Automatic cleaning method and apparatus of mobile robot, and mobile robot

Abstract

An automatic cleaning method and apparatus of a mobile robot, a mobile robot, and a storage medium. The automatic cleaning method comprises collecting a current image of a scene, recognizing an object in the current image, and determining the type of the object (S101); marking the recognized object as a preliminary obstacle on a map of the scene (S102); and on the basis of the type of the preliminary obstacle, performing a corresponding cleaning operation on the basis of a wall-following sensor (S103). By means of image recognition and a wall-following sensor, objects in a scene are intelligently recognized and classified, and accordingly a precise cleaning operation is performed, thereby improving the cleaning efficiency and accuracy of mobile robots.

Description

Mobile robot automatic cleaning method and device, mobile robot

[0001] The present application claims priority to the Chinese patent application No. 202411081911.1, filed on August 7, 2024, and entitled "Mobile robot automatic cleaning method and device, mobile robot", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the technical field of intelligent cleaning equipment, in particular to a mobile robot automatic cleaning method and device, a mobile robot and a storage medium. BACKGROUND

[0003] With the development of economy and the improvement of people's living standards, mobile robots for cleaning, such as sweeping robots, mopping robots, vacuum cleaners, etc., have become common household appliances in many families. These devices simplify daily chores through automation technology, providing users with more convenience and time freedom. Taking a sweeping robot as an example, it can automatically complete cleaning tasks such as dust collection, sweeping, and mopping, reducing the workload of people in household cleaning.

[0004] The cleaning efficiency and accuracy of a mobile robot are key indicators of its performance, and how to improve the cleaning efficiency and accuracy of a mobile robot has become a technical problem to be solved. SUMMARY

[0005] In view of the above problems, the present application is proposed to provide a mobile robot automatic cleaning method and device, a mobile robot and a storage medium that overcome the above problems or at least partially solve the above problems. The technical solution is as follows:

[0006] In a first aspect, a mobile robot automatic cleaning method is provided, comprising:

[0007] Collecting a current image of a scene, identifying an object in the current image, and determining the type of the object;

[0008] Marking the identified object as a preliminary obstacle on a map of the scene;

[0009] Performing a corresponding cleaning operation based on a wall-following sensor in combination with the type of the preliminary obstacle.

[0010] In one possible implementation, if the type of the preliminary obstacle is a first type of obstacle;

[0011] Performing a corresponding cleaning operation based on a wall-following sensor in combination with the type of the preliminary obstacle, comprising:

[0012] Identifying the height of the first type of obstacle through the wall-following sensor;

[0013] If the height of the first type of obstacle is greater than or equal to the preset height threshold, it is determined that the first type of obstacle identified through the image exists, and the operation of cleaning along the first type of obstacle through the wall-following sensor is continued.

[0014] In a possible implementation, the operation of cleaning along the first type of obstacle through the wall-following sensor is continued, and the operation includes:

[0015] The distance between the wall-following sensor and the first type of obstacle is measured through the wall-following sensor, and the distance between the wall-following sensor and the first type of obstacle is kept in the preset distance interval, and the operation of cleaning is performed.

[0016] In a possible implementation, the method further includes:

[0017] If the height of the first type of obstacle is less than the preset height threshold, it is determined that the first type of obstacle identified through the image does not exist, the marking of the first type of obstacle on the map of the scene is cancelled, and the operation of direct cleaning is performed.

[0018] In a possible implementation, if the type of the preliminary obstacle is a second type of obstacle;

[0019] Based on the type of the preliminary obstacle, corresponding cleaning operations are performed based on the wall-following sensor, and the operation includes:

[0020] The distance between the wall-following sensor and the second type of obstacle is measured through the wall-following sensor.

[0021] If the distance between the wall-following sensor and the second type of obstacle measured through the wall-following sensor is greater than the distance between the wall-following sensor and the second type of obstacle identified through the image, it is determined that the second type of obstacle identified through the image exists, the operation of cleaning along the second type of obstacle through the wall-following sensor is continued, and after the cleaning along the second type of obstacle is completed, the marking of the second type of obstacle on the map of the scene is cancelled.

[0022] In a possible implementation, if the type of the preliminary obstacle is a first type of obstacle;

[0023] Based on the type of the preliminary obstacle, corresponding cleaning operations are performed based on the wall-following sensor, and the operation includes:

[0024] The reflectivity of the position corresponding to the first type of obstacle is measured through the wall-following sensor.

[0025] Based on the measured reflectivity of the position corresponding to the first type of obstacle, it is determined whether the first type of obstacle identified through the image exists, if the first type of obstacle exists, the operation of cleaning along the first type of obstacle through the wall-following sensor is continued or the marking of the first type of obstacle on the map of the scene is cancelled, and the operation of direct cleaning is performed.

[0026] In a second aspect, a mobile robot automatic cleaning device is provided, comprising:

[0027] An identification unit configured to collect a current image of a scene, identify an object in the current image, and determine a type of the object;

[0028] A marking unit configured to mark the identified object as a preliminary obstacle on a map of the scene;

[0029] A cleaning unit configured to perform a corresponding cleaning operation along a wall sensor in combination with the type of the preliminary obstacle.

[0030] In a possible implementation, if the type of the preliminary obstacle is a first type of obstacle, the cleaning unit is further configured to:

[0031] identify a height of the first type of obstacle through the wall sensor;

[0032] if the height of the first type of obstacle is greater than or equal to a preset height threshold, determine that the first type of obstacle identified through the image exists, and continue to perform the cleaning operation along the first type of obstacle through the wall sensor.

[0033] In a possible implementation, the cleaning unit is further configured to:

[0034] continue to measure a distance to the first type of obstacle through the wall sensor, keep the distance to the first type of obstacle within a preset distance range, and perform the cleaning operation.

[0035] In a possible implementation, the cleaning unit is further configured to:

[0036] if the height of the first type of obstacle is less than the preset height threshold, determine that the first type of obstacle identified through the image does not exist, cancel the marking of the first type of obstacle on the map of the scene, and perform a direct cleaning operation.

[0037] In a possible implementation, if the type of the preliminary obstacle is a second type of obstacle, the cleaning unit is further configured to:

[0038] measure a distance to the second type of obstacle through the wall sensor;

[0039] if the measured distance to the second type of obstacle is greater than a distance to the second type of obstacle identified through the image, determine that the second type of obstacle identified through the image exists, continue to perform the cleaning operation along the second type of obstacle through the wall sensor, and cancel the marking of the second type of obstacle on the map of the scene after the cleaning along the second type of obstacle is completed.

[0040] In a possible implementation, if the type of the preliminary obstacle is the first type of obstacle, the cleaning unit is further configured to:

[0041] measure the reflectivity of the position corresponding to the first type of obstacle through the along-wall sensor;

[0042] determine whether the first type of obstacle identified through the image exists according to the measured reflectivity of the position corresponding to the first type of obstacle, and if the first type of obstacle exists, continue the operation of cleaning along the first type of obstacle through the along-wall sensor or cancel the marking of the first type of obstacle on the map of the scene and perform the operation of direct cleaning.

[0043] In a third aspect, a mobile robot is provided, which includes a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the mobile robot automatic cleaning method according to any one of the preceding aspects.

[0044] In a fourth aspect, a storage medium is provided, which stores a computer program, wherein the computer program is configured to perform the mobile robot automatic cleaning method according to any one of the preceding aspects when running.

[0045] In a fifth aspect, a computer program product is provided, which includes a computer program configured to perform the mobile robot automatic cleaning method according to any one of the preceding aspects when running.

[0046] By means of the above technical solutions, the mobile robot automatic cleaning method and device, the mobile robot, and the storage medium provided in the embodiments of the present application can acquire a current image of a scene, identify objects in the current image, determine the types of the objects, mark the identified objects as preliminary obstacles on a map of the scene, and perform corresponding cleaning operations based on an along-wall sensor in combination with the types of the preliminary obstacles. It can be seen that the embodiments of the present application can intelligently identify and classify objects in a scene through image recognition and an along-wall sensor, and perform accurate cleaning operations accordingly, thereby improving the cleaning efficiency and accuracy of the mobile robot. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the description of the embodiments of the present application will be briefly introduced.

[0048] FIG. 1 shows a flowchart of the mobile robot automatic cleaning method provided in the embodiments of the present application;

[0049] FIG. 2 shows a structural diagram of the mobile robot automatic cleaning device provided in the embodiments of the present application. DETAILED DESCRIPTION

[0050] Exemplary embodiments of the present application will be described herein below with reference to the accompanying drawings. While exemplary embodiments of the present application are illustrated, it is to be understood that the application is not limited to the embodiments described herein, which are presented as examples. Rather, the present application is intended to cover all modifications and alternatives that fall within the scope of the present application as defined by the appended claims.

[0051] It is to be noted that the terms "first", "second", and the like in the description and in the claims of the present application and the above-described drawings are intended to distinguish similar objects and not necessarily describe a particular sequential or chronological order. It is to be understood that the use of these terms in the appropriate situation enables the embodiments of the present application described herein to be carried out in sequences other than those illustrated or described herein. Furthermore, the term "comprise" and variations thereof are to be construed as open-ended terms meaning "including, but not limited to," in order to cover the occurrence where a stated integer is present, but other integers are absent.

[0052] To solve the above technical problems, the embodiments of the present application provide a mobile robot automatic cleaning method. The mobile robot can be a sweeping robot, a mopping robot, a vacuum cleaner, etc. The embodiments of the present application are not limited thereto. As shown in FIG. 1, the mobile robot automatic cleaning method can include the following steps S101-S103:

[0053] In step S101, a current image of a scene is collected, objects in the current image are identified, and the types of the objects are determined.

[0054] In this step, the scene can be a home environment, such as a living room, a bedroom, a kitchen, etc.; an office, such as an open office area, a conference room, a corridor, etc.; a hotel, such as a guest room, a public area, etc.; or an outdoor environment, such as a garden, a courtyard, a parking lot, etc. The embodiments of the present application are not limited thereto.

[0055] The current image of the scene can be collected by one or more cameras. When the current image of the scene is collected, image recognition can be performed on the current image to obtain objects in the current image, such as table legs, paper scraps, toys, wires, trash cans, liquids, human feet, pets, etc. The embodiments of the present application are not limited thereto.

[0056] Taking an RGB (Red Green Blue) camera as an example, the RGB camera can capture color images. Through image processing and computer vision algorithms, the identification of objects can be realized. The following are the general steps of RGB identification of objects.

[0057] 1) Image acquisition: The RGB camera captures color images of the scene.

[0058] 2) Image preprocessing: The collected images are processed, such as adjusting brightness, contrast, noise reduction, cropping, etc., to improve image quality.

[0059] 3) Feature extraction: using computer vision algorithms to extract useful features from the image, such as edges, corners, textures, etc.

[0060] 4) Object recognition: using a trained machine learning model, combined with the useful features extracted from the image, to recognize objects in the image. Here, deep learning techniques such as convolutional neural networks can be used, without limitation to this embodiment.

[0061] 5) Spatial localization: combining sensor data from the mobile robot and image information to determine the location of objects in space.

[0062] When the objects in the current image are obtained, these objects can be classified, for example, the first type of object is a static object, and the second type of object is a dynamic object. Taking the above examples, table legs, paper scraps, toys, wires, trash cans, liquids, etc. are static objects; human feet, pets, etc. are dynamic objects. It should be noted that the above examples are illustrative and do not limit the embodiment.

[0063] Step S102, mark the recognized objects as preliminary obstacles on the map of the scene.

[0064] The mobile robot can construct a two-dimensional or three-dimensional map of the scene, and can mark the recognized objects as preliminary obstacles on the two-dimensional or three-dimensional map of the scene. Here, when marking, the position of the object on the map, the type of the object, etc. can be recorded.

[0065] Further, marking the recognized objects as preliminary obstacles is a preliminary judgment of the objects, and later the along-wall sensor will be combined to make a further judgment to improve the accuracy of the judgment, and thus to perform an accurate cleaning operation, thereby improving the cleaning efficiency and accuracy of the mobile robot.

[0066] Step S103, based on the along-wall sensor, perform a corresponding cleaning operation according to the type of the preliminary obstacle.

[0067] In this step, according to the foregoing description, the type of the preliminary obstacle can be a static obstacle or a dynamic obstacle, for example, table legs, paper scraps, toys, wires, trash cans, liquids, etc. are static obstacles; human feet, pets, etc. are dynamic obstacles.

[0068] Here, the along-wall sensor is not limited to a specific sensor, and any sensor that can measure distance, reflectivity, etc. can be an along-wall sensor. For example, the along-wall sensor can be an infrared sensor, a laser sensor, an ultrasonic sensor, a TOF (Time of Flight) sensor, an optical sensor, etc. without limitation to this embodiment.

[0069] Take the TOF sensor as an example, it determines the distance by measuring the time it takes for a light or sound wave to travel from the transmitter to the object and back. The specific working principle is as follows.

[0070] (1) Transmit signal: The sensor transmits a beam of light (usually infrared) or sound wave.

[0071] (2) Signal reflection: The light or sound wave is reflected back when it encounters an object.

[0072] (3) Receive signal: The sensor receives the reflected signal.

[0073] (4) Calculate time: By calculating the time difference between the transmitted and received signals, the distance from the sensor to the object can be calculated.

[0074] In specific applications, the measurement range of the along-wall sensor needs to include the front of the mobile robot, which can be combined with historical signal data and historical distance positions to obtain the distance position of the object.

[0075] The embodiments of the present application intelligently identify and classify objects in the scene through image recognition and along-wall sensors, and accordingly perform precise cleaning operations, improving the cleaning efficiency and accuracy of the mobile robot.

[0076] A possible implementation is provided in the embodiments of the present application. If the type of the preliminary obstacle is the first type of obstacle, specifically a static obstacle, the above step S103 combines the type of the preliminary obstacle and performs a corresponding cleaning operation based on the along-wall sensor, which can specifically include the following steps A1 and A2:

[0077] Step A1, identifying the height of the first type of obstacle through the along-wall sensor.

[0078] For example, the point cloud data collected by the along-wall sensor is subjected to coordinate system conversion, then a depth image is generated with the height value as the scale factor, and a binary image is generated by comparing it with the obstacle height parameter. By calculating the area and boundary of the obstacle region in the binary image, the outline and height of the obstacle can be identified.

[0079] It should be noted that this is only an example and does not limit the embodiments. The core method is to use the data collected by the sensor to identify and measure the height of the obstacle through corresponding algorithm processing. The specific implementation details will vary depending on the type of sensor.

[0080] Step A2, if the height of the first type of obstacle is greater than or equal to the preset height threshold, it is determined that the first type of obstacle identified by image recognition exists, and the along-wall sensor is used to perform the along-wall cleaning operation along the first type of obstacle.

[0081] In this step, the preset height threshold can be 1 cm or 2 cm, and can be determined according to actual requirements, which is not limited in the embodiment.

[0082] The embodiment further determines whether the first type of obstacle exists in combination with the wall-following sensor, improves the accuracy of the determination, and then performs accurate cleaning operation accordingly. For example, when it is determined that the first type of obstacle identified through image recognition exists, the wall-following sensor is continued to be used to perform the cleaning operation along the first type of obstacle, thereby improving the cleaning efficiency and accuracy of the mobile robot.

[0083] In the embodiment, a possible implementation is provided. The wall-following sensor is continued to be used to perform the cleaning operation along the first type of obstacle in step A2, which can specifically be that the distance between the wall-following sensor and the first type of obstacle is continued to be measured to belong to the preset distance interval, the distance between the wall-following sensor and the first type of obstacle is maintained to belong to the preset distance interval, and the cleaning operation is performed.

[0084] The preset distance interval can be [0.5, 1] cm, which is only illustrative, and the preset distance interval can be determined according to actual requirements, which is not limited in the embodiment.

[0085] For example, for a normal ground (i.e., no high-low obstacle on the ground), the wall-following sensor detects a plane. If it is a static obstacle such as a wire or a stool, the static obstacle has a certain height, and thus the existence of the obstacle can be determined according to the height, and the distance between the wall-following sensor and the obstacle can be measured, for example, the distance belongs to [0.5, 1] cm, and the distance is maintained to perform the cleaning operation.

[0086] The mobile robot can be closer to the obstacle to perform the cleaning operation by accurately controlling the distance, thereby improving the cleaning efficiency and reducing the missed area.

[0087] In the embodiment, a possible implementation is provided. After the height of the first type of obstacle is identified by the wall-following sensor in step A1, the following step A3 can be further included.

[0088] In step A3, if the height of the first type of obstacle is identified to be less than the preset height threshold, it is determined that the first type of obstacle identified through image recognition does not exist, the mark of the first type of obstacle on the map of the scene is cancelled, and the direct cleaning operation is performed.

[0089] There may be misidentification through image recognition, such as identifying a reflection or pattern on the ground as a wire or a stain, etc. In this embodiment, the misidentified obstacles can be removed through secondary filtering by the wall-following sensor. In fact, if misidentified, the robot will not follow the wall in the first place. If it is a reflection or pattern, the wall-following sensor will not identify the height, so the result of image recognition will be wrong, and the object avoidance strategy will not be used, the object marker on the map of the scene will be cancelled, and the direct cleaning operation will be performed, i.e. the normal cleaning logic will be executed, thereby improving the cleaning efficiency of the mobile robot.

[0090] In this embodiment, a possible implementation is provided. If the type of the preliminary obstacle is the second type of obstacle, specifically a dynamic obstacle, the above step S103 combines the type of the preliminary obstacle and performs corresponding cleaning operation based on the wall-following sensor, which can specifically include the following steps B1 and B2:

[0091] Step B1, measuring the distance from the second type of obstacle through the wall-following sensor;

[0092] Step B2, if the measured distance from the second type of obstacle is greater than the distance from the second type of obstacle identified through image recognition, it is determined that the second type of obstacle identified through image recognition exists, and the wall-following sensor continues to perform the operation of cleaning along the second type of obstacle, and after the cleaning along the second type of obstacle is completed, the marker of the second type of obstacle on the map of the scene is cancelled.

[0093] Taking a human foot as an example, it has a certain height, and at the same time, the width of the human foot is not necessarily constant, i.e. the person may move, and when image recognition is performed, a box will be identified, and one box corresponds to one range. If the measured distance from the second type of obstacle through the wall-following sensor is greater than the distance from the second type of obstacle identified through image recognition, the human foot is regarded as a moving obstacle, i.e. a dynamic obstacle.

[0094] Through the above step S102, the identified object is marked as a preliminary obstacle on the map of the scene, so that the obstacle avoidance route of the preliminary obstacle can be planned. However, if a dynamic obstacle such as a human foot or a pet appears, the size and position of the marked obstacle may deviate, which may cause problems such as missed cleaning. For example, when the mobile robot cleans for the first time, a small dog stands on the path, and when the cleaning is completed, the dog walks away, so the position where the dog was before may cause missed cleaning.

[0095] The embodiment further determines the dynamic obstacle by the wall-following sensor, for example, by image recognition that the obstacle is a puppy, and it can be preliminarily considered that the obstacle is a dynamic obstacle, and then the wall-following sensor can be used for secondary confirmation, and the wall-following sensor is used for cleaning along the puppy, and after the cleaning along the puppy is completed, the mark of the puppy on the map of the scene is cancelled, so that the map is always missing a block, and the block will be cleaned again in the future, and the dynamic obstacle is avoided from being cleaned twice.

[0096] In the embodiment of the application, a possible implementation is provided. If the type of the preliminary obstacle is a first type of obstacle, specifically, a static obstacle, the above step S103 combines the type of the preliminary obstacle, and corresponding cleaning operation is performed based on the wall-following sensor, which can specifically include the following steps C1 and C2.

[0097] In step C1, the reflectivity of the position corresponding to the first type of obstacle is measured by the wall-following sensor.

[0098] In step C2, whether the first type of obstacle identified by image recognition exists is determined according to the measured reflectivity of the position corresponding to the first type of obstacle. If the first type of obstacle exists, the cleaning operation along the first type of obstacle is continued by the wall-following sensor, or the mark of the first type of obstacle on the map of the scene is cancelled, and the direct cleaning operation is performed.

[0099] For the liquid static obstacle, the reflectivity of the liquid is different from that of the ceramic tile or wooden floor. The wall-following sensor is also an optical sensor. The optical sensor detects objects by emitting light and receiving reflected light. The reflectivity of the object affects the amount of received light, so that the reflectivity of the position corresponding to the object can be inferred. Therefore, the reflectivity of the position corresponding to the first type of obstacle can be measured by the wall-following sensor. Whether the first type of obstacle identified by image recognition exists is determined according to the measured reflectivity of the position corresponding to the first type of obstacle. If the first type of obstacle exists, the cleaning operation along the first type of obstacle is continued by the wall-following sensor, or the mark of the first type of obstacle on the map of the scene is cancelled, and the direct cleaning operation is performed. The cleaning efficiency and accuracy of the mobile robot are improved.

[0100] It should be noted that the size of the serial number of each step in the above embodiment does not mean the order of execution. The execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the application. In actual application, all possible implementation manners described above can be combined in any combination to form possible embodiments of the application, which will not be described here.

[0101] Based on the mobile robot automatic cleaning method provided in the above embodiments, based on the same inventive concept, the embodiment of the application further provides a mobile robot automatic cleaning device.

[0102] FIG. 2 is a structural diagram of the mobile robot automatic cleaning device according to an embodiment of the present application. As shown in FIG. 2, the mobile robot automatic cleaning device can specifically include an identification unit 210, a marking unit 220, and a cleaning unit 230.

[0103] The identification unit 210 is configured to collect a current image of a scene, identify an object in the current image, and determine a type of the object.

[0104] The marking unit 220 is configured to mark the identified object as a preliminary obstacle on a map of the scene.

[0105] The cleaning unit 230 is configured to perform a corresponding cleaning operation based on a wall-following sensor in combination with the type of the preliminary obstacle.

[0106] In an embodiment of the present application, if the type of the preliminary obstacle is a first type of obstacle, the cleaning unit 230 is further configured to:

[0107] identify a height of the first type of obstacle through the wall-following sensor.

[0108] If the height of the first type of obstacle is greater than or equal to a preset height threshold, it is determined that the first type of obstacle identified through the image exists, and the operation of cleaning along the first type of obstacle through the wall-following sensor is continued.

[0109] In an embodiment of the present application, the cleaning unit 230 is further configured to:

[0110] continue to measure a distance to the first type of obstacle through the wall-following sensor, and keep the distance to the first type of obstacle within a preset distance interval, and perform the cleaning operation.

[0111] In an embodiment of the present application, the cleaning unit 230 is further configured to:

[0112] If the height of the first type of obstacle is less than the preset height threshold, it is determined that the first type of obstacle identified through the image does not exist, the marking of the first type of obstacle on the map of the scene is cancelled, and the direct cleaning operation is performed.

[0113] In an embodiment of the present application, if the type of the preliminary obstacle is a second type of obstacle, the cleaning unit 230 is further configured to:

[0114] measure a distance to the second type of obstacle through the wall-following sensor.

[0115] If the measured distance to the second type of obstacle is greater than the distance to the second type of obstacle identified through the image, it is determined that the second type of obstacle identified through the image exists, and the operation of cleaning along the second type of obstacle through the wall-following sensor is continued. After the cleaning along the second type of obstacle is completed, the marking of the second type of obstacle on the map of the scene is cancelled.

[0116] In the embodiments of the present application, a possible implementation is provided. If the type of the preliminary obstacle is the first type of obstacle, the cleaning unit 230 is further configured to:

[0117] The reflectivity of the position corresponding to the first type of obstacle is measured through the wall-following sensor.

[0118] According to the measured reflectivity of the position corresponding to the first type of obstacle, it is determined whether the first type of obstacle identified through the image exists. If the first type of obstacle exists, the operation of cleaning along the first type of obstacle through the wall-following sensor or the operation of directly cleaning is performed.

[0119] Based on the same inventive concept, the embodiments of the present application further provide a mobile robot, which comprises a processor and a memory. The memory stores a computer program, and the processor is configured to execute the computer program to perform the mobile robot automatic cleaning method of any one of the above-mentioned embodiments.

[0120] Based on the same inventive concept, the embodiments of the present application further provide a storage medium, which stores a computer program. The computer program is configured to execute the mobile robot automatic cleaning method of any one of the above-mentioned embodiments when executed.

[0121] Based on the same inventive concept, the embodiments of the present application further provide a computer program product, which comprises a computer program. The computer program is configured to execute the mobile robot automatic cleaning method of any one of the above-mentioned embodiments when executed.

[0122] Those skilled in the art can clearly understand the specific working process of the above-mentioned system, device and module. For brevity, the corresponding process in the foregoing method embodiments is referred to, and no further description is given here.

[0123] Those skilled in the art can understand that the technical solutions of the present application can be embodied in the form of software product essentially or partially, and the computer software product is stored in a storage medium, and includes a plurality of program instructions to make an electronic device (such as a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in the embodiments of the present application when the program instructions are run. The storage medium mentioned above includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0124] Alternatively, all or part of the steps of the foregoing method embodiments can be completed by program instruction related hardware (such as an electronic device of a personal computer, a server, or a network device, etc.), and the program instructions can be stored in a computer readable storage medium, and when the program instructions are executed by the processor of the electronic device, the electronic device executes all or part of the steps of the method described in the embodiments of the present application.

[0125] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that within the spirit and principle of the present application, the technical solutions recorded in the foregoing embodiments can still be modified, or part or all of the technical features can be replaced equivalently; and these modifications or replacements do not make the corresponding technical solutions deviate from the protection scope of the present application.

Claims

1. A mobile robot automatic cleaning method, wherein, The method comprises: collecting a current image of a scene, identifying an object in the current image, and determining a type of the object; marking the identified object as a preliminary obstacle on a map of the scene; based on a wall-following sensor, performing a corresponding cleaning operation in combination with the type of the preliminary obstacle.

2. The method of claim 1, wherein, If the type of the preliminary obstacle is a first type of obstacle; based on the wall-following sensor, performing a corresponding cleaning operation in combination with the type of the preliminary obstacle, comprising: identifying a height of the first type of obstacle through the wall-following sensor; if the height of the first type of obstacle is identified to be greater than or equal to a preset height threshold, determining that the first type of obstacle identified through the image exists, and continuing to perform the wall-following sensor along the first type of obstacle cleaning operation.

3. The method of claim 2, wherein, Continuing to perform the wall-following sensor along the first type of obstacle cleaning operation, comprising: continuing to measure the distance from the wall-following sensor to the first type of obstacle to belong to a preset distance interval, and maintaining the distance from the wall-following sensor to the first type of obstacle to belong to the preset distance interval to perform the cleaning operation.

4. The method of claim 2, wherein, The method further comprises: if the height of the first type of obstacle is identified to be less than the preset height threshold, determining that the first type of obstacle identified through the image does not exist, canceling the marking of the first type of obstacle on the map of the scene, and performing a direct cleaning operation.

5. The method of claim 1, wherein, If the type of the preliminary obstacle is a second type of obstacle; based on the wall-following sensor, performing a corresponding cleaning operation in combination with the type of the preliminary obstacle, comprising: measuring the distance from the wall-following sensor to the second type of obstacle; if the measured distance from the wall-following sensor to the second type of obstacle is greater than the distance from the wall-following sensor to the second type of obstacle identified through the image, determining that the second type of obstacle identified through the image exists, and continuing to perform the wall-following sensor along the second type of obstacle cleaning operation, and canceling the marking of the second type of obstacle on the map of the scene after the wall-following sensor along the second type of obstacle cleaning operation is completed.

6. The method of claim 1, wherein, If the type of the preliminary obstacle is a first type of obstacle; based on the wall-following sensor, performing a corresponding cleaning operation in combination with the type of the preliminary obstacle, comprising: measuring the reflectivity of the position corresponding to the first type of obstacle through the wall-following sensor; determining whether the first type of obstacle identified through the image exists according to the measured reflectivity of the position corresponding to the first type of obstacle, and if so, continuing to perform the wall-following sensor along the first type of obstacle cleaning operation or canceling the marking of the first type of obstacle on the map of the scene to perform a direct cleaning operation.

7. A mobile robot automatic cleaning apparatus, wherein, The method comprises: an identifying unit configured to collect a current image of a scene, identify an object in the current image, and determine a type of the object; a marking unit configured to mark the identified object as a preliminary obstacle on a map of the scene; a cleaning unit configured to, based on a wall-following sensor, perform a corresponding cleaning operation in combination with the type of the preliminary obstacle.

8. A mobile robot, wherein, The storage medium stores a computer program, and the computer program is configured to execute the mobile robot automatic cleaning method of any one of claims 1 to 6 when running.

9. A storage medium, wherein, The storage medium stores a computer program, and the computer program is configured to execute the mobile robot automatic cleaning method of any one of claims 1 to 6 when running.

10. A computer program product comprising a computer program, wherein, The computer program is configured to execute the mobile robot automatic cleaning method of any one of claims 1 to 6 when running.

Images