comparing module and mobile module, until reaching fore condition.
7. vision sweeping robot as claimed in claim 6, it is characterised in that the preset condition is the robot energy
The identification marking set on seat is recharged described in enough identification；The mobile module further includes：
Charhing unit, for identifying the identification marking recharged on seat, using the identification marking as reference, is moved to described return
Fill a charge position.
8. vision sweeping robot as claimed in claim 7, it is characterised in that the charhing unit includes：
Charge subelement, is marked for identifying on the cradle by symmetrically arranged two identifications of symmetry axis of charging electrode
Know.
9. vision sweeping robot as claimed in claim 6, it is characterised in that the taking module includes：
Feature dot element, for extracting characteristic point and the storage of the image.
10. vision sweeping robot as claimed in claim 9, it is characterised in that the comparing module includes：
Matching unit, for the characteristic point of the ambient image of the storage and the feature for recharging an image to prestore to be clicked through
Row matching；
Value cell is matched, for counting out in calculating, generates matching value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711260465.0A CN107945233B (en) | 2017-12-04 | 2017-12-04 | Visual floor sweeping robot and refilling method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711260465.0A CN107945233B (en) | 2017-12-04 | 2017-12-04 | Visual floor sweeping robot and refilling method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107945233A true CN107945233A (en) | 2018-04-20 |
| CN107945233B CN107945233B (en) | 2020-11-24 |
Family
ID=61947555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711260465.0A Active CN107945233B (en) | 2017-12-04 | 2017-12-04 | Visual floor sweeping robot and refilling method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107945233B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108599303A (en) * | 2018-04-28 | 2018-09-28 | 广州视源电子科技股份有限公司 | Mobile charging method, device and system and computer readable storage medium |
| CN108614562A (en) * | 2018-06-05 | 2018-10-02 | 北京智行者科技有限公司 | A kind of cleaning method for optimizing route |
| CN108733060A (en) * | 2018-06-05 | 2018-11-02 | 北京智行者科技有限公司 | A kind of processing method of operation cartographic information |
| CN109512340A (en) * | 2018-12-06 | 2019-03-26 | 深圳飞科机器人有限公司 | A kind of control method and relevant device of clean robot |
| CN109623816A (en) * | 2018-12-19 | 2019-04-16 | 中新智擎科技有限公司 | A kind of robot recharging method, device, storage medium and robot |
| 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 |
| 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 |
| CN110032196A (en) * | 2019-05-06 | 2019-07-19 | 北京云迹科技有限公司 | A kind of robot recharging method and device |
| CN110301866A (en) * | 2019-08-01 | 2019-10-08 | 商洛市虎之翼科技有限公司 | Collect the device and its operating method of rubbish |
| CN110378285A (en) * | 2019-07-18 | 2019-10-25 | 北京小狗智能机器人技术有限公司 | A kind of recognition methods of cradle, device, robot and storage medium |
| CN110597265A (en) * | 2019-09-25 | 2019-12-20 | 深圳巴诺机器人有限公司 | Recharging method and device for sweeping robot |
| CN110632915A (en) * | 2018-06-21 | 2019-12-31 | 科沃斯机器人股份有限公司 | Robot recharging path planning method, robot and charging system |
| US10585437B1 (en) | 2018-09-25 | 2020-03-10 | NextVPU (Shanghai) Co., Ltd. | Auto-recharging of robot |
| CN111753580A (en) * | 2019-03-27 | 2020-10-09 | 北京外号信息技术有限公司 | Identification method of optical communication device and corresponding electronic equipment |
| CN113138596A (en) * | 2021-03-31 | 2021-07-20 | 深圳市优必选科技股份有限公司 | Robot automatic charging method, system, terminal device and storage medium |
| CN117137374A (en) * | 2023-10-27 | 2023-12-01 | 张家港极客嘉智能科技研发有限公司 | Sweeping robot recharging method based on computer vision |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1853552A (en) * | 2005-04-20 | 2006-11-01 | Lg电子株式会社 | Cleaning robot having auto-return function to charching-stand and method using the same |
| KR20080017521A (en) * | 2006-08-21 | 2008-02-27 | 문철홍 | Method for multiple movement body tracing movement using of difference image |
| CN102545275A (en) * | 2010-12-07 | 2012-07-04 | 上海新世纪机器人有限公司 | Robot automatic charging device and robot automatic charging method |
| CN102866706A (en) * | 2012-09-13 | 2013-01-09 | 深圳市银星智能科技股份有限公司 | Cleaning robot adopting smart phone navigation and navigation cleaning method thereof |
| 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 |
| CN106803261A (en) * | 2015-11-20 | 2017-06-06 | 沈阳新松机器人自动化股份有限公司 | robot relative pose estimation method |
| CN106826821A (en) * | 2017-01-16 | 2017-06-13 | 深圳前海勇艺达机器人有限公司 | The method and system that robot auto-returned based on image vision guiding charges |
| CN106980320A (en) * | 2017-05-18 | 2017-07-25 | 上海思岚科技有限公司 | Robot charging method and device |
-
2017
- 2017-12-04 CN CN201711260465.0A patent/CN107945233B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1853552A (en) * | 2005-04-20 | 2006-11-01 | Lg电子株式会社 | Cleaning robot having auto-return function to charching-stand and method using the same |
| KR20080017521A (en) * | 2006-08-21 | 2008-02-27 | 문철홍 | Method for multiple movement body tracing movement using of difference image |
| CN102545275A (en) * | 2010-12-07 | 2012-07-04 | 上海新世纪机器人有限公司 | Robot automatic charging device and robot automatic charging method |
| CN102866706A (en) * | 2012-09-13 | 2013-01-09 | 深圳市银星智能科技股份有限公司 | Cleaning robot adopting smart phone navigation and navigation cleaning method thereof |
| 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 |
| CN106803261A (en) * | 2015-11-20 | 2017-06-06 | 沈阳新松机器人自动化股份有限公司 | robot relative pose estimation method |
| CN106826821A (en) * | 2017-01-16 | 2017-06-13 | 深圳前海勇艺达机器人有限公司 | The method and system that robot auto-returned based on image vision guiding charges |
| CN106980320A (en) * | 2017-05-18 | 2017-07-25 | 上海思岚科技有限公司 | Robot charging method and device |
Non-Patent Citations (1)
| Title |
|---|
| 王建元 等: "基于图像识别的移动机器人自动完成充电", 《电测与仪表》 * |
Cited By (23)
| 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 |
| CN108599303A (en) * | 2018-04-28 | 2018-09-28 | 广州视源电子科技股份有限公司 | Mobile charging method, device and system and computer readable storage medium |
| CN108614562A (en) * | 2018-06-05 | 2018-10-02 | 北京智行者科技有限公司 | A kind of cleaning method for optimizing route |
| CN108733060A (en) * | 2018-06-05 | 2018-11-02 | 北京智行者科技有限公司 | A kind of processing method of operation cartographic information |
| CN108614562B (en) * | 2018-06-05 | 2021-05-07 | 北京智行者科技有限公司 | Cleaning path optimization method |
| CN110632915A (en) * | 2018-06-21 | 2019-12-31 | 科沃斯机器人股份有限公司 | Robot recharging path planning method, robot and charging system |
| WO2020062835A1 (en) * | 2018-09-25 | 2020-04-02 | 上海肇观电子科技有限公司 | Robot and automatic recharging method and system therefor, electronic device and storage medium |
| US10585437B1 (en) | 2018-09-25 | 2020-03-10 | NextVPU (Shanghai) Co., Ltd. | Auto-recharging of robot |
| CN109512340A (en) * | 2018-12-06 | 2019-03-26 | 深圳飞科机器人有限公司 | A kind of control method and relevant device of clean robot |
| CN109512340B (en) * | 2018-12-06 | 2021-05-25 | 深圳飞科机器人有限公司 | Control method of cleaning robot and related equipment |
| CN109623816A (en) * | 2018-12-19 | 2019-04-16 | 中新智擎科技有限公司 | A kind of robot recharging method, device, storage medium and robot |
| 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 |
| 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 |
| CN111753580A (en) * | 2019-03-27 | 2020-10-09 | 北京外号信息技术有限公司 | Identification method of optical communication device and corresponding electronic equipment |
| CN110032196A (en) * | 2019-05-06 | 2019-07-19 | 北京云迹科技有限公司 | A kind of robot recharging method and device |
| CN110032196B (en) * | 2019-05-06 | 2022-03-29 | 北京云迹科技股份有限公司 | Robot recharging method and device |
| CN110378285A (en) * | 2019-07-18 | 2019-10-25 | 北京小狗智能机器人技术有限公司 | A kind of recognition methods of cradle, device, robot and storage medium |
| CN110301866A (en) * | 2019-08-01 | 2019-10-08 | 商洛市虎之翼科技有限公司 | Collect the device and its operating method of rubbish |
| CN110301866B (en) * | 2019-08-01 | 2023-07-21 | 商洛市虎之翼科技有限公司 | Device for collecting refuse and method for operating the same |
| CN110597265A (en) * | 2019-09-25 | 2019-12-20 | 深圳巴诺机器人有限公司 | Recharging method and device for sweeping robot |
| CN113138596A (en) * | 2021-03-31 | 2021-07-20 | 深圳市优必选科技股份有限公司 | Robot automatic charging method, system, terminal device and storage medium |
| CN117137374A (en) * | 2023-10-27 | 2023-12-01 | 张家港极客嘉智能科技研发有限公司 | Sweeping robot recharging method based on computer vision |
| CN117137374B (en) * | 2023-10-27 | 2024-01-26 | 张家港极客嘉智能科技研发有限公司 | Sweeping robot recharging method based on computer vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107945233B (en) | 2020-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107945233A (en) | Vision sweeping robot and its recharging method | |
| CN106940186B (en) | A kind of robot autonomous localization and navigation methods and systems | |
| CN205458451U (en) | Robot | |
| CN105990876B (en) | Charging pile, identification method and device thereof and automatic cleaning equipment | |
| CN109431381A (en) | Localization method and device, electronic equipment, the storage medium of robot | |
| KR101950558B1 (en) | Pose estimation apparatus and vacuum cleaner system | |
| CN107564012A (en) | Towards the augmented reality method and device of circumstances not known | |
| JP2019523496A (en) | Estimate dimensions of enclosed space using multi-directional camera | |
| Goncalves et al. | A visual front-end for simultaneous localization and mapping | |
| CN105700525B (en) | Method is built based on Kinect sensor depth map robot working environment uncertainty map | |
| CN109901590A (en) | Desktop machine people's recharges control method | |
| CN110515383A (en) | The method and mobile robot of recharging | |
| CN109416843A (en) | Real-time height mapping | |
| CN110477825A (en) | Clean robot, recharging method, system and readable storage medium storing program for executing | |
| CN207488823U (en) | A kind of mobile electronic device | |
| CN107229274B (en) | Position indication method, terminal device, self-propelled device, and program | |
| Yue et al. | Fast 3D modeling in complex environments using a single Kinect sensor | |
| CN106846479B (en) | Three-dimensional visialization of tunnel system and method based on depth camera | |
| CN108459596A (en) | A kind of method in mobile electronic device and the mobile electronic device | |
| JP2017117386A (en) | Self-motion estimation system, control method and program of self-motion estimation system | |
| CN108225328A (en) | A kind of interior three dimensional data collection method | |
| Hertzberg et al. | Experiences in building a visual SLAM system from open source components | |
| CN107136649A (en) | A kind of three-dimensional foot type measuring device and implementation method based on automatic seeking board pattern | |
| Zhu et al. | Real-time global localization with a pre-built visual landmark database | |
| Gomez-Lahoz et al. | Recovering traditions in the digital era: the use of blimps for modelling the archaeological cultural heritage |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190906 Address after: Room 402, 4th floor, Kanghe Sheng Building, New Energy Innovation Industrial Park, No. 1 Chuangsheng Road, Nanshan District, Shenzhen City, Guangdong Province, 518000 Applicant after: Shenzhen Infinite Power Development Co., Ltd. Address before: 518000 B, block 1079, garden city digital garden, Nanhai Road, Shekou, Shenzhen, Guangdong, 503, Nanshan District 602, China Applicant before: SHENZHEN WOTE WODE CO., LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |