CN109171571A - Method for cleaning, device and the clean robot of rubbish - Google Patents
Method for cleaning, device and the clean robot of rubbish Download PDFInfo
- Publication number
- CN109171571A CN109171571A CN201811089245.0A CN201811089245A CN109171571A CN 109171571 A CN109171571 A CN 109171571A CN 201811089245 A CN201811089245 A CN 201811089245A CN 109171571 A CN109171571 A CN 109171571A
- Authority
- CN
- China
- Prior art keywords
- cleaning
- robot
- rubbish
- region
- clearance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/24—Floor-sweeping machines, motor-driven
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
- A47L11/4002—Installations of electric equipment
- A47L11/4008—Arrangements of switches, indicators or the like
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
- A47L2201/06—Control of the cleaning action for autonomous devices; Automatic detection of the surface condition before, during or after cleaning
Landscapes
- Electric Vacuum Cleaner (AREA)
Abstract
The invention discloses a kind of method for cleaning of rubbish, device and clean robots.Wherein, this method comprises: acquiring the image information in region for clearance;Image information is recognized based on identification model, obtain the area information in region for clearance, wherein, identification model is obtained using multi-group data by decision tree training, and every group of data in multi-group data include: image information and the corresponding area information of image information;Cleaning area is treated according to area information control robot to be cleared up.The present invention, which solves existing clean robot, there is technical issues that cleaning.
Description
Technical field
The present invention relates to field of intelligent control, in particular to the method for cleaning, device and cleaner of a kind of rubbish
Device people.
Background technique
With the fast development of computer technology, more stringent requirements are proposed for convenience of the people to life, wherein intelligence
The appearance of equipment is that people's lives bring convenience, for example, clean robot can help user to clean domestic hygiene, section automatically
Save time and the physical strength of user.However, existing clean robot mostly uses sensor to detect rubbish greatly, to prevent
Clean robot is collided with other furniture.However, under corner, bed, under sofa, carpet is inferior has shelter to block
The rubbish in region, clean robot are typically due to sensor and can not incude, and lead to cleaning dead angle occur.
There are problems that cleaning dead angle above-mentioned existing clean robot, not yet proposes effective solution side at present
Case.
Summary of the invention
The embodiment of the invention provides a kind of method for cleaning of rubbish, device and clean robots, existing at least to solve
With the presence of clean robot clean dead angle the technical issues of.
According to an aspect of an embodiment of the present invention, a kind of method for cleaning of rubbish is provided, comprising: acquire area for clearance
The image information in domain;Image information is recognized based on identification model, obtains the area information in region for clearance, wherein distinguish
Know model and obtained using multi-group data by decision tree training, every group of data in multi-group data include: image information
And the corresponding area information of image information;Cleaning area is treated according to area information control robot to be cleared up.
Further, the method for cleaning of rubbish further include: determine processing mode corresponding with area information, wherein processing
Mode includes at least one following: cleaning arm manner of cleaning up, reinforces manner of cleaning up, shelter cleaning side at sweep brush manner of cleaning up
Formula;Cleaning area is treated according to processing mode control robot to be cleared up.
Further, the method for cleaning of rubbish further include: in the case where area information includes rubbish position, in rubbish position
In the case where being set to the position that robot can not reach, control robot treats cleaning area progress using cleaning arm manner of cleaning up
Cleaning.
Further, the method for cleaning of rubbish further include: include at least rubbish type and rubbish position in area information
In the case of, in the case where rubbish position is robot accessible position and rubbish type is specified type, control machine
People treats cleaning area using sweep brush manner of cleaning up and clears up.
Further, the method for cleaning of rubbish further include: in the case where area information includes at least degree of fouling, dirty
In the case that dirty degree reaches default degree of fouling, control robot treats cleaning area progress clearly using manner of cleaning up is reinforced
Reason, wherein reinforce manner of cleaning up including at least one of following: water horning, drying cleaning.
Further, the method for cleaning of rubbish further include: in the case where area information includes at least coverage extent, hiding
In the case that gear degree is greater than default coverage extent, control robot using shelter manner of cleaning up to shelter block to clear
Reason region is cleared up.
Further, the method for cleaning of rubbish further include: the cleaning road conditions of robot are identified according to image information;According to clear
It is mobile that line of reasoning condition controls robot.
According to another aspect of an embodiment of the present invention, a kind of clean robot is additionally provided, comprising: image acquisition units,
For acquiring the image information in region for clearance;Central processing unit, including image processing unit, wherein image processing unit is used
Image information is recognized in based on identification model, obtains the area information in region for clearance, and control according to area information
Robot treats cleaning area and is cleared up, wherein identification model is obtained using multi-group data by decision tree training, more
Every group of data in group data include: image information and the corresponding area information of image information.
Further, area information includes one of following: rubbish position, rubbish type, degree of fouling, coverage extent.
Further, central processing unit further include: sweep brush is robot accessible position in rubbish position, and
In the case that rubbish type is rubbish clast, treats cleaning area and cleared up;Cleaning arm, for being robot in rubbish position
In the case where the position that can not be reached, treats cleaning area and cleared up.
Further, image processing unit is also used to identify the cleaning road conditions of robot according to image information, according to cleaning
It is mobile that road conditions control robot.
According to another aspect of an embodiment of the present invention, a kind of cleaning plant of rubbish is additionally provided, comprising: acquisition module,
For acquiring the image information in region for clearance;Module is recognized, for being recognized based on identification model to image information, is obtained
The area information in region for clearance, wherein identification model is obtained using multi-group data by decision tree training, multi-group data
In every group of data include: image information and the corresponding area information of image information;Cleaning modul, for being believed according to region
Breath control robot treats cleaning area and is cleared up.
According to another aspect of an embodiment of the present invention, a kind of storage medium is additionally provided, which includes storage
Program, wherein the method for cleaning of program execution rubbish.
According to another aspect of an embodiment of the present invention, a kind of processor is additionally provided, which is used to run program,
In, the method for cleaning of rubbish is executed when program is run.
In embodiments of the present invention, by the way of image identification rubbish, the image information for acquiring region for clearance it
Afterwards, robot recognizes image information based on identification model, the area information in region for clearance is obtained, then further according to area
Domain information control robot treats cleaning area and is cleared up, wherein identification model is to be instructed using multi-group data by decision tree
It gets, every group of data in multi-group data include: image information and the corresponding area information of image information.
In above process, by recognizing to image information, the rubbish being blocked by obstructions can be identified, to protect
Effective identification to all rubbish has been demonstrate,proved, and then the rubbish being blocked by obstructions has been cleared up, so as to avoid cleaning dead angle.
In addition, also can be identified the contents such as the type of rubbish, degree of fouling by image information, and then can be according to the rubbish picked out
The contents such as type, degree of fouling rubbish is cleared up using reasonable manner of cleaning up, so that realizing has rubbish
Imitate the technical effect of cleaning.
It can be seen that scheme provided herein can solve the technology that existing clean robot has cleaning dead angle
Problem.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is a kind of flow chart of the method for cleaning of rubbish according to an embodiment of the present invention;
Fig. 2 is a kind of training testing process of optional identification model according to an embodiment of the present invention;
Fig. 3 is a kind of structural schematic diagram of clean robot according to an embodiment of the present invention;And
Fig. 4 is a kind of structural schematic diagram of the cleaning plant of rubbish according to an embodiment of the present invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
Embodiment 1
According to embodiments of the present invention, a kind of embodiment of the method for cleaning of rubbish is provided, it should be noted that in attached drawing
Process the step of illustrating can execute in a computer system such as a set of computer executable instructions, although also,
Logical order is shown in flow charts, but in some cases, can be executed with the sequence for being different from herein it is shown or
The step of description.
Fig. 1 is the flow chart of the method for cleaning of rubbish according to an embodiment of the present invention, as shown in Figure 1, this method includes such as
Lower step:
Step S102 acquires the image information in region for clearance.
It, can also be with it should be noted that region for clearance can be the region (for example, on ground) that is not blocked by obstructions
For the region being blocked by obstructions, for example, under bed, the inferior region blocked by bed, sofa of sofa.In addition, clean robot can
The rubbish treated in cleaning area is cleared up, wherein clean robot can be but be not limited to sweeping robot, wipe window machine
Device people, wipe a table robot.
In addition it is also necessary to explanation, clean robot has image acquisition units, and image acquisition units can be acquired to clear
Manage the image information in region, wherein image acquisition units can be but be not limited to camera.
Step S104 recognizes image information based on identification model, obtains the area information in region for clearance,
In, identification model is obtained using multi-group data by decision tree training, and every group of data in multi-group data include: image
Information and the corresponding area information of image information.
It should be noted that clean robot further includes image processing unit, wherein image processing unit can believe image
Breath is recognized.In addition, the area information in region for clearance includes at least one following: rubbish position (example in step S104
Such as, on ground, under carpet), rubbish type (for example, dust, paper scrap, dirt), degree of fouling, coverage extent (for example, all hide
Gear, partial occlusion).
In a kind of optional scheme, Fig. 2 shows a kind of training testing process of optional identification model, can by Fig. 2
Know, after the image information for obtaining region for clearance, image processing unit passes through Gabor function first and extracts image information
Feature, and the feature extracted is pre-processed.Then with profound neural network model (the i.e. above-mentioned identification of fractal structure
Model) pretreated feature is trained, it obtains the corresponding area information of image information and image information and region is believed
The corresponding relationship of breath.For guarantee identification model can accurate recognition go out the area information in region for clearance, obtaining identification model
Later, identification model can also be tested, wherein the test process for recognizing model is similar with training process, no longer superfluous herein
It states.
In addition it is also necessary to explanation, identification model is trained using the picture of multiple types of floors deployment scenarios, and this is more
The attribute that the number of plies of task basic decision tree and the area information of training sample are included is (for example, rubbish type, degree of fouling
Deng) quantity it is consistent.In addition, step S104 can precisely be picked out by the identification model of multitask basic decision tree it is for clearance
The area information in region ensure that clean robot treats effective cleaning of cleaning area.
Step S106 treats cleaning area according to area information control robot and is cleared up.
It should be noted that the robot in step S106 is above-mentioned clean robot.In addition, for different areas
Domain information, clean robot is treated cleaning area using different processing modes and is cleared up, for example, under bed, under sofa
The region that equal clean robots are not easily accessible, clean robot can be used cleaning arm under bed, the inferior clean robot of sofa not
The region easily entered is cleared up, and region accessibility for robot, can directly adopt the mode of sweep brush to for clearance
Region is cleared up.
Based on scheme defined by above-mentioned steps S102 to step S106, it can know, using the side of image identification rubbish
Formula, after the image information for acquiring region for clearance, robot is based on identification model and recognizes to image information, obtain to
Then the area information of cleaning area is treated cleaning area further according to area information control robot and is cleared up, wherein identification
Model is obtained using multi-group data by decision tree training, every group of data in multi-group data include: image information with
And the corresponding area information of image information.
It is easily noted that, by recognizing to image information, can identify the rubbish being blocked by obstructions, thus
It ensure that effective identification to all rubbish, and then the rubbish being blocked by obstructions cleared up, it is dead so as to avoid cleaning
Angle.In addition, also can be identified the contents such as the type of rubbish, degree of fouling by image information, and then can be according to picking out
The contents such as type, the degree of fouling of rubbish clear up rubbish using reasonable manner of cleaning up, thus realize to rubbish into
The technical effect that row is effectively cleared up.
It can be seen that scheme provided herein can solve the technology that existing clean robot has cleaning dead angle
Problem.
In a kind of optional scheme, the image acquisition units in clean robot acquire primary figure every preset time
Picture, and acquired image is sent to image processing unit, image processing unit is based on identification model and recognizes to image,
Determine in front of clean robot whether there is barrier.In the case where determining has barrier in front of clean robot, at image
Reason unit further judges whether the barrier in front is rubbish, optionally, can be according to the shape, height, color etc. of barrier
Determine whether barrier is rubbish, for example, being highly less than 1cm, also, obstacle when the shape of barrier is irregular shape
The volume of object is less than preset vol (for example, 1 cubic centimetre), then can determine that barrier is rubbish.Further, barrier is being determined
Hindering object is the information of clean robot acquisition rubbish after rubbish, for example, rubbish type, degree of fouling, coverage extent etc., and
Determine that suitable manner of cleaning up clears up rubbish according to the information of rubbish.
Optionally, cleaning area is treated according to area information control robot to be cleared up, may include:
Step S1060 determines processing mode corresponding with area information, wherein processing mode includes at least one following:
Cleaning arm manner of cleaning up, reinforces manner of cleaning up, shelter manner of cleaning up at sweep brush manner of cleaning up;
Step S1062 treats cleaning area according to processing mode control robot and is cleared up.
It is machine in the case where area information includes rubbish position, and in rubbish position in a kind of optional scheme
In the case where the position that people can not reach, control robot treats cleaning area using cleaning arm manner of cleaning up and is cleared up.Its
In, cleaning arm is telescopic cleaning arm.When clean robot detects rubbish in clean robot in accessibility region
When, cleaning arm is hidden in the inside of clean robot.When clean robot detection rubbish is in the not accessibility area of clean robot
When in domain, for example, rubbish is located under bed or under sofa, the cleaning arm of clean robot is touched, and extend out to clean robot
In vitro, to clean the rubbish under bed or under sofa.
In another optional scheme, in the case where area information includes at least rubbish type and rubbish position, and
And in the case where rubbish position is robot accessible position and rubbish type is specified type, control robot is adopted
Cleaning area is treated with sweep brush manner of cleaning up to be cleared up.Wherein, the rubbish of specified type can be greater than pre- for rubbish quantity
If quantity, and garbage bulk is less than the rubbish of preset vol, for example, the rubbish clast such as swill, paper scrap, spitball.Specifically
, when clean robot moves on floor, detect that there are rubbish on the ground of front, and rubbish type is that rubbish is broken
Bits, then clean robot cleans the region by sweep brush.
It should be noted that clean robot can also be according to the degree of fouling of rubbish in scheme provided herein
To select different manner of cleaning up to clear up rubbish.Optionally, in the case where area information includes at least degree of fouling,
And in the case where degree of fouling reaches default degree of fouling, control robot treats cleaning area using manner of cleaning up is reinforced
It is cleared up, wherein reinforce manner of cleaning up including at least one of following: water horning, drying cleaning.
In a kind of optional scheme, clean robot may recognize that the degree of fouling of rubbish by recognizing model, and will
Obtained dirty program is compared with default degree of fouling, and the dirty grade of rubbish is determined according to comparison result.Wherein, rubbish
The dirty grade of rubbish can be divided into cleaning, dirtier, dirty, extremely dirty etc., and each dirty grade corresponds to different processing modes.For example,
On floor dust and be stained with greasy dirt it is more when, corresponding grade can be to be dirty, at this point, clean robot is using Water spraying wiper
Mode cleared up.In order to ground ponding and damp ground clear up, using after water horning, cleaning
Robot further using drying manner of cleaning up the ponding on ground is cleared up, with solve due to ponding etc. caused by two
Secondary cleaning problems.
It is big in coverage extent in the case where area information includes at least coverage extent in another optional scheme
In the case where default coverage extent, region for clearance that control robot blocks shelter using shelter manner of cleaning up into
Row cleaning.Optionally, when image processing unit picks out the rubbish by carpet or article placing frame partial occlusion, clean robot
Cleaning arm is touched, and controls scalable cleaning arm and scoops up carpet or article placing frame edge, is carried out while advancing by cleaning arm
Clean rubbish.
There is also a kind of optional scheme, after the image information for acquiring region for clearance, clean robot also according to
Image information identifies the cleaning road conditions of robot, and mobile according to cleaning road conditions control robot.Specifically, clean robot exists
After obtaining image information, image information is analyzed, to determine that whether there are obstacles in front.Wherein, in front of determination
There are in the case where barrier, whether clean robot disturbance in judgement object is rubbish.If barrier is rubbish, machine is cleaned
People clears up rubbish.If barrier is not rubbish, whether the lower section of the further disturbance in judgement object of clean robot is deposited
In rubbish, if there are rubbish below barrier, clean robot clears up rubbish by cleaning arm;If obstacle
Rubbish is not present in the lower section of object, then the image information on clean robot acquisition left side, right side and rear, and according to collected
Image information determines the moving direction of clean robot.For example, determining the feelings for there was only not no barrier on the left of clean robot
Under condition, clean robot moves to the left.In the case where determining does not have barrier there are two above direction, clean robot
Moving direction is determined by random sequence.
It should be noted that as shown in the above, scheme provided herein passes through Image Acquisition and multitask base
This decision tree recognize model identification front cleaning road conditions, and by telescopic cleaning arm under bed, the inferior cleaning of sofa it is dead
It angle and is precisely cleaned by the rubbish of carpet or article placing frame partial occlusion, and then eliminates and there is the drawbacks of cleaning dead angle, greatly
The user experience is improved.
Embodiment 2
According to embodiments of the present invention, a kind of embodiment of clean robot is additionally provided, the clean robot is executable real
Apply the method for cleaning of rubbish provided by example 1.Wherein, Fig. 3 is the structural representation of clean robot according to an embodiment of the present invention
Figure, as shown in figure 3, clean robot may include: image acquisition units 30 and central processing unit 31.
Wherein, image acquisition units 30, for acquiring the image information in region for clearance;Central processing unit 31, including figure
As processing unit 311, wherein image processing unit is used to recognize image information based on identification model, obtains for clearance
The area information in region, and cleaning area is treated according to area information control robot and is cleared up, wherein identification model is to make
It is obtained with multi-group data by decision tree training, every group of data in multi-group data include: image information and image letter
Cease corresponding area information.
It, can also be with it should be noted that region for clearance can be the region (for example, on ground) that is not blocked by obstructions
For the region being blocked by obstructions, for example, under bed, the inferior region blocked by bed, sofa of sofa.Believe in the region in region for clearance
Breath includes at least one following: rubbish position (for example, on ground, under carpet), rubbish type are (for example, dust, paper scrap, dirt
Dirt), degree of fouling, coverage extent (for example, all block, partial occlusion).In addition, clean robot can be but be not limited to sweep
Floor-washing robot, wiping window robot, wipe a table robot.
In addition it is also necessary to explanation, for different area informations, clean robot uses different processing modes pair
Region for clearance is cleared up, for example, under bed, the region that the inferior clean robot of sofa is not easily accessible, clean robot
Can be used cleaning arm under bed, the region that the inferior clean robot of sofa is not easily accessible clears up, and robot can be arrived
The region reached, the mode that can directly adopt sweep brush are treated cleaning area and are cleared up.
From the foregoing, it will be observed that by the way of image identification rubbish, after the image information for acquiring region for clearance, robot
Image information is recognized based on identification model, the area information in region for clearance is obtained, then further according to area information control
Robot processed treats cleaning area and is cleared up, wherein and identification model is obtained using multi-group data by decision tree training,
Every group of data in multi-group data include: image information and the corresponding area information of image information.
It is easily noted that, by recognizing to image information, can identify the rubbish being blocked by obstructions, thus
It ensure that effective identification to all rubbish, and then the rubbish being blocked by obstructions cleared up, it is dead so as to avoid cleaning
Angle.In addition, also can be identified the contents such as the type of rubbish, degree of fouling by image information, and then can be according to picking out
The contents such as type, the degree of fouling of rubbish clear up rubbish using reasonable manner of cleaning up, thus realize to rubbish into
The technical effect that row is effectively cleared up.
It can be seen that scheme provided herein can solve the technology that existing clean robot has cleaning dead angle
Problem.
In a kind of optional scheme, from the figure 3, it may be seen that central processing unit further include: sweep brush 313 and cleaning arm 315.
Wherein, sweep brush 313, in the case where rubbish position is robot accessible position and rubbish type is rubbish clast,
Cleaning area is treated to be cleared up;Cleaning arm 315, for rubbish position be robot can not reach position in the case where,
It treats cleaning area to be cleared up, wherein cleaning arm is telescopic cleaning arm.
It should be noted that clean robot can also be according to the degree of fouling of rubbish in scheme provided herein
To select different manner of cleaning up to clear up rubbish.Optionally, in the case where area information includes at least degree of fouling,
And in the case where degree of fouling reaches default degree of fouling, control robot treats cleaning area using manner of cleaning up is reinforced
It is cleared up, wherein reinforce manner of cleaning up including at least one of following: water horning, drying cleaning.
In a kind of optional scheme, clean robot may recognize that the degree of fouling of rubbish by recognizing model, and will
Obtained dirty program is compared with default degree of fouling, and the dirty grade of rubbish is determined according to comparison result.Wherein, rubbish
The dirty grade of rubbish can be divided into cleaning, dirtier, dirty, extremely dirty etc., and each dirty grade corresponds to different processing modes.For example,
On floor dust and be stained with greasy dirt it is more when, corresponding grade can be to be dirty, at this point, clean robot is using Water spraying wiper
Mode cleared up.In order to ground ponding and damp ground clear up, using after water horning, cleaning
Robot further using drying manner of cleaning up the ponding on ground is cleared up, with solve due to ponding etc. caused by two
Secondary cleaning problems.
It is big in coverage extent in the case where area information includes at least coverage extent in another optional scheme
In the case where default coverage extent, region for clearance that control robot blocks shelter using shelter manner of cleaning up into
Row cleaning.Optionally, when image processing unit picks out the rubbish by carpet or article placing frame partial occlusion, clean robot
Cleaning arm is touched, and controls scalable cleaning arm and scoops up carpet or article placing frame edge, is carried out while advancing by cleaning arm
Clean rubbish.
There is also a kind of optional scheme, image processing unit is also used to identify the cleaning road of robot according to image information
Condition, it is mobile according to cleaning road conditions control robot.Specifically, clean robot is after obtaining image information, to image information
It is analyzed, to determine that whether there are obstacles in front.Wherein, machine is cleaned there are in the case where barrier in front of determination
Whether people's disturbance in judgement object is rubbish.If barrier is rubbish, clean robot clears up rubbish.If barrier
It is not rubbish, then the lower section of the further disturbance in judgement object of clean robot whether there is rubbish, if the lower section of barrier exists
Rubbish, then clean robot clears up rubbish by cleaning arm;If rubbish, cleaner is not present in the lower section of barrier
Device people acquires the image information on left side, right side and rear, and the shifting of clean robot is determined according to acquired image information
Dynamic direction.For example, determining that clean robot moves to the left in the case where only having on the left of clean robot without barrier.
In the case where determining does not have barrier there are two above direction, clean robot determines moving direction by random sequence.
Embodiment 3
According to embodiments of the present invention, a kind of embodiment of the cleaning plant of rubbish is additionally provided, the device is executable to be implemented
The method for cleaning of rubbish provided by example 1.Wherein, Fig. 4 is that the structure of the cleaning plant of rubbish according to an embodiment of the present invention is shown
It is intended to, as shown in figure 4, the apparatus may include: acquisition module 401, identification module 403 and cleaning modul 405.
Wherein, acquisition module 401, for acquiring the image information in region for clearance;Module 403 is recognized, is distinguished for being based on
Know model to recognize image information, obtain the area information in region for clearance, wherein identification model is to use multi-group data
It is obtained by decision tree training, every group of data in multi-group data include: image information and the corresponding area of image information
Domain information;Cleaning modul 405 is cleared up for treating cleaning area according to area information control robot.
It should be noted that above-mentioned acquisition module 401, identification module 403 and cleaning modul 405 correspond to embodiment 1
In step S102 to step S106, the example and application scenarios that three modules and corresponding step are realized be identical but unlimited
In 1 disclosure of that of above-described embodiment.
In a kind of optional scheme, cleaning modul comprises determining that module and control module.Wherein it is determined that module, is used
In determining processing mode corresponding with area information, wherein processing mode includes at least one following: cleaning arm manner of cleaning up,
Sweep brush manner of cleaning up reinforces manner of cleaning up, shelter manner of cleaning up;Control module, for controlling machine according to processing mode
People treats cleaning area and clears up.
It should be noted that above-mentioned determining module and control module correspond to the step S1060 in embodiment 1 to step
S1062, two modules are identical as example and application scenarios that corresponding step is realized, but it is public to be not limited to the above embodiments 1 institute
The content opened.
In a kind of optional scheme, in the case where area information includes rubbish position, cleaning modul includes: the first control
Molding block.Wherein, the first control module, for controlling machine in the case where rubbish position is the position that robot can not reach
Device people treats cleaning area using cleaning arm manner of cleaning up and clears up.
In a kind of optional scheme, in the case where area information includes at least rubbish type and rubbish position, cleaning
Module includes: the second control module.Wherein, the second control module, for being robot accessible position in rubbish position, and
And in the case that rubbish type is specified type, control robot treats cleaning area using sweep brush manner of cleaning up and carries out clearly
Reason.
In a kind of optional scheme, in the case where area information includes at least degree of fouling, cleaning modul includes: the
Three control modules.Wherein, third control module, for controlling machine in the case where degree of fouling reaches default degree of fouling
People treats cleaning area using reinforcement manner of cleaning up and clears up, wherein reinforces manner of cleaning up including at least one of following: water spray
Cleaning, drying cleaning.
In a kind of optional scheme, in the case where area information includes at least coverage extent, cleaning modul includes: the
Four control modules.Wherein, the 4th control module, for controlling machine in the case where coverage extent is greater than default coverage extent
People clears up the region for clearance that shelter blocks using shelter manner of cleaning up.
In a kind of optional scheme, the cleaning plant of rubbish further include: identification module and the 5th control module.Its
In, identification module, for identifying the cleaning road conditions of robot according to image information;5th control module, for according to cleaning road
It is mobile that condition controls robot.
Embodiment 4
According to another aspect of an embodiment of the present invention, a kind of storage medium is additionally provided, which includes storage
Program, wherein program executes the method for cleaning of rubbish provided by embodiment 1.
Embodiment 5
According to another aspect of an embodiment of the present invention, a kind of processor is additionally provided, which is used to run program,
In, the method for cleaning of rubbish provided by embodiment 1 is executed when program is run.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
In the above embodiment of the invention, it all emphasizes particularly on different fields to the description of each embodiment, does not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code
Medium.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (14)
1. a kind of method for cleaning of rubbish characterized by comprising
Acquire the image information in region for clearance;
Described image information is recognized based on identification model, obtains the area information in the region for clearance, wherein described
Identification model is obtained using multi-group data by decision tree training, and every group of data in the multi-group data include: institute
State image information and the corresponding area information of described image information;
Robot is controlled according to the area information to clear up the region for clearance.
2. the method according to claim 1, wherein controlling robot to described to clear according to the area information
Reason region is cleared up, comprising:
Determine processing mode corresponding with the area information, wherein the processing mode includes at least one following: cleaning arm
Manner of cleaning up, reinforces manner of cleaning up, shelter manner of cleaning up at sweep brush manner of cleaning up;
The robot is controlled according to the processing mode to clear up the region for clearance.
3. according to the method described in claim 2, it is characterized in that, in the case where the area information includes rubbish position,
Robot is controlled according to the area information to clear up the region for clearance, comprising:
In the case where the rubbish position is the position that the robot can not reach, the robot is controlled using described clear
Clean arm manner of cleaning up clears up the region for clearance.
4. according to the method described in claim 2, it is characterized in that, including at least rubbish type and rubbish in the area information
In the case where position, robot is controlled according to the area information, the region for clearance is cleared up, comprising:
The rubbish position be the robot accessible position, and the rubbish type be specified type the case where
Under, it controls the robot and the region for clearance is cleared up using the sweep brush manner of cleaning up.
5. according to the method described in claim 2, it is characterized in that, the case where the area information includes at least degree of fouling
Under, robot is controlled according to the area information, the region for clearance is cleared up, comprising:
In the case where the degree of fouling reaches default degree of fouling, the robot is controlled using the reinforcement manner of cleaning up
The region for clearance is cleared up, wherein the reinforcement manner of cleaning up includes at least one of following: water horning, drying
Cleaning.
6. according to the method described in claim 2, it is characterized in that, the case where the area information includes at least coverage extent
Under, robot is controlled according to the area information, the region for clearance is cleared up, comprising:
In the case where the coverage extent is greater than default coverage extent, the robot is controlled using the shelter cleaning side
Formula clears up the region for clearance that shelter blocks.
7. described the method according to claim 1, wherein after the image information for acquiring region for clearance
Method further include:
The cleaning road conditions of the robot are identified according to described image information;
It is mobile that the robot is controlled according to the cleaning road conditions.
8. a kind of clean robot characterized by comprising
Image acquisition units, for acquiring the image information in region for clearance;
Central processing unit, including image processing unit, wherein described image processing unit is used for based on identification model to the figure
As information is recognized, the area information in the region for clearance is obtained, and robot is controlled to institute according to the area information
It states region for clearance to be cleared up, wherein the identification model is obtained using multi-group data by decision tree training, described
Every group of data in multi-group data include: described image information and the corresponding area information of described image information.
9. clean robot according to claim 8, which is characterized in that the area information includes one of following: rubbish
Position, rubbish type, degree of fouling, coverage extent.
10. clean robot according to claim 9, which is characterized in that the central processing unit further include:
Sweep brush is the robot accessible position in the rubbish position, and the rubbish type is rubbish clast
In the case where, the region for clearance is cleared up;
Cleaning arm, for the rubbish position be the robot can not reach position in the case where, to described for clearance
Region is cleared up.
11. clean robot according to claim 8, which is characterized in that described image processing unit is also used to according to institute
The cleaning road conditions that image information identifies the robot are stated, it is mobile to control the robot according to the cleaning road conditions.
12. a kind of cleaning plant of rubbish characterized by comprising
Acquisition module, for acquiring the image information in region for clearance;
Module is recognized, for recognizing based on identification model to described image information, obtains the region in the region for clearance
Information, wherein the identification model is obtained using multi-group data by decision tree training, every group in the multi-group data
Data include: described image information and the corresponding area information of described image information;
Cleaning modul clears up the region for clearance for controlling robot according to the area information.
13. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein described program right of execution
Benefit require any one of 1 to 7 described in rubbish method for cleaning.
14. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit require any one of 1 to 7 described in rubbish method for cleaning.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811089245.0A CN109171571A (en) | 2018-09-18 | 2018-09-18 | Method for cleaning, device and the clean robot of rubbish |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811089245.0A CN109171571A (en) | 2018-09-18 | 2018-09-18 | Method for cleaning, device and the clean robot of rubbish |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109171571A true CN109171571A (en) | 2019-01-11 |
Family
ID=64908331
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811089245.0A Pending CN109171571A (en) | 2018-09-18 | 2018-09-18 | Method for cleaning, device and the clean robot of rubbish |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109171571A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109740581A (en) * | 2019-03-01 | 2019-05-10 | 成都信息工程大学 | A kind of intelligent garbage, which is collected, monitors system with scene |
CN110013197A (en) * | 2019-04-16 | 2019-07-16 | 上海天诚通信技术股份有限公司 | A kind of sweeping robot object identification method |
CN110458068A (en) * | 2019-07-31 | 2019-11-15 | 秒针信息技术有限公司 | The management method of hotel's health, device and system |
CN110474947A (en) * | 2019-03-27 | 2019-11-19 | 黄慧 | Block chain transaction processing system and method |
CN110693397A (en) * | 2019-10-29 | 2020-01-17 | 珠海市一微半导体有限公司 | Control method of cleaning robot, cleaning robot and medium |
CN110980050A (en) * | 2019-12-13 | 2020-04-10 | 珠海格力电器股份有限公司 | Garbage disposal method, storage medium and garbage storage equipment |
CN111358387A (en) * | 2020-04-20 | 2020-07-03 | 成都科梦极信息科技有限公司 | Building outer wall cleaning system and cleaning method |
CN111643017A (en) * | 2020-06-02 | 2020-09-11 | 深圳市杉川机器人有限公司 | Cleaning robot control method and device based on schedule information and cleaning robot |
CN112192583A (en) * | 2020-10-09 | 2021-01-08 | 常熟云开智能科技有限公司 | Control method of automatic hazardous chemical cleaning robot of vacuum cleaning system |
WO2021008339A1 (en) * | 2019-07-16 | 2021-01-21 | 深圳市杉川机器人有限公司 | Robot, robot-based cleaning method, and computer readable storage medium |
CN112380897A (en) * | 2020-09-30 | 2021-02-19 | 宁波市世纪耀达环卫保洁有限公司 | Road stain cleaning method and system, storage medium and intelligent terminal |
CN114348201A (en) * | 2021-12-31 | 2022-04-15 | 国信中船(青岛)海洋科技有限公司 | Intelligent cleaning system for cabin wall of culture cabin of culture ship |
CN114941448A (en) * | 2021-02-07 | 2022-08-26 | 广东博智林机器人有限公司 | Mortar cleaning method, device, system and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105380575A (en) * | 2015-12-11 | 2016-03-09 | 美的集团股份有限公司 | Control method and system for sweeping robot, cloud server and sweeping robot |
CN105395144A (en) * | 2015-12-21 | 2016-03-16 | 美的集团股份有限公司 | Control method, system and cloud server of sweeping robot and sweeping robot |
CN107180241A (en) * | 2017-04-20 | 2017-09-19 | 华南理工大学 | A kind of animal classification method of the profound neutral net based on Gabor characteristic with fractal structure |
US20180092499A1 (en) * | 2016-10-05 | 2018-04-05 | Lenovo (Singapore) Pte. Ltd. | Systems and methods to command a robotic cleaning device to move to a dirty region of an area |
CN108107886A (en) * | 2017-11-29 | 2018-06-01 | 珠海格力电器股份有限公司 | Travel control method and device, the sweeping robot of sweeping robot |
CN108416271A (en) * | 2018-02-06 | 2018-08-17 | 宁夏宁信信息科技有限公司 | Cleaning method and purging system |
-
2018
- 2018-09-18 CN CN201811089245.0A patent/CN109171571A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105380575A (en) * | 2015-12-11 | 2016-03-09 | 美的集团股份有限公司 | Control method and system for sweeping robot, cloud server and sweeping robot |
CN105395144A (en) * | 2015-12-21 | 2016-03-16 | 美的集团股份有限公司 | Control method, system and cloud server of sweeping robot and sweeping robot |
US20180092499A1 (en) * | 2016-10-05 | 2018-04-05 | Lenovo (Singapore) Pte. Ltd. | Systems and methods to command a robotic cleaning device to move to a dirty region of an area |
CN107180241A (en) * | 2017-04-20 | 2017-09-19 | 华南理工大学 | A kind of animal classification method of the profound neutral net based on Gabor characteristic with fractal structure |
CN108107886A (en) * | 2017-11-29 | 2018-06-01 | 珠海格力电器股份有限公司 | Travel control method and device, the sweeping robot of sweeping robot |
CN108416271A (en) * | 2018-02-06 | 2018-08-17 | 宁夏宁信信息科技有限公司 | Cleaning method and purging system |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109740581A (en) * | 2019-03-01 | 2019-05-10 | 成都信息工程大学 | A kind of intelligent garbage, which is collected, monitors system with scene |
CN110474947A (en) * | 2019-03-27 | 2019-11-19 | 黄慧 | Block chain transaction processing system and method |
CN110013197A (en) * | 2019-04-16 | 2019-07-16 | 上海天诚通信技术股份有限公司 | A kind of sweeping robot object identification method |
WO2021008339A1 (en) * | 2019-07-16 | 2021-01-21 | 深圳市杉川机器人有限公司 | Robot, robot-based cleaning method, and computer readable storage medium |
CN110458068A (en) * | 2019-07-31 | 2019-11-15 | 秒针信息技术有限公司 | The management method of hotel's health, device and system |
CN110693397B (en) * | 2019-10-29 | 2021-11-19 | 珠海一微半导体股份有限公司 | Control method of cleaning robot, cleaning robot and medium |
CN110693397A (en) * | 2019-10-29 | 2020-01-17 | 珠海市一微半导体有限公司 | Control method of cleaning robot, cleaning robot and medium |
CN110980050A (en) * | 2019-12-13 | 2020-04-10 | 珠海格力电器股份有限公司 | Garbage disposal method, storage medium and garbage storage equipment |
CN110980050B (en) * | 2019-12-13 | 2021-06-22 | 珠海格力电器股份有限公司 | Garbage disposal method, storage medium and garbage storage equipment |
CN111358387A (en) * | 2020-04-20 | 2020-07-03 | 成都科梦极信息科技有限公司 | Building outer wall cleaning system and cleaning method |
CN111643017A (en) * | 2020-06-02 | 2020-09-11 | 深圳市杉川机器人有限公司 | Cleaning robot control method and device based on schedule information and cleaning robot |
CN111643017B (en) * | 2020-06-02 | 2022-08-16 | 深圳市杉川机器人有限公司 | Cleaning robot control method and device based on schedule information and cleaning robot |
CN112380897A (en) * | 2020-09-30 | 2021-02-19 | 宁波市世纪耀达环卫保洁有限公司 | Road stain cleaning method and system, storage medium and intelligent terminal |
CN112192583A (en) * | 2020-10-09 | 2021-01-08 | 常熟云开智能科技有限公司 | Control method of automatic hazardous chemical cleaning robot of vacuum cleaning system |
CN114941448A (en) * | 2021-02-07 | 2022-08-26 | 广东博智林机器人有限公司 | Mortar cleaning method, device, system and storage medium |
CN114941448B (en) * | 2021-02-07 | 2023-09-05 | 广东博智林机器人有限公司 | Mortar cleaning method, device, system and storage medium |
CN114348201A (en) * | 2021-12-31 | 2022-04-15 | 国信中船(青岛)海洋科技有限公司 | Intelligent cleaning system for cabin wall of culture cabin of culture ship |
CN114348201B (en) * | 2021-12-31 | 2024-05-03 | 国信中船(青岛)海洋科技有限公司 | Intelligent cleaning system for cabin walls of aquaculture engineering ship |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109171571A (en) | Method for cleaning, device and the clean robot of rubbish | |
CN106894481B (en) | One kind is detected automatically based on intelligent closestool and is cleaned dirt method and system | |
CN105395144B (en) | Control method, system, Cloud Server and the sweeping robot of sweeping robot | |
CN108514381A (en) | Method, apparatus of sweeping the floor and sweeping robot | |
CN108697293A (en) | The cleaning system of the control device of autonomous type dust catcher, the autonomous type dust catcher for having the control device and the control device for having autonomous type dust catcher | |
CN108416271A (en) | Cleaning method and purging system | |
CN107137022A (en) | Intelligent cleaning robot system | |
CN107752910A (en) | Region cleaning method, device, storage medium, processor and sweeping robot | |
CN110622085A (en) | Mobile robot and control method and control system thereof | |
CN105411491A (en) | Home intelligent cleaning system and method based on environment monitoring | |
CN109213137A (en) | sweeping robot, sweeping robot system and its working method | |
CN110502014A (en) | A kind of method and robot of robot obstacle-avoiding | |
CN105700531A (en) | Customized map-based household sweeping robot used for two-storey house and sweeping method thereof | |
CN110403528A (en) | A kind of method and system improving cleaning coverage rate based on clean robot | |
CN107713913A (en) | Robot recognizes and the method for processing pet dung | |
CN108903819A (en) | A kind of hotel's clean robot and its control method based on artificial intelligence | |
CN109448002A (en) | A kind of sweeping robot control method, system, mobile terminal and storage medium | |
CN108836195A (en) | A kind of get rid of poverty method and the sweeping robot of sweeping robot | |
CN107862313A (en) | Dish-washing machine and its control method and device | |
CN115503655A (en) | Car washing intelligent control system based on Internet of things | |
CN113180549A (en) | Cleaning control method, device and air conditioner | |
CN110326999A (en) | Control method for vehicle, device, equipment, automatic driving vehicle and storage medium | |
CN109602343A (en) | Control method and device, the system of sweeping robot based on microwave radar | |
CN210704858U (en) | Cleaning robot with binocular camera | |
CN112971644B (en) | Cleaning method and device of sweeping robot, storage medium and sweeping robot |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190111 |