WO2021043287A1

WO2021043287A1 - Carpet detection method and apparatus, sweeping robot and computer storage medium

Info

Publication number: WO2021043287A1
Application number: PCT/CN2020/113586
Authority: WO
Inventors: 杨勇; 吴泽晓; 罗治佳
Original assignee: 深圳市杉川机器人有限公司
Priority date: 2019-09-05
Filing date: 2020-09-04
Publication date: 2021-03-11
Also published as: CN110522360A

Abstract

A carpet detection method and apparatus, a sweeping robot, and a computer storage medium. The carpet detection method comprises: acquiring ground detection data detected by at least one sensor; inputting the ground detection data into a corresponding pre-established regression coefficient model to obtain at least one regression coefficient; using the at least one regression coefficient to perform calculations in accordance with a preset algorithm to obtain a carpet probability value; and when it is determined that the carpet probability value is greater than or equal to a preset probability value, determining that a sweeping robot is located on a carpet. The carpet detection method may use a plurality of sensors to concurrently obtain ground detection data, and by means of the regression coefficient model, obtain a plurality of regression coefficients for carpet detection, which may thus improve the reliability of detection, ensure the accuracy of carpet detection, and increase the speed of carpet detection.

Description

Carpet detection method, device, sweeping robot and computer storage medium

Cross-references to related applications

This disclosure claims the priority of a Chinese patent application filed with the Chinese Patent Office on September 5, 2019, with the application number CN201910838509.6, titled "Carpet Inspection Method, Device, Sweeping Robot, and Computer Storage Medium", the entire content of which is approved Reference is incorporated in this disclosure.

Technical field

The present disclosure relates to the field of sweeping robots, and in particular to a carpet detection method, device, sweeping robot, and computer storage medium.

Background technique

With the rapid development of computer technology and artificial intelligence technology, intelligent robotics technology has gradually become a hot spot in the field of modern robotics research. Among them, the sweeping robot, as the most practical one of the intelligent robots, can use its artificial intelligence to complete the ground cleaning work.

Current intelligent sweeping robots generally use brush sweeping and vacuum methods to suck ground debris into their own dust box, thereby completing the function of ground cleaning. However, the general sweeping robot is limited by the built-in sensors and processing algorithms, and cannot detect special items such as carpets in the room. It also cleans the carpets like regular floors, and cannot effectively remove the garbage and debris on the carpets, or With a simple judgment method using a single sensor, the accuracy of carpet detection is low, and false detection is prone to occur, and the judgment speed is slow, and it is easy to perform wrong cleaning operations on the carpet.

Summary of the invention

In view of the foregoing problems, the present disclosure provides a carpet detection method, device, sweeping robot, and computer storage medium to improve the reliability of carpet detection, ensure the accuracy of carpet detection, and increase the speed of carpet detection.

In order to achieve the above objectives, the present disclosure adopts the following technical solutions:

A carpet detection method, applied to a sweeping robot, includes:

Acquiring ground detection data detected by at least one sensor;

Input the ground detection data into the corresponding pre-established regression coefficient model to obtain at least one regression coefficient;

Using the at least one regression coefficient to perform operations according to a preset algorithm to obtain a carpet probability value;

When it is determined that the probability value of the carpet is greater than or equal to the preset probability value, it is determined that the sweeping robot is located on the carpet.

Preferably, in the carpet detection method, the sensor includes an optical flow image sensor, and the ground detection data includes optical flow image quality;

The "inputting the ground detection data into the corresponding pre-established regression coefficient model to obtain at least one regression coefficient" includes:

The optical flow image quality is smoothed and then input into a pre-established optical flow image regression coefficient model to obtain the optical flow regression coefficient.

Preferably, in the carpet detection method, the sensor includes an infrared sensor, and the ground detection data further includes an infrared signal;

The "inputting the ground detection data into the corresponding pre-established regression coefficient model to obtain at least one regression coefficient" also includes:

The infrared signal is oversampled to obtain the infrared signal sampling value and then input into the pre-established infrared regression coefficient model to obtain the infrared regression coefficient.

Preferably, the carpet detection method further includes:

Acquiring the current value of at least one working motor, inputting the current value of the working motor into a corresponding pre-established regression coefficient model to obtain at least one regression coefficient;

Wherein, the working motor includes a rolling brush motor, a walking motor, and a side brush motor, and the regression coefficient model includes a rolling brush current regression coefficient model, a walking current regression coefficient model, and a side brush current regression coefficient model.

Preferably, in the carpet detection method, the "using the at least one regression coefficient to perform an operation according to a preset algorithm to obtain a carpet probability value" includes:

When it is determined that the regression coefficient is within the corresponding preset regression coefficient range, the probability value of the corresponding weight of the regression coefficient is obtained;

The probability value of each weight obtained is added to obtain the probability value of the carpet.

Preferably, the carpet detection method further includes:

When it is determined that the sweeping robot is located on the carpet and it is determined that the sweeping robot is in the cleaning mode, the suction power of the vacuum cleaner of the sweeping robot is increased.

Preferably, the carpet detection method further includes:

When it is determined that the sweeping robot is located on the carpet and it is determined that the sweeping robot is in the mopping mode, control the sweeping robot to retreat from the carpet area, mark the carpet area and/or send the location of the carpet area to the customer end.

The present disclosure also provides a carpet detection device, which is applied to the sweeping robot, and includes:

The detection data acquisition module is configured to acquire ground detection data detected by at least one sensor;

A regression coefficient calculation module, configured to input the ground detection data into a corresponding pre-established regression coefficient model to obtain at least one regression coefficient;

The carpet probability calculation module is configured to use the at least one regression coefficient to perform calculations according to a preset algorithm to obtain a carpet probability value;

The carpet detection and determination module is configured to determine that the cleaning robot is located on the carpet when it is determined that the probability value of the carpet is greater than or equal to the preset probability value.

The present disclosure also provides a sweeping robot, including a memory, a processor, an optical flow image sensor, and an infrared sensor. The memory is configured to store a computer program, and the processor runs the computer program to make the sweeping robot execute the The carpet detection method.

The present disclosure also provides a computer storage medium, which stores the computer program used in the sweeping robot.

The present disclosure provides a carpet detection method, which is applied to a sweeping robot, including: acquiring ground detection data detected by at least one sensor; inputting the ground detection data into a corresponding pre-established regression coefficient model to obtain at least one Regression coefficient; using the at least one regression coefficient to perform operations according to a preset algorithm to obtain a carpet probability value; when it is determined that the carpet probability value is greater than or equal to the preset probability value, it is determined that the sweeping robot is located on the carpet. The carpet detection method of the present disclosure can simultaneously obtain ground detection data by using multiple sensors, and obtain multiple regression coefficients through the regression coefficient model for carpet detection, thereby improving the reliability of carpet detection and ensuring the accuracy of carpet detection. And improve the speed of carpet detection.

In order to make the above objectives, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with accompanying drawings are described in detail below.

Description of the drawings

In order to explain the technical solutions of the present disclosure more clearly, the drawings that need to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present disclosure, and therefore should not be It is regarded as a limitation of the protection scope of the present disclosure. In each figure, similar components are numbered similarly.

FIG. 1 is a flowchart of a carpet detection method provided in Embodiment 1 of the present disclosure;

2 is a flowchart of a carpet detection method provided in Embodiment 2 of the present disclosure;

FIG. 3 is a flowchart of a carpet detection method provided in Embodiment 3 of the present disclosure;

FIG. 4 is a schematic structural diagram of a carpet detection device provided in Embodiment 4 of the present disclosure.

detailed description

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments.

The components of the embodiments of the present disclosure generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed present disclosure, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work shall fall within the protection scope of the present disclosure.

Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present disclosure are only intended to represent specific features, numbers, steps, operations, elements, components, or combinations of the foregoing, And should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or adding one or more features, numbers, steps, operations, elements, components Or the possibility of a combination of the foregoing.

In addition, the terms "first", "second", "third", etc. are only used for distinguishing description, and cannot be understood as indicating or implying relative importance.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which various embodiments of the present disclosure belong. The terms (such as those defined in commonly used dictionaries) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having idealized or overly formal meanings, Unless clearly defined in various embodiments of the present disclosure.

Example 1

Fig. 1 is a flowchart of a carpet detection method provided in Embodiment 1 of the present disclosure, and the method includes the following steps:

Step S11: Obtain ground detection data detected by at least one sensor.

In the embodiment of the present disclosure, various sensors may be provided in the sweeping robot, for example, current sensors including infrared sensors, ultrasonic sensors, and various motors. When the sweeping robot is working, multiple sensors can be used to perform ground detection at the same time, and ground detection data from multiple sensors can be obtained and analyzed.

In the embodiments of the present disclosure, the above-mentioned ground detection data includes at least one of optical flow image quality and infrared signals, that is, the sweeping robot includes at least one sensor such as a streamer sensor and an infrared sensor, and the sweeping robot is Automatically turn on the above-mentioned sensors when working and obtain various ground detection data.

Step S12: Input the ground detection data into the corresponding pre-established regression coefficient model to obtain at least one regression coefficient.

In the embodiments of the present disclosure, after the ground detection data of various sensors are obtained, various ground data can be input into the corresponding regression coefficient model to obtain the output of the corresponding regression coefficient model. Wherein, the sensor includes an optical flow image sensor, the ground detection data includes optical flow image quality, and obtaining the regression coefficient includes: smoothing the optical flow image quality and inputting it into a pre-established optical flow image regression coefficient model, Obtain the optical flow regression coefficient.

In the implementation of the present disclosure, the above-mentioned sensor further includes an infrared sensor, and the ground detection data also includes an infrared signal. When the regression coefficient is obtained, it includes: over-sampling the infrared signal to obtain an infrared signal sample value and then input it to a pre-established infrared regression In the coefficient model, the infrared regression coefficient is obtained.

In the embodiments of the present disclosure, not only can the sweeping robot be analyzed by the sensor whether it is on the carpet, but also the carpet detection can be carried out by the current of the working motor. The specific principle is that the resistance received by the sweeping robot on the carpet is greater than the smooth floor, so the working motor is The current will increase significantly, so the above step of obtaining the regression coefficient may further include: obtaining the current value of at least one working motor, and inputting the current value of the working motor into the corresponding pre-established regression coefficient model to obtain For at least one regression coefficient; wherein the working motor includes a rolling brush motor, a walking motor, and a side brush motor, and the regression coefficient model includes a rolling brush current regression coefficient model, a walking current regression coefficient model, and a side brush current regression coefficient model.

In the embodiments of the present disclosure, the above-mentioned regression coefficient models established in advance in the sweeping robot are based on a large amount of test data, that is, a large amount of detection data can be obtained after carpet detection with corresponding sensors, and generated based on a large amount of detection data. A machine learning module can also be provided in the sweeping robot, and a regression coefficient model corresponding to the sensor is generated through machine learning when the sweeping robot is working.

Step S13: Use the at least one regression coefficient to perform calculations according to a preset algorithm to obtain a carpet probability value.

In the embodiments of the present disclosure, each regression coefficient model can generate a corresponding regression coefficient according to the input ground detection data, and compare the regression coefficient with the corresponding coefficient range stored in advance. When the regression coefficient is within the corresponding coefficient range, It can be considered that the corresponding sensor has detected the carpet. Specifically, the method includes: obtaining the probability value of the corresponding weight of the regression coefficient when determining that the regression coefficient is within the corresponding preset regression coefficient range; adding the obtained probability values of the weights to obtain the carpet probability value.

In the embodiments of the present disclosure, if the optical flow regression coefficient, walking motor coefficient, rolling brush motor coefficient, side brush motor coefficient, and infrared coefficient are obtained through the sensor, working motor, and corresponding regression coefficient model in the sweeping robot, the carpet probability value is obtained as described above The process includes: determining that the optical flow regression coefficient is within the preset optical flow coefficient range, obtaining the corresponding probability value of the first weight; and/or determining that the rolling brush current regression coefficient is within the preset rolling brush current When the coefficient is within the range, obtain the probability value of the corresponding second weight; and/or when it is determined that the walking current regression coefficient is within the preset walking current coefficient range, obtain the probability value of the corresponding third weight; and/or determine When the side brush current regression coefficient is within the preset side brush current coefficient range, obtain the corresponding probability value of the fourth weight; and/or when it is determined that the infrared regression coefficient is within the preset infrared coefficient range, obtain the corresponding The probability value of the fifth weight of, and the probability value of each weight obtained is added to obtain the probability value of the carpet.

In the embodiments of the present disclosure, the probability values of the weights corresponding to the various regression coefficients mentioned above are also the reliability of detecting the carpet based on the regression coefficients. For example, the sweeping robot mainly uses optical flow image sensors to detect carpets, the probability of the first weight can be set to 50%, and the probability values of the second weight, the third weight, the fourth weight, and the fifth weight can be set to It is 20%, 10%, 10%, and 10%. When the optical flow regression coefficient and the rolling brush current regression coefficient are determined to be within the corresponding coefficient ranges, the probability value of the carpet obtained is 70%. Among them, when the regression coefficient is not in the corresponding coefficient range, the preset probability value of the corresponding weight will not be obtained.

Step S14: When it is determined that the probability value of the carpet is greater than or equal to the preset probability value, it is determined that the sweeping robot is located on the carpet.

In the embodiment of the present disclosure, a preset probability value is also set in the cleaning robot, which is configured to judge with the carpet probability value, so as to determine whether the cleaning robot is located on the carpet. Wherein, the preset probability value can be set to 50%, that is, when the carpet probability value is higher than 50%, it can be determined that the sweeping robot is located on the carpet.

In the embodiments of the present disclosure, multiple sensors can be used to obtain ground detection data at the same time, and multiple regression coefficients with different weights can be obtained through the regression coefficient model for carpet detection, thereby improving the reliability of detection and ensuring the accuracy of carpet detection , And improve the speed of carpet detection.

Example 2

Fig. 2 is a flowchart of a carpet detection method provided in Embodiment 2 of the present disclosure, and the method includes the following steps:

Step S21: Obtain ground detection data detected by at least one sensor.

This step is consistent with the above step S11, and will not be repeated here.

Step S22: Input the ground detection data into the corresponding pre-established regression coefficient model to obtain at least one regression coefficient.

This step is consistent with the above step S12, and will not be repeated here.

Step S23: Use the at least one regression coefficient to perform calculations according to a preset algorithm to obtain a carpet probability value.

This step is consistent with the above step S13, and will not be repeated here.

Step S24: When it is determined that the probability value of the carpet is greater than or equal to the preset probability value, it is determined that the sweeping robot is located on the carpet.

This step is consistent with the above step S14, and will not be repeated here.

Step S25: When it is determined that the cleaning robot is located on the carpet, and it is determined that the cleaning robot is in the cleaning mode, increase the suction power of the vacuum cleaner of the cleaning robot.

In the embodiment of the present disclosure, it is detected that the sweeping robot is located on the carpet through the above method, and when the sweeping robot is in the normal cleaning mode, the vacuum cleaner of the sweeping robot can be controlled to increase the suction power of the vacuum cleaner to effectively clean the carpet. Some cleaning robots equipped with a carpet cleaning mode can switch to the carpet cleaning mode.

Example 3

FIG. 3 is a flowchart of a carpet detection method provided in Embodiment 3 of the present disclosure, and the method includes the following steps:

Step S31: Obtain ground detection data detected by at least one sensor.

This step is consistent with the above step S11, and will not be repeated here.

Step S32: Input the ground detection data into the corresponding pre-established regression coefficient model to obtain at least one regression coefficient.

This step is consistent with the above step S12, and will not be repeated here.

Step S33: Use the at least one regression coefficient to perform calculations according to a preset algorithm to obtain a carpet probability value.

This step is consistent with the above step S13, and will not be repeated here.

Step S34: When it is determined that the probability value of the carpet is greater than or equal to the preset probability value, it is determined that the sweeping robot is located on the carpet.

This step is consistent with the above step S14, and will not be repeated here.

Step S35: When it is determined that the sweeping robot is located on the carpet and it is determined that the sweeping robot is in the mopping mode, control the sweeping robot to retreat from the carpet area, and mark the carpet area and/or move the carpet area The location is sent to the client.

In the embodiment of the present disclosure, it is detected by the above method that the sweeping robot is located on the carpet, and when the sweeping robot is in the mopping mode, the sweeping robot can retreat from the carpet area in the opposite direction, and at the same time can mark the area where the carpet is detected It is a virtual carpet, it can automatically avoid this area when it is in mopping mode next time, and when it is in normal cleaning mode, it can enter this area after increasing the suction power of the vacuum cleaner in advance. Wherein, the sweeping robot can also send the location information of the area where the carpet is detected to the client, so that the user can clear the corresponding virtual carpet mark in the sweeping robot through the client after removing the carpet.

Example 4

The carpet detection device 400 includes:

The detection data acquisition module 410 is configured to acquire ground detection data detected by at least one sensor;

The regression coefficient calculation module 420 is configured to input the ground detection data into a corresponding pre-established regression coefficient model to obtain at least one regression coefficient;

The carpet probability calculation module 430 is configured to use the at least one regression coefficient to perform calculations according to a preset algorithm to obtain a carpet probability value;

The carpet detection and determination module 440 is configured to determine that the sweeping robot is located on the carpet when it is determined that the probability value of the carpet is greater than or equal to the preset probability value.

In the embodiments of the present disclosure, for more detailed functional descriptions of the foregoing modules and units, reference may be made to the content of the corresponding parts in the foregoing embodiments, which will not be repeated here.

In addition, the present disclosure also provides a cleaning robot. The cleaning robot includes a memory, a processor, an optical flow image sensor, and an infrared sensor. The memory can be configured to store a computer program. The processor runs the computer program to make the cleaning robot Perform the above method or the function of each module in the above carpet detection device.

The memory may include a storage program area and a storage data area. The storage program area may store an operating system, an application program required by at least one function (such as a sound playback function or an image playback function, etc.), etc.; the storage data area may store according to the sweeping robot Use the created data (such as audio data or phone book, etc.) and so on. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

This embodiment also provides a computer storage medium configured to store the computer program used in the above-mentioned sweeping robot.

In the several embodiments provided in this application, it should be understood that the disclosed device and method may also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and structural diagrams in the accompanying drawings show the possible implementation architectures and functions of the devices, methods, and computer program products according to multiple embodiments of the present disclosure. And operation. In this regard, each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the module, program segment, or part of code includes one or more Executable instructions. It should also be noted that, in alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two consecutive blocks can actually be executed in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the structure diagram and/or flowchart, and the combination of the blocks in the structure diagram and/or flowchart, can be used as a dedicated hardware-based system that performs specified functions or actions. , Or can be realized by a combination of dedicated hardware and computer instructions.

In addition, the functional modules or units in the various embodiments of the present disclosure may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present disclosure essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a smart phone, a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present disclosure. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes. .

The above are only specific implementations of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present disclosure. It should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

A carpet detection method applied to a sweeping robot, characterized in that it includes:

Acquiring ground detection data detected by at least one sensor;

Input the ground detection data into the corresponding pre-established regression coefficient model to obtain at least one regression coefficient;

Using the at least one regression coefficient to perform operations according to a preset algorithm to obtain a carpet probability value;

When it is determined that the probability value of the carpet is greater than or equal to the preset probability value, it is determined that the sweeping robot is located on the carpet.
The carpet detection method according to claim 1, wherein the sensor comprises an optical flow image sensor, and the ground detection data comprises an optical flow image quality;

The "inputting the ground detection data into the corresponding pre-established regression coefficient model to obtain at least one regression coefficient" includes:

The optical flow image quality is smoothed and then input into a pre-established optical flow image regression coefficient model to obtain the optical flow regression coefficient.
The carpet detection method according to claim 2, wherein the sensor comprises an infrared sensor, and the ground detection data further comprises an infrared signal;

The "inputting the ground detection data into the corresponding pre-established regression coefficient model to obtain at least one regression coefficient" also includes:

The infrared signal is oversampled to obtain the infrared signal sampling value and then input into the pre-established infrared regression coefficient model to obtain the infrared regression coefficient.
The carpet detection method according to claim 1, further comprising:

Acquiring the current value of at least one working motor, inputting the current value of the working motor into a corresponding pre-established regression coefficient model to obtain at least one regression coefficient;

Wherein, the working motor includes a rolling brush motor, a walking motor, and a side brush motor, and the regression coefficient model includes a rolling brush current regression coefficient model, a walking current regression coefficient model, and a side brush current regression coefficient model.
The carpet detection method according to claim 1, wherein the "using the at least one regression coefficient to perform operations according to a preset algorithm to obtain a carpet probability value" comprises:

When it is determined that the regression coefficient is within the corresponding preset regression coefficient range, the probability value of the corresponding weight of the regression coefficient is obtained;

The probability value of each weight obtained is added to obtain the probability value of the carpet.
The carpet detection method according to claim 1, further comprising:

When it is determined that the sweeping robot is located on the carpet and it is determined that the sweeping robot is in the cleaning mode, the suction power of the vacuum cleaner of the sweeping robot is increased.
The carpet detection method according to claim 1, further comprising:

When it is determined that the sweeping robot is located on the carpet and it is determined that the sweeping robot is in the mopping mode, control the sweeping robot to retreat from the carpet area, mark the carpet area and/or send the location of the carpet area to the customer end.
A carpet detection device applied to a sweeping robot, characterized in that it comprises:

The detection data acquisition module is configured to acquire ground detection data detected by at least one sensor;

A regression coefficient calculation module, configured to input the ground detection data into a corresponding pre-established regression coefficient model to obtain at least one regression coefficient;

The carpet probability calculation module is configured to use the at least one regression coefficient to perform calculations according to a preset algorithm to obtain a carpet probability value;

The carpet detection and determination module is configured to determine that the sweeping robot is located on the carpet when it is determined that the probability value of the carpet is greater than or equal to the preset probability value.
A sweeping robot, characterized by comprising a memory, a processor, an optical flow image sensor and an infrared sensor, the memory is configured to store a computer program, and the processor runs the computer program to make the sweeping robot execute according to the right The carpet detection method described in any one of 1 to 7 is required.
A computer storage medium, characterized in that it stores a computer program used in the cleaning robot according to claim 9.