CN114794953A - Intelligent cleaning robot welt cleaning system and method based on deep learning - Google Patents
Intelligent cleaning robot welt cleaning system and method based on deep learning Download PDFInfo
- Publication number
- CN114794953A CN114794953A CN202210410368.XA CN202210410368A CN114794953A CN 114794953 A CN114794953 A CN 114794953A CN 202210410368 A CN202210410368 A CN 202210410368A CN 114794953 A CN114794953 A CN 114794953A
- Authority
- CN
- China
- Prior art keywords
- cleaning
- module
- cleaning robot
- glass
- sensing module
- 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
- 238000004140 cleaning Methods 0.000 title claims abstract description 282
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000013135 deep learning Methods 0.000 title claims abstract description 18
- 239000011521 glass Substances 0.000 claims abstract description 92
- 230000009471 action Effects 0.000 claims abstract description 72
- 239000000428 dust Substances 0.000 claims description 23
- 230000000875 corresponding effect Effects 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 17
- 230000001276 controlling effect Effects 0.000 claims description 11
- 230000007246 mechanism Effects 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 7
- 230000003749 cleanliness Effects 0.000 claims description 6
- 238000001179 sorption measurement Methods 0.000 claims description 6
- 230000006378 damage Effects 0.000 claims description 5
- 208000027418 Wounds and injury Diseases 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 208000014674 injury Diseases 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 239000004744 fabric Substances 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
Images
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
- A47L1/00—Cleaning windows
- A47L1/02—Power-driven machines or devices
-
- 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
-
- 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
-
- 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
- A47L11/4061—Steering means; Means for avoiding obstacles; Details related to the place where the driver is accommodated
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- A47L2201/04—Automatic control of the travelling movement; Automatic obstacle detection
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Electric Vacuum Cleaner (AREA)
Abstract
The invention discloses an intelligent cleaning robot welt cleaning system and method based on deep learning, and relates to the technical field of cleaning robots. According to the intelligent cleaning robot welt cleaning system and method based on deep learning, cleaning actions and cleaning combination actions are preset, so that the cleaning robot can independently learn the cleaning actions, and further when the cleaning robot encounters a cleaning obstacle problem, the cleaning robot can automatically convert the cleaning actions into corresponding cleaning actions to complete the cleaning work of glass, and the working efficiency is improved.
Description
Technical Field
The invention relates to the technical field of cleaning robots, in particular to an intelligent cleaning robot welt cleaning system and method based on deep learning.
Background
In daily life, people generally use cleaning cloth to clean small pieces of glass, rod type glass cleaning cloth is generally used to clean large pieces of glass and the outer vertical surfaces of windows, however, when the rod type glass cleaning cloth is used to clean the glass, arms are easy to fatigue, and when outdoor glass is cleaned, particularly for high-rise buildings, the operation process is very dangerous, so that an intelligent cleaning robot appears in the market, can replace manpower, and saves the labor intensity.
However, when the existing glass cleaning robot is used for cleaning, the randomness is high, and each position of glass cannot be cleaned, so that the cleaned glass still has stains, and the defect is not correspondingly improved.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent cleaning robot welting cleaning system and method based on deep learning, and solves the problems that the existing glass cleaning robot is large in randomness and cannot clean every position of glass, and therefore the cleaned glass still has stains.
In order to achieve the purpose, the invention is realized by the following technical scheme: clean system of intelligence cleaning machines people hem based on degree of deep learning, including master control CPU and detecting element, learning system, the control unit and cleaning machines people, through wireless connection between detecting element and the master control CPU, master control CPU and learning system electric connection, electric connection between learning system and the control unit, later the control unit carries out work through wireless remote control cleaning machines people.
The cleaning robot comprises a detection unit, a learning system, a control unit and a cleaning robot, wherein the detection unit is used for detecting the working state of the cleaning robot and the cleaned glass on line, the learning system automatically learns the cleaning action step by self and combines the information monitored by the detection unit, the cleaning robot automatically selects the corresponding cleaning action, and then the control unit is used for controlling the cleaning robot to clean the glass.
Furthermore, the detection unit comprises an ultrasonic sensing module, an attitude sensing module, a pressure sensing module, a dust sensing module, a speed sensing module, a signal receiving module and a data threshold module, wherein the ultrasonic sensing module is used for detecting the distance between the cleaning robot and a barrier on the glass, the attitude sensing module is used for detecting the attitude condition of the cleaning robot, the pressure sensing module is used for detecting the adsorption pressure between the cleaning robot and the glass to ensure that the cleaning robot cannot crush the glass and also cannot fall off the glass, the dust sensing module is used for detecting the dust on the glass to judge the cleanliness of the glass after cleaning, the speed sensing module is used for detecting the walking speed of the cleaning robot during cleaning, and the signal receiving module respectively performs comparison on the ultrasonic sensing module, the attitude sensing module, the dust sensing module and the data threshold module, And the information detected by the pressure sensing module, the dust sensing module and the speed sensing module is collected and received.
Further, the attitude conditions detected by the attitude sensing module include cleaning angle determination, cleaning position determination, cleaning route, automatic calibration of angle drift caused by changes of self characteristics, electromagnetism and environment in a sensing running state, and parameter reading and backup.
Further, the data threshold value module sets up the parameter of cleaning robot in the cleaning in operation, when making ultrasonic sensing module detect predetermined parameter, cleaning robot can automatic change the route of walking, prevent that cleaning robot from producing the collision condition, gesture sensing module can be according to predetermined parameter, make cleaning robot carry out cleaning at predetermined route, all give clean every corner on the glass, pressure sensing module can be according to predetermined parameter, make cleaning robot guarantee that the suction of constant range is attached on glass, guarantee cleaning robot's stability in the cleaning process, can not cause the injury to glass simultaneously.
Furthermore, the learning system comprises an action meta-module, a combined action meta-module, a rule base, a planning module and a learning mechanism module, wherein the action meta-module is used for cleaning each cleaning action of the cleaning robot in the cleaning process, the combined action meta-module combines various cleaning actions in the action meta-module mutually so that the cleaning robot can make corresponding cleaning actions under different conditions, the actions form a rule repository in the rule base, the planning module is used for presetting corresponding measures required when the cleaning robot encounters cleaning obstacles, and the learning mechanism module can enable the cleaning robot to clean according to the preset rules in the planning module and make corresponding action measures.
Furthermore, the control unit comprises a walking control module, a steering control module, a negative pressure control module, a cleaning control module and a speed control module, wherein the walking control module is used for controlling a walking route of the cleaning robot so as to clean all positions on the glass conveniently, the steering control module is used for controlling a steering function of the cleaning robot, the cleaning robot can automatically steer when encountering obstacles and avoid collision, the negative pressure control module is used for controlling a negative pressure value between the cleaning robot and the glass to enable the negative pressure value to be within a preset constant negative pressure range value, the cleaning control module is used for controlling the cleaning robot to clean stains on the glass, and the speed control module is used for controlling the walking speed of the cleaning robot in the process of cleaning the glass.
Furthermore, the steering control module comprises a left steering module, a right steering module, an oblique steering module and a backward steering module, and the steering modules are controlled by a steering motor.
Further, the intelligent cleaning robot welt cleaning method based on deep learning comprises the following steps:
s1, presetting each cleaning action in the cleaning process in the action meta-module in advance, combining the action meta-module to combine various cleaning actions in the action meta-module, making the action meta-module capable of making corresponding cleaning actions under different conditions, forming a rule repository in the rule repository by the actions, presetting corresponding measures required when the cleaning robot meets cleaning obstacles in the planning module, and enabling the cleaning robot to clean according to the rules preset in the planning module and make corresponding action measures by the learning mechanism module;
s2, setting parameters of the cleaning robot in operation during cleaning in a data threshold module, enabling the cleaning robot to automatically change a walking route when an ultrasonic sensing module detects preset parameters, preventing the cleaning robot from colliding, enabling a posture sensing module to perform cleaning work on the preset route according to the preset parameters, cleaning each corner of glass, enabling a pressure sensing module to ensure that suction in a constant range is attached to the glass according to the preset parameters, ensuring the stability of the cleaning robot in the cleaning process, and meanwhile not causing damage to the glass;
s3, the ultrasonic sensing module detects the distance between the cleaning robot and the obstacle on the glass, the attitude sensing module detects the attitude status of the cleaning robot, the pressure sensing module detects the adsorption pressure between the cleaning robot and the glass to ensure that the cleaning robot can not crush the glass and can not fall off the glass, the dust sensing module detects the dust on the glass to judge the cleanliness of the glass after cleaning, the speed sensing module detects the walking speed of the cleaning robot during cleaning, the signal receiving module respectively collects and receives the information detected by the ultrasonic sensing module, the attitude sensing module, the pressure sensing module, the dust sensing module and the speed sensing module, and the cleaning robot cleans the glass according to the collected information and the learned information.
Advantageous effects
The invention provides an intelligent cleaning robot welt cleaning system and method based on deep learning, which have the following beneficial effects compared with the prior art:
1. according to the intelligent cleaning robot welt cleaning system and method based on deep learning, cleaning actions and cleaning combination actions are preset, so that the cleaning robot can independently learn the cleaning actions, and further when the cleaning robot encounters a cleaning obstacle problem, the cleaning robot can automatically convert the cleaning actions into corresponding cleaning actions to complete the cleaning work of glass, and the working efficiency is improved.
2. This intelligence cleaning machines people welt clean system and method based on degree of depth study, through the detection of multiple sensing, guarantee cleaning machines people's stability in the cleaning process, the condition of can not taking place to drop can all give cleanness with every corner on the glass simultaneously, can give clean moreover with glass.
Drawings
FIG. 1 is a functional block diagram of the present invention;
FIG. 2 is a schematic block diagram of a detection unit of the present invention;
FIG. 3 is a functional block diagram of the learning system of the present invention;
fig. 4 is a schematic block diagram of the control unit of the present invention.
In the figure: 1. a main control CPU; 2. a detection unit; 21. an ultrasonic sensing module; 22. an attitude sensing module; 23. a pressure sensing module; 24. a dust sensing module; 25. a speed sensing module; 26. a signal receiving module; 27. a data threshold module; 3. a learning system; 31. an action meta-module; 32. a combined action meta-module; 33. a rule base; 34. a planning module; 35. a learning mechanism module; 4. a control unit; 41. a walking control module; 42. a steering control module; 43. a negative pressure control module; 44. a cleaning control module; 45. a speed control module; 5. the robot is cleaned.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the invention provides a technical solution, an intelligent cleaning robot welt cleaning system based on deep learning, comprising a main control CPU1, a detection unit 2, and a learning system 3, the cleaning robot comprises a control unit 4 and a cleaning robot 5, wherein the detection unit 2 is in wireless connection with a main control CPU1, the main control CPU1 is electrically connected with a learning system 3, the learning system 3 is electrically connected with the control unit 4, then the control unit 4 controls the cleaning robot 5 to work through wireless remote control, the detection unit 2 carries out online detection work on the working state of the cleaning robot 5 and the cleaned glass, the learning system 3 automatically learns and cleans the glass through the steps of cleaning actions, the cleaning robot 5 automatically selects corresponding cleaning actions according to information monitored by the detection unit 2, and then the control unit 4 controls the cleaning robot 5 to clean the glass.
Referring to fig. 2, in an embodiment of the present invention, the detecting unit 2 includes an ultrasonic sensing module 21, an attitude sensing module 22, a pressure sensing module 23, a dust sensing module 24, a speed sensing module 25, a signal receiving module 26, and a data threshold module 27, the ultrasonic sensing module 21 is configured to detect a distance between the cleaning robot 5 and an obstacle on the glass, the attitude sensing module 22 is configured to detect an attitude status of the cleaning robot 5, the pressure sensing module 23 is configured to detect an adsorption pressure between the cleaning robot 5 and the glass, so as to ensure that the cleaning robot 5 does not crush the glass and also does not fall off the glass, the dust sensing module 24 is configured to detect dust on the glass, determine cleanliness of the glass after cleaning, the speed sensing module 25 is configured to detect a traveling speed of the cleaning robot 5 during cleaning, and the signal receiving module 26 is respectively configured to the ultrasonic sensing module 21 and the attitude sensing module 22, The information detected by the pressure sensing module 23, the dust sensing module 24 and the speed sensing module 25 is collected and received, the gesture status detected by the gesture sensing module 22 includes cleaning angle determination, cleaning position determination, cleaning route, automatic calibration of angle drift caused by self characteristics, electromagnetism and environment changes in a sensing running state, parameter reading and backup are realized, the data threshold module 27 sets parameters in the cleaning running process of the cleaning robot 5, when the ultrasonic sensing module 21 detects preset parameters, the cleaning robot 5 can automatically change the running route to prevent the collision of the cleaning robot 5, the gesture sensing module 22 can enable the cleaning robot 5 to perform cleaning work in the preset route according to the preset parameters, each corner on the glass is cleaned, the pressure sensing module 23 can perform cleaning work according to the preset parameters, make cleaning robot 5 guarantee that the suction of constant within range is attached on glass, guarantee cleaning robot 5 stability in the cleaning process, can not cause the injury to glass simultaneously.
Referring to fig. 3, in the embodiment of the present invention, the learning system 3 includes an action meta-module 31, a combined action meta-module 32, a rule base 33, a planning module 34, and a learning mechanism module 35, where the action meta-module 31 is each cleaning action of the cleaning robot 5 in the cleaning process, the combined action meta-module 32 combines various cleaning actions in the action meta-module 31 to enable the cleaning robot to perform corresponding cleaning actions under different conditions, the actions form a rule repository in the rule base 33, the planning module 34 is used for presetting corresponding measures required when the cleaning robot 5 encounters a cleaning obstacle, and the learning mechanism module 35 enables the cleaning robot 5 to perform cleaning according to rules preset in the planning module 34 and perform corresponding action measures.
Referring to fig. 4, in the embodiment of the present invention, the control unit 4 includes a walking control module 41, a steering control module 42, a negative pressure control module 43, a cleaning control module 44, and a speed control module 45, the walking control module 41 is configured to control a walking path of the cleaning robot 5, so as to facilitate cleaning of each position on the glass, the steering control module 42 is configured to control a steering function of the cleaning robot 5, when the cleaning robot 5 encounters an obstacle, the cleaning robot can automatically steer to avoid collision, the negative pressure control module 43 is configured to control a negative pressure value between the cleaning robot 5 and the glass to be within a preset constant negative pressure range value, the cleaning control module 44 is configured to control the cleaning robot 5 to perform cleaning of stains on the glass, the speed control module 45 is configured to control a walking speed of the cleaning robot 5 during cleaning of the glass, the steering control module 42 includes left and right steering, diagonal steering, and reverse steering, which are controlled by a steering motor.
In the embodiment of the invention, the intelligent cleaning robot welt cleaning method based on deep learning comprises the following steps:
s1, presetting each cleaning action in the cleaning process in advance in the action element module 31, combining the action element module 32 to combine the cleaning actions in the action element module 31, so that the cleaning actions can be made correspondingly under different conditions, these actions form a rule repository in the rule repository 33, presetting corresponding measures in the planning module 34 when the cleaning robot 5 encounters a cleaning obstacle, and the learning mechanism module 35 can make the cleaning robot 5 perform cleaning according to the rules preset in the planning module 34 and make corresponding action measures;
s2, setting parameters of the cleaning robot 5 during cleaning operation in the data threshold module 27, so that when the ultrasonic sensing module 21 detects preset parameters, the cleaning robot 5 will automatically change a walking route to prevent the cleaning robot 5 from colliding, and the posture sensing module 22 will perform cleaning work on the cleaning robot 5 in the preset route according to the preset parameters, so as to clean each corner of the glass, and the pressure sensing module 23 will attach the cleaning robot 5 to the glass with a suction force within a guaranteed constant range according to the preset parameters, so as to ensure the stability of the cleaning robot 5 during cleaning, and at the same time, not to damage the glass;
s3, the ultrasonic sensing module 21 detects the distance between the cleaning robot 5 and an obstacle on the glass, the attitude sensing module 22 detects the working attitude condition of the cleaning robot 5, the pressure sensing module 23 detects the adsorption pressure between the cleaning robot 5 and the glass, the cleaning robot 5 is guaranteed not to crush the glass and not to fall off from the glass, the dust sensing module 24 detects dust on the glass and judges the cleanliness of the glass after cleaning, the speed sensing module 25 detects the walking speed of the cleaning robot 5 during cleaning, the signal receiving module 26 respectively collects and receives the information detected by the ultrasonic sensing module 21, the attitude sensing module 22, the pressure sensing module 23, the dust sensing module 24 and the speed sensing module 25, and the cleaning robot 5 cleans the glass according to the collected information and the learned information.
And those not described in detail in this specification are well within the skill of those in the art.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Claims (8)
1. Clean system of intelligent cleaning robot welt based on degree of depth study, its characterized in that: the cleaning robot comprises a main control CPU (1), a detection unit (2), a learning system (3), a control unit (4) and a cleaning robot (5), wherein the detection unit (2) is in wireless connection with the main control CPU (1), the main control CPU (1) is electrically connected with the learning system (3), the learning system (3) is electrically connected with the control unit (4), and then the control unit (4) controls the cleaning robot (5) to work in a wireless remote mode;
the detection unit (2) detects the working state of the cleaning robot (5) and the cleaned glass on line, the learning system (3) automatically learns the cleaning action step and automatically selects the corresponding cleaning action by combining the information monitored by the detection unit (2), and then the control unit (4) controls the cleaning robot (5) to clean the glass.
2. The intelligent cleaning robot welt cleaning system based on deep learning of claim 1, wherein: the detection unit (2) comprises an ultrasonic sensing module (21), a posture sensing module (22), a pressure sensing module (23), a dust sensing module (24), a speed sensing module (25), a signal receiving module (26) and a data threshold value module (27), wherein the ultrasonic sensing module (21) is used for detecting the distance between the cleaning robot (5) and an obstacle on the glass, the posture sensing module (22) is used for detecting the working posture condition of the cleaning robot (5), the pressure sensing module (23) is used for detecting the adsorption pressure between the cleaning robot (5) and the glass, so that the cleaning robot (5) cannot crush the glass and cannot fall off from the glass, the dust sensing module (24) is used for detecting the dust on the glass and judging the cleanliness of the glass after cleaning, and the speed sensing module (25) is used for detecting the walking speed of the cleaning robot (5) during cleaning, the signal receiving module (26) respectively collects and receives information detected by the ultrasonic sensing module (21), the attitude sensing module (22), the pressure sensing module (23), the dust sensing module (24) and the speed sensing module (25).
3. The intelligent cleaning robot welt cleaning system based on deep learning of claim 2, wherein: the attitude conditions detected by the attitude sensing module (22) comprise cleaning angle judgment, cleaning position judgment, cleaning route, automatic calibration of angle drift caused by self characteristics, electromagnetism and environment change in a sensing running state, and parameter reading and backup.
4. The intelligent cleaning robot welt cleaning system based on deep learning of claim 2, wherein: data threshold value module (27) sets up the parameter of cleaning robot (5) in the clear operation, when making ultrasonic sensing module (21) detect predetermined parameter, cleaning robot (5) can change the walking route automatically, prevent that cleaning robot (5) from taking place the condition of colliding, gesture sensing module (22) can be according to predetermined parameter, make cleaning robot (5) carry out cleaning work at predetermined route, give every corner on the glass and clean, pressure sensing module (23) can be according to predetermined parameter, make cleaning robot (5) guarantee that the suction of constant range is attached on glass, guarantee cleaning robot (5) the stability of cleaning process, can not cause the injury to glass simultaneously.
5. The intelligent cleaning robot welt cleaning system based on deep learning of claim 1, wherein: the learning system (3) comprises an action meta-module (31), a combined action meta-module (32), a rule base (33), a planning module (34) and a learning mechanism module (35), the action meta-module (31) is used for cleaning each cleaning action of the cleaning robot (5) in the cleaning process, the combined action meta-module (32) combines various cleaning actions in the action meta-module (31) mutually so as to make the combined action meta-module capable of responding to the corresponding cleaning actions under different conditions, the actions form a rule repository in a rule base (33), the planning module (34) is used for presetting corresponding measures required to be taken when the cleaning robot (5) encounters a cleaning obstacle, the learning mechanism module (35) enables the cleaning robot (5) to clean according to rules preset in the planning module (34) and to take corresponding action measures.
6. The intelligent cleaning robot welt cleaning system based on deep learning of claim 1, wherein: the control unit (4) comprises a walking control module (41), a steering control module (42), a negative pressure control module (43), a cleaning control module (44) and a speed control module (45), wherein the walking control module (41) is used for controlling a walking route of the cleaning robot (5) so as to conveniently clean each position on the glass, the steering control module (42) is used for controlling a steering function of the cleaning robot (5), the cleaning robot (5) can automatically steer to avoid collision when encountering obstacles, the negative pressure control module (43) is used for controlling a negative pressure value between the cleaning robot (5) and the glass to enable the negative pressure value to be within a preset constant negative pressure range value, the cleaning control module (44) is used for controlling the cleaning robot (5) to clean stains on the glass, and the speed control module (45) is used for controlling the cleaning robot (5) in the process of cleaning the glass, the speed of walking.
7. The intelligent cleaning robot welt cleaning system based on deep learning of claim 6, wherein: the steering control module (42) comprises a left steering module, a right steering module, an oblique steering module and a backward steering module, and the steering modules are controlled by a steering motor.
8. Intelligent cleaning robot welt cleaning method based on degree of depth study, its characterized in that: a cleaning system comprising any one of claims 1 to 7, the method comprising the steps of:
s1, presetting each cleaning action in the cleaning process in the action meta-module (31) in advance, combining the action meta-module (32) to combine various cleaning actions in the action meta-module (31) mutually to make the action meta-module capable of making corresponding cleaning actions under different conditions, forming a rule repository in the rule repository (33) by the actions, presetting corresponding measures required when the cleaning robot (5) meets cleaning obstacles in the planning module (34), and enabling the cleaning robot (5) to clean according to the rules preset in the planning module (34) by the learning mechanism module (35) and making corresponding action measures;
s2, setting parameters of the cleaning robot (5) in cleaning operation in a data threshold module (27), enabling the cleaning robot (5) to automatically change a walking route when the ultrasonic sensing module (21) detects preset parameters, preventing the cleaning robot (5) from colliding, enabling the cleaning robot (5) to clean the glass in the preset route according to the preset parameters by the attitude sensing module (22), and enabling the cleaning robot (5) to ensure that suction in a constant range is attached to the glass according to the preset parameters by the pressure sensing module (23), so that the stability of the cleaning robot (5) in the cleaning process is ensured, and the glass cannot be damaged;
s3, detecting the distance between the cleaning robot (5) and an obstacle on the glass by the ultrasonic sensing module (21), detecting the working posture condition of the cleaning robot (5) by the posture sensing module (22), detecting the adsorption pressure between the cleaning robot (5) and the glass by the pressure sensing module (23) to ensure that the cleaning robot (5) cannot crush the glass and fall off the glass, detecting the dust on the glass by the dust sensing module (24) to judge the cleanliness of the glass after cleaning, detecting the walking speed of the cleaning robot (5) by the speed sensing module (25), and respectively detecting the ultrasonic sensing module (21) and the posture sensing module (22) by the signal receiving module (26), the pressure sensing module (23), the dust sensing module (24) and the speed sensing module (25) collect and receive the detected information, and the cleaning robot (5) cleans the glass according to the collected information and the learned information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210410368.XA CN114794953A (en) | 2022-04-19 | 2022-04-19 | Intelligent cleaning robot welt cleaning system and method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210410368.XA CN114794953A (en) | 2022-04-19 | 2022-04-19 | Intelligent cleaning robot welt cleaning system and method based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114794953A true CN114794953A (en) | 2022-07-29 |
Family
ID=82506461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210410368.XA Pending CN114794953A (en) | 2022-04-19 | 2022-04-19 | Intelligent cleaning robot welt cleaning system and method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114794953A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118587813A (en) * | 2024-08-05 | 2024-09-03 | 广东君箭智能有限公司 | Automatic vending machine management system |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5032775A (en) * | 1989-06-07 | 1991-07-16 | Kabushiki Kaisha Toshiba | Control apparatus for plane working robot |
| WO2003090981A1 (en) * | 2002-04-26 | 2003-11-06 | Honda Giken Kogyo Kabushiki Kaisha | System for estimating attitude of leg type moving robot itself |
| CN103845002A (en) * | 2012-11-30 | 2014-06-11 | 三星电子株式会社 | Cleaning robot and control method thereof |
| CN104932534A (en) * | 2015-05-22 | 2015-09-23 | 广州大学 | Method for cloud robot to clean items |
| CN206543159U (en) * | 2016-11-25 | 2017-10-10 | 北京恒通绿建节能科技有限公司 | Floor cleaning device, aircleaning facility and two-in-one device |
| CN107378971A (en) * | 2017-09-08 | 2017-11-24 | 南京阿凡达机器人科技有限公司 | A kind of Study of Intelligent Robot Control system |
| US20180267489A1 (en) * | 2017-03-15 | 2018-09-20 | Fanuc Corporation | Cleaning process optimization device and machine learning device |
| KR20180134155A (en) * | 2017-06-08 | 2018-12-18 | 엘지전자 주식회사 | Robot cleaner and robot cleaning system |
| CN109984664A (en) * | 2017-12-29 | 2019-07-09 | 科沃斯机器人股份有限公司 | Multimedium Intelligent cleaning robot and its control method |
| CN110063694A (en) * | 2019-04-28 | 2019-07-30 | 彭春生 | A kind of binocular sweeping robot and working method |
| KR20190109659A (en) * | 2018-03-08 | 2019-09-26 | 양창학 | Robot scavenger apparatus for cleaning window |
| JP2020181434A (en) * | 2019-04-26 | 2020-11-05 | アマノ株式会社 | Autonomous traveling work apparatus and autonomous traveling work system |
| CN112387627A (en) * | 2019-08-19 | 2021-02-23 | 长鑫存储技术有限公司 | Cleaning mechanism, cleaning vehicle and automatic material carrying system |
| CN113475977A (en) * | 2021-06-22 | 2021-10-08 | 深圳拓邦股份有限公司 | Robot path planning method and device and robot |
-
2022
- 2022-04-19 CN CN202210410368.XA patent/CN114794953A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5032775A (en) * | 1989-06-07 | 1991-07-16 | Kabushiki Kaisha Toshiba | Control apparatus for plane working robot |
| WO2003090981A1 (en) * | 2002-04-26 | 2003-11-06 | Honda Giken Kogyo Kabushiki Kaisha | System for estimating attitude of leg type moving robot itself |
| CN103845002A (en) * | 2012-11-30 | 2014-06-11 | 三星电子株式会社 | Cleaning robot and control method thereof |
| CN104932534A (en) * | 2015-05-22 | 2015-09-23 | 广州大学 | Method for cloud robot to clean items |
| CN206543159U (en) * | 2016-11-25 | 2017-10-10 | 北京恒通绿建节能科技有限公司 | Floor cleaning device, aircleaning facility and two-in-one device |
| US20180267489A1 (en) * | 2017-03-15 | 2018-09-20 | Fanuc Corporation | Cleaning process optimization device and machine learning device |
| KR20180134155A (en) * | 2017-06-08 | 2018-12-18 | 엘지전자 주식회사 | Robot cleaner and robot cleaning system |
| CN107378971A (en) * | 2017-09-08 | 2017-11-24 | 南京阿凡达机器人科技有限公司 | A kind of Study of Intelligent Robot Control system |
| CN109984664A (en) * | 2017-12-29 | 2019-07-09 | 科沃斯机器人股份有限公司 | Multimedium Intelligent cleaning robot and its control method |
| KR20190109659A (en) * | 2018-03-08 | 2019-09-26 | 양창학 | Robot scavenger apparatus for cleaning window |
| JP2020181434A (en) * | 2019-04-26 | 2020-11-05 | アマノ株式会社 | Autonomous traveling work apparatus and autonomous traveling work system |
| CN110063694A (en) * | 2019-04-28 | 2019-07-30 | 彭春生 | A kind of binocular sweeping robot and working method |
| CN112387627A (en) * | 2019-08-19 | 2021-02-23 | 长鑫存储技术有限公司 | Cleaning mechanism, cleaning vehicle and automatic material carrying system |
| CN113475977A (en) * | 2021-06-22 | 2021-10-08 | 深圳拓邦股份有限公司 | Robot path planning method and device and robot |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118587813A (en) * | 2024-08-05 | 2024-09-03 | 广东君箭智能有限公司 | Automatic vending machine management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110448241B (en) | Robot trapped detection and escaping method | |
| JP6290943B2 (en) | Robot cleaner and control method of robot cleaner | |
| EP3302203B1 (en) | A method of controlling a mobile robot | |
| CN103349531B (en) | The side of robot cleaner returns charging method | |
| CN105700531A (en) | Customized map-based household sweeping robot used for two-storey house and sweeping method thereof | |
| CN108261150B (en) | Intelligent floor wiping machine and working state automatic identification protection method thereof | |
| US11458628B1 (en) | Method for efficient operation of mobile robotic devices | |
| CN108241373A (en) | Barrier-avoiding method and intelligent robot | |
| CN113017518A (en) | Cleaning control method and device for sweeping and mopping integrated robot | |
| CN114794953A (en) | Intelligent cleaning robot welt cleaning system and method based on deep learning | |
| CN108528395A (en) | A kind of Vehicular intelligent rain scrape control method and system based on image recognition | |
| CN103349530B (en) | Improve the method that robot cleaner charging returns docking reliability | |
| CN113679298B (en) | Robot control method, robot control device, robot, and readable storage medium | |
| KR102122236B1 (en) | Robot cleaner and method for controlling the robot cleaner | |
| KR20200046158A (en) | Robot cleaner and method for controlling thereof | |
| CN114451814B (en) | Automatic walking device and control method for automatic walking device | |
| CN112220413B (en) | Method and device for detecting slippage of sweeping robot and readable storage medium | |
| CN113693501A (en) | Cleaning equipment, cleaning path, cleaning map generation method and cleaning map generation system | |
| KR20050010591A (en) | The control Methode of cleaning path for cleaning robot | |
| KR101641242B1 (en) | Robot cleaner and controlling method thereof | |
| CN112971644B (en) | Cleaning method and device of sweeping robot, storage medium and sweeping robot | |
| WO2024140713A1 (en) | Water supply and drainage module state checking method, system, base, and storage medium | |
| CN108319270B (en) | Automatic dust collection robot optimal path planning method based on historical data analysis | |
| CN117017117A (en) | Control method of cleaning device, cleaning device and storage medium | |
| CN116115121A (en) | Cleaning robot, control method, device and system thereof and storage medium |
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 |