CN109452914A - Intelligent cleaning equipment, cleaning mode selection method, computer storage medium - Google Patents
Intelligent cleaning equipment, cleaning mode selection method, computer storage medium Download PDFInfo
- Publication number
- CN109452914A CN109452914A CN201811295518.7A CN201811295518A CN109452914A CN 109452914 A CN109452914 A CN 109452914A CN 201811295518 A CN201811295518 A CN 201811295518A CN 109452914 A CN109452914 A CN 109452914A
- Authority
- CN
- China
- Prior art keywords
- cleaning mode
- cleaning
- cleaning equipment
- operative scenario
- work
- 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
- A47L11/40—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
- A47L11/4011—Regulation of the cleaning machine by electric means; Control systems and remote control systems therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The cleaning mode selection method based on convolutional neural networks that the invention discloses a kind of, comprising the following steps: S1: the work at present scene image of acquisition intelligent cleaning equipment；S2: collected work at present scene image is input to the operative scenario convolutional neural networks disaggregated model of the intelligent cleaning equipment, to determine the type of work at present scene, wherein, the operative scenario convolutional neural networks disaggregated model is established according to training sample set, and the pre-acquired operative scenario image tagged that the training sample is concentrated has corresponding operative scenario type label；S3: corresponding cleaning mode is used according to the type of work at present scene.The present invention is input to trained operative scenario convolutional neural networks disaggregated model you can get it the type of intelligent cleaning equipment work at present scene by acquisition work at present scene image, and then takes corresponding cleaning mode.The present invention makes the more efficient selection of cleaning mode, intelligence, diversification, meets consumer demand.
Description
Technical field
The present invention relates to intelligent cleaning technical field more particularly to a kind of cleaning mode selections based on convolutional neural networks
Method, intelligent cleaning equipment and computer storage medium.
Background technique
The sensing device that existing intelligent cleaning equipment usually passes through itself provides location information and movement to control system
Status information, and then realizing route planning, obstacle avoidance etc., intelligent cleaning equipment in this way are " can't see " objects
, the object in working environment can only be taken as barrier and be crossed or separate.Also, existing intelligent cleaning equipment can not
The room locating for oneself is directly told, can only be user carries out map partitioning by mobile terminal to inform its specific location, and
Which type of cleaning mode should be taken.Aforesaid way is not smart enough, and the manual intervention needed is excessive, cause cleaning efficiency compared with
It is low.
Summary of the invention
A series of concept of reduced forms is introduced in Summary, this will in the detailed description section into
One step is described in detail.Summary of the invention is not meant to attempt to limit technical solution claimed
Key feature and essential features do not mean that the protection scope for attempting to determine technical solution claimed more.
In order at least be partially solved the above problem, according to the first aspect of the invention, provide a kind of based on convolution mind
Cleaning mode selection method through network, comprising the following steps:
S1: the work at present scene image of the intelligent cleaning equipment is acquired；
S2: collected work at present scene image is input to the operative scenario convolutional Neural of the intelligent cleaning equipment
Network class model, to determine the type of work at present scene, wherein the operative scenario convolutional neural networks disaggregated model root
It is established according to training sample set, the pre-acquired operative scenario image tagged that the training sample is concentrated has corresponding operative scenario type
Label；
S3: corresponding cleaning mode is used according to the type of work at present scene.
Cleaning mode selection method based on convolutional neural networks according to the present invention for intelligent cleaning equipment, passes through
Work at present scene image is acquired, trained operative scenario convolutional neural networks disaggregated model is input to you can get it intelligence
The type of energy cleaning equipment work at present scene, and then take corresponding cleaning mode.The present invention makes the selection of cleaning mode more
Increase effect, intelligence, diversification, meets consumer demand.
Preferably, the operative scenario convolutional neural networks disaggregated model is adaptive convolutional neural networks disaggregated model,
For completing incremental learning according to new training sample.
Intelligent cleaning equipment can accumulate new training sample in constantly use process as a result, complete further
Study, more intelligently judges its operative scenario.
Preferably, the operative scenario type label includes room property label, and the room property label is for characterizing
The spatial position of the intelligent cleaning equipment.
Preferably,
The step S2 includes the room property for determining work at present scene；
The step S3 includes using corresponding first cleaning mode according to the room property；
First cleaning mode be configured to the intelligent cleaning equipment used for different room properties it is different clear
Clean dynamics.
Preferably, the operative scenario type label includes small items attribute tags, the small items attribute tags
For characterizing the ambient enviroment of the intelligent cleaning equipment.
Preferably,
The step S2 includes the small items attribute for determining work at present scene；
The step S3 includes using corresponding second cleaning mode according to the small items attribute；
Second cleaning mode is configured to drop when the intelligent cleaning equipment avoids small items or closes on small items
Speed walking cleaning.
Preferably, the operative scenario type label includes ground material properties label, the ground material properties label
The ground material being located at for characterizing the intelligent cleaning equipment.
Preferably,
The step S2 includes the ground material properties for determining work at present scene；
The step S3 includes using corresponding third cleaning mode according to the ground material properties；
The third cleaning mode is configured to the intelligent cleaning equipment and uses difference for Different Ground material properties
Cleaning dynamics and/or use different cleaning humidity.
Preferably, the blower and/or cleaning using different cleaning dynamics by the adjusting intelligent cleaning equipment
Number is realized.
According to the second aspect of the invention, a kind of intelligent cleaning equipment is provided comprising memory, processor and be stored in
The computer program run on the memory and on the processor, the processor realize basis when executing described program
The step of cleaning mode selection method based on convolutional neural networks of the invention.
According to the third aspect of the invention we, a kind of computer storage medium is provided, computer program is stored thereon with, it is described
The step of cleaning mode selection method according to the present invention based on convolutional neural networks is realized when program is executed by processor.
Detailed description of the invention
Following drawings of the invention is incorporated herein as part of the present invention for the purpose of understanding the present invention.Shown in the drawings of this hair
Bright embodiment and its description, device used to explain the present invention and principle.In the accompanying drawings,
Fig. 1 is the flow chart of the cleaning mode selection method according to the present invention based on convolutional neural networks.
Specific embodiment
In the following description, a large amount of concrete details are given so as to provide a more thorough understanding of the present invention.So
And it is obvious to the skilled person that the present invention may not need one or more of these details and be able to
Implement.In other examples, in order to avoid confusion with the present invention, for some technical characteristics well known in the art not into
Row description.
In order to thoroughly understand the present invention, detailed structure will be proposed in following description, to illustrate the present invention.It is aobvious
So, execution of the invention is not limited to the specific details that the those skilled in the art are familiar with.Preferable reality of the invention
Example is applied to be described in detail as follows, however other than these detailed descriptions, the present invention can also have other embodiments, should not solve
It is interpreted as being confined to embodiments presented herein.
Fig. 1 shows the flow chart of the cleaning mode selection method according to the present invention based on convolutional neural networks.Specifically
Ground, the selection method the following steps are included:
S1: the work at present scene image of the intelligent cleaning equipment is acquired；
S2: collected work at present scene image is input to the operative scenario convolutional Neural of the intelligent cleaning equipment
Network class model, to determine the type of work at present scene, wherein the operative scenario convolutional neural networks disaggregated model root
It is established according to training sample set, the pre-acquired operative scenario image tagged that the training sample is concentrated has corresponding operative scenario type
Label；
S3: corresponding cleaning mode is used according to the type of work at present scene.
Cleaning mode selection method based on convolutional neural networks according to the present invention for intelligent cleaning equipment, passes through
Work at present scene image is acquired, trained operative scenario convolutional neural networks disaggregated model is input to you can get it intelligence
The type of energy cleaning equipment work at present scene, and then take corresponding cleaning mode.The present invention makes the selection of cleaning mode more
Increase effect, intelligence, diversification, meets consumer demand.
It should be noted that building and utilizing for the operative scenario convolutional neural networks disaggregated model in step S2
Training sample set is trained the disaggregated model, already belongs to the technology of comparative maturity in this field, provide herein one it is excellent
The embodiment of choosing carries out brief description.
Firstly, the pre-acquired operative scenario image that training sample is concentrated can be before the factory of intelligent cleaning equipment just
Through what is inputted, it is also possible to further carry out what collection in worksite obtained to its family in user's family initialization procedure, and
And the pre-acquired operative scenario image has been marked with corresponding operative scenario type label.Pre-acquired operative scenario image be
Image under various illumination, angle, focus condition.
Secondly, the build process of operative scenario convolutional neural networks disaggregated model:
Operative scenario convolutional neural networks disaggregated model includes that C convolutional layer, F full articulamentums and a softmax divide
Class device, 2≤C≤5,1≤F≤3；Convolution, pond and normalized are carried out in each convolutional layer；The volume of each convolutional layer
Product core size is ci*ci, step-length sci*sci, wherein 1≤ci≤10,1≤sci≤5,1≤i≤C；Convolution is carried out to image
Processing obtains ki kind feature, 1≤ki≤256；The pondization processing of each convolutional layer uses maximum pond, size pi*pi, step-length
For spi*spi, wherein 1≤pi≤10,1≤spi≤5,1≤i≤C；To pondization, treated that image is normalized；Figure
As the result obtained after the processing of a upper convolutional layer inputs next convolutional layer；After the C convolutional layer, by what is obtained
Characteristic expansion is input in first full articulamentum at one-dimensional vector, and the result of first full articulamentum is then input to second
In a full articulamentum, and so on, logits value is being obtained after F full articulamentums, the logits that will finally obtain
Value is input in softmax classifier, obtains the probability value that the picture belongs to each classification, thus probability value and true
Cross entropy loss function is calculated in label, so as to complete building for convolutional neural networks model；Wherein, each connects entirely
Connecing the neuron number contained in layer is fj, wherein 1≤fj≤768,1≤j≤F.
The training process of operative scenario convolutional neural networks disaggregated model: training uses gradient descent method, and learning rate uses
Learning rate is changed, training the number of iterations is between 50,000-10 ten thousand times.
It is input to after the work at present scene image of acquisition is pre-processed and utilizes the trained yard of aforesaid way
In preceding C+F layers of scape convolutional neural networks disaggregated model, logits value is obtained, then in logits value where selection maximum value
Subscript, the label as predicted, to complete to identify.
Intelligent cleaning equipment uses corresponding cleaning mode according to the type of the work at present scene identified later.
In one embodiment, operative scenario convolutional neural networks disaggregated model can be adaptive convolutional neural networks
Disaggregated model, for completing incremental learning according to new training sample.Adaptive convolutional neural networks disaggregated model can be in original
Input layer, central core and excitation layer are added on the basis of the operative scenario convolutional neural networks disaggregated model come, input layer represents
The sample of classification error in operative scenario neural network training process originally, central core represent wrong classification samples not
With cluster, excitation layer representative sample mode can directly export sample mode according to the output of central core, or activate originally
The further recognition mode of operative scenario convolutional neural networks disaggregated model.
Continue with the classification of the type of operative scenario being related in description step S2 and step S3 and corresponding
The content of cleaning mode and key content of the invention.
In one embodiment, operative scenario type label may include room property label, and room property label is used
In the spatial position of characterization intelligent cleaning equipment.
Further, the cleaning mode selection method according to the present invention based on convolutional neural networks may include walking as follows
It is rapid:
Step S2 includes the step of determining the room property of work at present scene；Step S3 includes being adopted according to room property
With corresponding first cleaning mode；First cleaning mode is configured to intelligent cleaning equipment and uses difference for different room properties
Cleaning dynamics the step of.
For example, such as having pumping in the work at present scene image of intelligent cleaning equipment acquisition for kitchen, balcony and other places
The significant object such as kitchen ventilator has corresponding kitchen then after the analysis of operative scenario convolutional neural networks disaggregated model
Room property label then passes through alternatively, having the significant object such as potting in the work at present scene image of intelligent cleaning equipment acquisition
After crossing the analysis of operative scenario convolutional neural networks disaggregated model, there is the room property label of corresponding balcony, then can add
Big power of fan repeats to clean twice；For bedroom and other places, i.e., such as intelligent cleaning equipment acquisition work at present scene figure
There is the significant object such as bed as in, then after the analysis of operative scenario convolutional neural networks disaggregated model, there is corresponding bedroom
Room property label, cleaned then blower can be closed, prevent from bothering user's rest.
In one embodiment, operative scenario type label may include small items attribute tags, small items category
Property label be used to characterize the ambient enviroment of intelligent cleaning equipment.
Further, the cleaning mode selection method according to the present invention based on convolutional neural networks may include walking as follows
It is rapid:
The step of step S2 includes the small items attribute for determining work at present scene；Step S3 includes, according to minim
Body attribute uses corresponding second cleaning mode；Second cleaning mode is configured to intelligent cleaning equipment and avoids small items or close on
When small items the step of reduction of speed walking cleaning.
For example, the object that can be pushed easily for dustbin, toy, slippers etc. or animal wastes etc. are directly avoided；It is right
It can then be walked and be cleaned with reduction of speed in general barrier (will not cause damages to user colliding).
As long as it should be noted that having in the example above in the work at present scene image of intelligent cleaning equipment acquisition
Small items, then after the analysis of operative scenario convolutional neural networks disaggregated model, the object that just there is correspondence can push easily
The small items attribute tags of body；If having those will not be to user in the work at present scene image of intelligent cleaning equipment acquisition
The general barrier of loss is brought, then after the analysis of operative scenario convolutional neural networks disaggregated model, just has corresponding one
As barrier small items attribute tags.It therefore, can basis for the differentiation of general barrier and the object that can be moved easily
Empirical cumulative or user demand carry out self-defining.
In one embodiment, operative scenario type label may include ground material properties label, ground material category
Property label for characterizing the ground material that intelligent cleaning equipment is located at.
Further, the cleaning mode selection method according to the present invention based on convolutional neural networks may include walking as follows
It is rapid:
The step of step S2 includes the ground material properties for determining work at present scene；Step S3 includes base area plane materiel
Matter attribute uses corresponding third cleaning mode；Third cleaning mode is configured to intelligent cleaning equipment for Different Ground material category
Property and the step of use different cleaning dynamics and/or use different cleaning humidity.
For example, when intelligent cleaning equipment is located on floor tile, it can be using wet cleaning mode, for example open intelligent cleaning
The water outlet of the mopping function of equipment can also increase cleaning dynamics, for example increase power of fan or repetition if floor tile is dirtier
It cleans；When intelligent cleaning equipment is located in timber floor, drying mode can be used, for example close the function that mops floor of intelligent cleaning equipment
The water outlet of energy reduces water yield.
It should be noted that if display is to be located at floor in the work at present scene image of intelligent cleaning equipment acquisition
On, then after the analysis of operative scenario convolutional neural networks disaggregated model, just there is the ground material properties mark on corresponding floor
Label；If display is located on floor tile in the work at present scene image of intelligent cleaning equipment acquisition, rolled up by operative scenario
After product neural network classification model analysis, just there is the ground material properties label of corresponding floor tile.
The present invention also provides a kind of intelligent cleaning equipment comprising memory, processor and is stored in the memory
Computer program that is upper and running on the processor, processor perform the steps of when executing program
S1: the work at present scene image of acquisition intelligent cleaning equipment；
S2: collected work at present scene image is input to the operative scenario convolutional neural networks of intelligent cleaning equipment
Disaggregated model, to determine the type of work at present scene, wherein operative scenario convolutional neural networks disaggregated model is according to training sample
This collection is established, and the pre-acquired operative scenario image tagged that training sample is concentrated has corresponding operative scenario type label；
S3: corresponding cleaning mode is used according to the type of work at present scene.
In one embodiment, operative scenario convolutional neural networks point are performed the steps of when processor executes program
Class model is adaptive convolutional neural networks disaggregated model, for completing incremental learning according to new training sample.
In one embodiment, performing the steps of operative scenario type label when processor executes program includes room
Between attribute tags, room property label is used to characterize the spatial position of intelligent cleaning equipment.
In one embodiment, performing the steps of step S2 when processor executes program includes determining work at present
The room property of scene；Step S3 includes using corresponding first cleaning mode according to room property；First cleaning mode construction
Different cleaning dynamics is used for different room properties for intelligent cleaning equipment.
In one embodiment, it includes micro- for performing the steps of operative scenario type label when processor executes program
Wisp attribute tags, small items attribute tags are used to characterize the ambient enviroment of intelligent cleaning equipment.
In one embodiment, performing the steps of step S2 when processor executes program includes determining work at present
The small items attribute of scene；Step S3 includes using corresponding second cleaning mode according to small items attribute；Second cleaning
Schema construction is reduction of speed walking cleaning when intelligent cleaning equipment avoids small items or closes on small items.
In one embodiment, operative scenario type label is performed the steps of when processor executes program includes ground
Plane materiel matter attribute tags, ground material properties label is for characterizing the ground material that intelligent cleaning equipment is located at.
In one embodiment, performing the steps of step S2 when processor executes program includes determining work at present
The ground material properties of scene；Step S3 includes that base area face material properties use corresponding third cleaning mode；Third cleaning
Schema construction is that intelligent cleaning equipment uses different cleaning dynamics for Different Ground material properties and/or using different
Clean humidity.
In one embodiment, it performs the steps of when processor executes program and is passed through using different cleaning dynamics
It adjusts the blower of intelligent cleaning equipment and/or cleans number to realize.
The present invention also provides a kind of computer storage mediums, are stored thereon with computer program, and computer program is located
Reason device performs the steps of when executing
S1: the work at present scene image of acquisition intelligent cleaning equipment；
S2: collected work at present scene image is input to the operative scenario convolutional neural networks of intelligent cleaning equipment
Disaggregated model, to determine the type of work at present scene, wherein operative scenario convolutional neural networks disaggregated model is according to training sample
This collection is established, and the pre-acquired operative scenario image tagged that training sample is concentrated has corresponding operative scenario type label；
S3: corresponding cleaning mode is used according to the type of work at present scene.
In one embodiment, operative scenario convolution mind is performed the steps of when computer program is executed by processor
It is adaptive convolutional neural networks disaggregated model through network class model, for completing incremental learning according to new training sample.
In one embodiment, it is performed the steps of when computer program is executed by processor
Operative scenario type label includes room property label, and room property label is used to characterize the sky of intelligent cleaning equipment
Between position.
In one embodiment, step S2 is performed the steps of when computer program is executed by processor includes, and determines
The room property of work at present scene；Step S3 includes using corresponding first cleaning mode according to room property；First cleaning
Schema construction is intelligent cleaning equipment for different room properties and using different cleaning dynamics.
In one embodiment, operative scenario type mark is performed the steps of when computer program is executed by processor
Label include small items attribute tags, and small items attribute tags are used to characterize the ambient enviroment of intelligent cleaning equipment.
In one embodiment, step S2 is performed the steps of when computer program is executed by processor includes, and determines
The small items attribute of work at present scene；Step S3 includes using corresponding second cleaning mode according to small items attribute；
Second cleaning mode is configured to reduction of speed walking cleaning when intelligent cleaning equipment avoids small items or closes on small items.
In one embodiment, operative scenario type mark is performed the steps of when computer program is executed by processor
Label include ground material properties label, and ground material properties label is for characterizing the ground material that intelligent cleaning equipment is located at.
In one embodiment, step S2 is performed the steps of when computer program is executed by processor includes, and determines
The ground material properties of work at present scene；Step S3 includes that base area face material properties use corresponding third cleaning mode；
Third cleaning mode is configured to intelligent cleaning equipment and uses different cleaning dynamics for Different Ground material properties and/or adopt
With different cleaning humidity.
In one embodiment, it is performed the steps of when computer program is executed by processor using different cleanings
Dynamics is realized by adjusting the blower of intelligent cleaning equipment and/or cleaning number.
Each technical characteristic of above each embodiment can be combined arbitrarily, for simplicity of description, not to above-mentioned each
The all possible combination of each technical characteristic in embodiment is all described, as long as however, the combination of these technical characteristics
There is no contradictions, all should be considered as described in this specification.
Unless otherwise defined, technical and scientific term used herein and those skilled in the art of the invention
Normally understood meaning is identical.Term used herein is intended merely to describe specifically to implement purpose, it is not intended that limitation is originally
Invention.Terms such as herein presented " components " can both indicate single part, can also indicate the group of multiple parts
It closes.The terms such as herein presented " installation ", " setting " can both indicate that a component was attached directly to another component,
It can also indicate that a component is attached to another component by middleware.The feature described in one embodiment herein
It can be applied in combination another embodiment individually or with other feature, unless this feature is in the another embodiment
In be not suitable for or be otherwise noted.
The present invention is illustrated by above embodiment, but it is to be understood that, above embodiment is
Purpose for illustrating and illustrating, and be not intended to limit the invention within the scope of described embodiment.Furthermore this field
It is understood that the invention is not limited to above embodiment, introduction according to the present invention can also be made technical staff
More kinds of variants and modifications, all fall within the scope of the claimed invention for these variants and modifications.
Claims (11)
1. a kind of cleaning mode selection method based on convolutional neural networks for intelligent cleaning equipment, which is characterized in that packet
Include following steps:
S1: the work at present scene image of the intelligent cleaning equipment is acquired；
S2: collected work at present scene image is input to the operative scenario convolutional neural networks of the intelligent cleaning equipment
Disaggregated model, to determine the type of work at present scene, wherein the operative scenario convolutional neural networks disaggregated model is according to instruction
Practice sample set to establish, the pre-acquired operative scenario image tagged that the training sample is concentrated has corresponding operative scenario type mark
Label；
S3: corresponding cleaning mode is used according to the type of work at present scene.
2. cleaning mode selection method according to claim 1, which is characterized in that the operative scenario convolutional neural networks
Disaggregated model is adaptive convolutional neural networks disaggregated model, for completing incremental learning according to new training sample.
3. cleaning mode selection method according to claim 1, which is characterized in that the operative scenario type label includes
Room property label, the room property label are used to characterize the spatial position of the intelligent cleaning equipment.
4. cleaning mode selection method according to claim 3, which is characterized in that
The step S2 includes the room property for determining work at present scene；
The step S3 includes using corresponding first cleaning mode according to the room property；
First cleaning mode is configured to the intelligent cleaning equipment and uses different cleaning force for different room properties
Degree.
5. cleaning mode selection method according to claim 1, which is characterized in that the operative scenario type label includes
Small items attribute tags, the small items attribute tags are used to characterize the ambient enviroment of the intelligent cleaning equipment.
6. cleaning mode selection method according to claim 5, which is characterized in that
The step S2 includes the small items attribute for determining work at present scene；
The step S3 includes using corresponding second cleaning mode according to the small items attribute；
Second cleaning mode is configured to reduction of speed row when the intelligent cleaning equipment avoids small items or closes on small items
Walk cleaning.
7. cleaning mode selection method according to claim 1, which is characterized in that the operative scenario type label includes
Ground material properties label, the ground material properties label is for characterizing the ground plane materiel that the intelligent cleaning equipment is located at
Matter.
8. cleaning mode selection method according to claim 7, which is characterized in that
The step S2 includes the ground material properties for determining work at present scene；
The step S3 includes using corresponding third cleaning mode according to the ground material properties；
The third cleaning mode be configured to the intelligent cleaning equipment used for Different Ground material properties it is different clear
Clean dynamics and/or the different cleaning humidity of use.
9. the cleaning mode selection method according to claim 4 or 8, which is characterized in that described using different cleaning force
Degree is realized by adjusting the blower of the intelligent cleaning equipment and/or cleaning number.
10. a kind of intelligent cleaning equipment, including memory, processor and it is stored on the memory and on the processor
The computer program of operation, which is characterized in that the processor realizes any one of claims 1 to 9 when executing described program
The step of the method.
11. a kind of computer storage medium, is stored thereon with computer program, which is characterized in that described program is held by processor
The step of any one of claims 1 to 9 the method is realized when row.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111500223.0A CN114424916A (en) | 2018-11-01 | 2018-11-01 | Cleaning mode selection method, intelligent cleaning device, computer storage medium |
| CN201811295518.7A CN109452914A (en) | 2018-11-01 | 2018-11-01 | Intelligent cleaning equipment, cleaning mode selection method, computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811295518.7A CN109452914A (en) | 2018-11-01 | 2018-11-01 | Intelligent cleaning equipment, cleaning mode selection method, computer storage medium |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111500223.0A Division CN114424916A (en) | 2018-11-01 | 2018-11-01 | Cleaning mode selection method, intelligent cleaning device, computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109452914A true CN109452914A (en) | 2019-03-12 |
Family
ID=65609180
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111500223.0A Pending CN114424916A (en) | 2018-11-01 | 2018-11-01 | Cleaning mode selection method, intelligent cleaning device, computer storage medium |
| CN201811295518.7A Pending CN109452914A (en) | 2018-11-01 | 2018-11-01 | Intelligent cleaning equipment, cleaning mode selection method, computer storage medium |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111500223.0A Pending CN114424916A (en) | 2018-11-01 | 2018-11-01 | Cleaning mode selection method, intelligent cleaning device, computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN114424916A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110674731A (en) * | 2019-09-22 | 2020-01-10 | 江苏悦达专用车有限公司 | Road cleanliness quantification method based on deep learning |
| CN111012261A (en) * | 2019-11-18 | 2020-04-17 | 深圳市杉川机器人有限公司 | Sweeping method and system based on scene recognition, sweeping equipment and storage medium |
| CN111096714A (en) * | 2019-12-25 | 2020-05-05 | 江苏美的清洁电器股份有限公司 | Control system and method of sweeping robot and sweeping robot |
| CN111248815A (en) * | 2020-01-16 | 2020-06-09 | 珠海格力电器股份有限公司 | Method, device and equipment for generating working map and storage medium |
| CN111476098A (en) * | 2020-03-06 | 2020-07-31 | 珠海格力电器股份有限公司 | Method, device, terminal and computer readable medium for identifying target area |
| CN111528739A (en) * | 2020-05-09 | 2020-08-14 | 小狗电器互联网科技（北京）股份有限公司 | Sweeping mode switching method and system, electronic equipment, storage medium and sweeper |
| CN111759226A (en) * | 2019-04-02 | 2020-10-13 | 青岛塔波尔机器人技术股份有限公司 | Sweeping robot control method and sweeping robot |
| 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 |
| CN112690704A (en) * | 2020-12-22 | 2021-04-23 | 珠海市一微半导体有限公司 | Robot control method, control system and chip based on vision and laser fusion |
| CN114305208A (en) * | 2021-12-17 | 2022-04-12 | 深圳市倍思科技有限公司 | Driving method, device, equipment, program product and system of intelligent cleaning equipment |
| CN114468857A (en) * | 2022-02-17 | 2022-05-13 | 美智纵横科技有限责任公司 | Control method and device of cleaning equipment, cleaning equipment and readable storage medium |
| CN115413959A (en) * | 2021-05-12 | 2022-12-02 | 美智纵横科技有限责任公司 | Operation method and device based on cleaning robot, electronic equipment and medium |
| WO2023125698A1 (en) * | 2021-12-28 | 2023-07-06 | 美智纵横科技有限责任公司 | Cleaning device, and control method and control apparatus therefor |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106155049A (en) * | 2015-04-15 | 2016-11-23 | 小米科技有限责任公司 | Intelligent cleaning equipment and bootstrap technique, guiding stake, intelligent cleaning system |
| CN106228177A (en) * | 2016-06-30 | 2016-12-14 | 浙江大学 | Daily life subject image recognition methods based on convolutional neural networks |
| CN106821157A (en) * | 2017-04-14 | 2017-06-13 | 小狗电器互联网科技（北京）股份有限公司 | The cleaning method that a kind of sweeping robot is swept the floor |
| WO2018038553A1 (en) * | 2016-08-25 | 2018-03-01 | 엘지전자 주식회사 | Mobile robot and control method therefor |
| CN108125622A (en) * | 2017-12-15 | 2018-06-08 | 珊口（上海）智能科技有限公司 | Control method, system and the clean robot being applicable in |
| CN108594692A (en) * | 2017-12-18 | 2018-09-28 | 深圳市奇虎智能科技有限公司 | A kind of cleaning equipment control method, device, computer equipment and storage medium |
| CN108681752A (en) * | 2018-05-28 | 2018-10-19 | 电子科技大学 | A kind of image scene mask method based on deep learning |
| CN108710847A (en) * | 2018-05-15 | 2018-10-26 | 北京旷视科技有限公司 | Scene recognition method, device and electronic equipment |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105138963A (en) * | 2015-07-31 | 2015-12-09 | 小米科技有限责任公司 | Picture scene judging method, picture scene judging device and server |
| CN105809146B (en) * | 2016-03-28 | 2019-08-30 | 北京奇艺世纪科技有限公司 | A kind of image scene recognition methods and device |
| CN106446930B (en) * | 2016-06-28 | 2019-11-22 | 沈阳工业大学 | Robot operative scenario recognition methods based on deep layer convolutional neural networks |
| CN107092254B (en) * | 2017-04-27 | 2019-11-29 | 北京航空航天大学 | A kind of design method of the Household floor-sweeping machine device people based on depth enhancing study |
| CN107688856B (en) * | 2017-07-24 | 2020-11-06 | 清华大学 | Indoor robot scene active identification method based on deep reinforcement learning |
| JP7203844B2 (en) * | 2017-07-25 | 2023-01-13 | 達闥機器人股▲分▼有限公司 | Training data generation method, generation device, and semantic segmentation method for the image |
| CN107622244B (en) * | 2017-09-25 | 2020-08-28 | 华中科技大学 | Indoor scene fine analysis method based on depth map |
| CN107944386B (en) * | 2017-11-22 | 2019-11-22 | 天津大学 | Visual scene recognition methods based on convolutional neural networks |
| CN108523768B (en) * | 2018-03-12 | 2020-09-18 | 苏州大学 | Household cleaning robot control system based on self-adaptive strategy optimization |
-
2018
- 2018-11-01 CN CN202111500223.0A patent/CN114424916A/en active Pending
- 2018-11-01 CN CN201811295518.7A patent/CN109452914A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106155049A (en) * | 2015-04-15 | 2016-11-23 | 小米科技有限责任公司 | Intelligent cleaning equipment and bootstrap technique, guiding stake, intelligent cleaning system |
| CN106228177A (en) * | 2016-06-30 | 2016-12-14 | 浙江大学 | Daily life subject image recognition methods based on convolutional neural networks |
| WO2018038553A1 (en) * | 2016-08-25 | 2018-03-01 | 엘지전자 주식회사 | Mobile robot and control method therefor |
| CN106821157A (en) * | 2017-04-14 | 2017-06-13 | 小狗电器互联网科技（北京）股份有限公司 | The cleaning method that a kind of sweeping robot is swept the floor |
| CN108125622A (en) * | 2017-12-15 | 2018-06-08 | 珊口（上海）智能科技有限公司 | Control method, system and the clean robot being applicable in |
| CN108594692A (en) * | 2017-12-18 | 2018-09-28 | 深圳市奇虎智能科技有限公司 | A kind of cleaning equipment control method, device, computer equipment and storage medium |
| CN108710847A (en) * | 2018-05-15 | 2018-10-26 | 北京旷视科技有限公司 | Scene recognition method, device and electronic equipment |
| CN108681752A (en) * | 2018-05-28 | 2018-10-19 | 电子科技大学 | A kind of image scene mask method based on deep learning |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111759226B (en) * | 2019-04-02 | 2022-12-20 | 青岛塔波尔机器人技术股份有限公司 | Sweeping robot control method and sweeping robot |
| CN111759226A (en) * | 2019-04-02 | 2020-10-13 | 青岛塔波尔机器人技术股份有限公司 | Sweeping robot control method and sweeping robot |
| 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 |
| CN110674731A (en) * | 2019-09-22 | 2020-01-10 | 江苏悦达专用车有限公司 | Road cleanliness quantification method based on deep learning |
| CN111012261A (en) * | 2019-11-18 | 2020-04-17 | 深圳市杉川机器人有限公司 | Sweeping method and system based on scene recognition, sweeping equipment and storage medium |
| WO2021098536A1 (en) * | 2019-11-18 | 2021-05-27 | 深圳市杉川机器人有限公司 | Cleaning method and system employing scene recognition, sweeping device, and storage medium |
| CN111096714A (en) * | 2019-12-25 | 2020-05-05 | 江苏美的清洁电器股份有限公司 | Control system and method of sweeping robot and sweeping robot |
| CN111096714B (en) * | 2019-12-25 | 2024-05-10 | 美智纵横科技有限责任公司 | Control system and method of sweeping robot and sweeping robot |
| CN111248815A (en) * | 2020-01-16 | 2020-06-09 | 珠海格力电器股份有限公司 | Method, device and equipment for generating working map and storage medium |
| CN111476098A (en) * | 2020-03-06 | 2020-07-31 | 珠海格力电器股份有限公司 | Method, device, terminal and computer readable medium for identifying target area |
| CN111528739A (en) * | 2020-05-09 | 2020-08-14 | 小狗电器互联网科技（北京）股份有限公司 | Sweeping mode switching method and system, electronic equipment, storage medium and sweeper |
| CN112690704A (en) * | 2020-12-22 | 2021-04-23 | 珠海市一微半导体有限公司 | Robot control method, control system and chip based on vision and laser fusion |
| CN115413959A (en) * | 2021-05-12 | 2022-12-02 | 美智纵横科技有限责任公司 | Operation method and device based on cleaning robot, electronic equipment and medium |
| CN114305208A (en) * | 2021-12-17 | 2022-04-12 | 深圳市倍思科技有限公司 | Driving method, device, equipment, program product and system of intelligent cleaning equipment |
| WO2023125698A1 (en) * | 2021-12-28 | 2023-07-06 | 美智纵横科技有限责任公司 | Cleaning device, and control method and control apparatus therefor |
| CN114468857A (en) * | 2022-02-17 | 2022-05-13 | 美智纵横科技有限责任公司 | Control method and device of cleaning equipment, cleaning equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114424916A (en) | 2022-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109452914A (en) | Intelligent cleaning equipment, cleaning mode selection method, computer storage medium | |
| CN110174888B (en) | Self-moving robot control method, device, equipment and storage medium | |
| CN111543902A (en) | Floor cleaning method and device, intelligent cleaning equipment and storage medium | |
| CN110751721A (en) | Furniture layout drawing generation method and device, computer equipment and storage medium | |
| Luperto et al. | A system for building semantic maps of indoor environments exploiting the concept of building typology | |
| CN108107886B (en) | Driving control method and device of sweeping robot and sweeping robot | |
| CN106979599A (en) | Household appliance control method and device, server | |
| CN111643014A (en) | Intelligent cleaning method and device, intelligent cleaning equipment and storage medium | |
| CN107316308A (en) | A kind of clean robot map dividing method based on improved multi-path spectral clustering algorithm | |
| Nguyen et al. | Recognising behaviours of multiple people with hierarchical probabilistic model and statistical data association | |
| Beckage et al. | More complex complexity: Exploring the nature of computational irreducibility across physical, biological, and human social systems | |
| WO2020179686A1 (en) | Equipment control system | |
| CN111738074B (en) | Pedestrian attribute identification method, system and device based on weak supervision learning | |
| CN110781595A (en) | Energy use efficiency PUE prediction method, device, terminal and medium | |
| CN114089752A (en) | Autonomous exploration method for robot, and computer-readable storage medium | |
| Saha et al. | Online area covering robot in unknown dynamic environments | |
| Louis-Lucas et al. | Role of green roofs in urban connectivity, an exploratory approach using landscape graphs in the city of Paris, France | |
| US20230154296A1 (en) | Identifying regions of interest in an imaging field of view | |
| CN110824930B (en) | Control method, device and system of household appliance | |
| WO2022012471A1 (en) | Control method for self-moving device, apparatus, storage medium, and self-moving device | |
| Nickahdar et al. | Smart sustainable neighbourhood design: A prototype for Bahrain | |
| WO2022152875A2 (en) | Situation assessment by way of object recognition in autonomous mobile robots | |
| Bin Mostafiz et al. | Automated health monitoring and watering system for plants (plant nursing system) | |
| Lay | Development of a synthesis concept for the Smart City Maun Science Park: Integration of (digitally) re-programmable space by using the Internet of Things | |
| Al-Ani | Reinforcement learning in home energy management systems: tutorial, survey and application |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information |
Address after: 100192 No. 6016, 6017, 6018, Block C, No. 8 Heiquan Road, Haidian District, Beijing Applicant after: Beijing Roborock Technology Co.,Ltd. Address before: 100192 No. 6016, 6017, 6018, Block C, No. 8 Heiquan Road, Haidian District, Beijing Applicant before: BEIJING ROCKROBO TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190312 |
|
| RJ01 | Rejection of invention patent application after publication |