Methods, systems and media for rapid mapping of cleaning robots

Abstract

This application discloses a method, system, and medium for rapid mapping of cleaning robots, relating to the field of 3D mapping technology. It is applied to a rapid mapping system for cleaning robots that includes laser devices and image acquisition devices. The system includes: acquiring mapping environment information of the cleaning robot, wherein the mapping environment information includes laser feedback environment information acquired by the laser device and image feedback environment information acquired by the image acquisition device; determining mapping mode information based on the image feedback environment information, wherein the mapping mode information includes a first mapping mode with single feedback information and a second mapping mode with multiple feedback information; when the mapping mode information is the first mapping mode, performing rapid 3D mapping based on either the laser feedback environment information or the image feedback environment information; when the mapping mode information is the second mapping mode, performing rapid 3D mapping based on both the laser feedback environment information and the image feedback environment information. This improves the mapping accuracy of the cleaning robot.

Description

Technical Field

[0001] This application relates to the field of 3D mapping technology, and in particular to a method, system and medium for rapid mapping of a cleaning robot. Background Technology

[0002] Currently, in the process of mapping cleaning robots, the use of specific detection algorithms, such as the K-MEANS algorithm, can lead to inaccurate map construction (e.g., missing objects) by incorrectly filtering out small objects. For example, there may be few laser points hitting a table leg, and these laser points are often far from other laser points in the environment. Therefore, these laser points hitting the table leg must be classified separately. Because the number of these laser points is relatively small, they are frequently filtered out, resulting in the absence of that table leg in the constructed map. This method of mapping cleaning robots results in low accuracy due to missing elements.

[0003] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a method, system and medium for rapid mapping of cleaning robots, which aims to solve the technical problem of low mapping accuracy of cleaning robots.

[0005] To achieve the above objectives, this application proposes a rapid mapping method for a cleaning robot. This rapid mapping method is applied to a rapid mapping system for a cleaning robot, which includes a laser device and an image acquisition device. The rapid mapping method for the cleaning robot includes:

[0006] The mapping environment information of the cleaning robot is obtained, wherein the mapping environment information includes the laser feedback environment information collected by the laser device and the image feedback environment information collected by the image acquisition device;

[0007] Mapping mode information is determined based on the image feedback environment information, wherein the mapping mode information includes a first mapping mode with single feedback information and a second mapping mode with multiple feedback information.

[0008] When the mapping mode information is the first mapping mode, rapid three-dimensional mapping is performed based on the laser feedback environment information or the image feedback environment information.

[0009] When the mapping mode information is the second mapping mode, rapid 3D mapping is performed based on the laser feedback environment information and the image feedback environment information.

[0010] In one embodiment, the step of determining the mapping mode information based on the image feedback environment information includes:

[0011] Determine the image imaging region in the image feedback environment information and the image imaging features corresponding to the image imaging region;

[0012] When the image imaging features match the preset planar imaging features, the mapping mode information of the first image imaging region in the image feedback environment information is determined as the first mapping mode, wherein the first image imaging region includes the image imaging region that matches the image imaging features with the preset planar imaging features.

[0013] When the image imaging features match the preset inclined plane imaging features, the mapping mode information of the second image imaging region in the image feedback environment information is determined to be the second mapping mode, wherein the second image imaging region includes the image imaging region that matches the image imaging features with the preset inclined plane imaging features.

[0014] When the image imaging features match the preset obstacle imaging features, the mapping mode information of the third image imaging region in the image feedback environment information is determined to be the second mapping mode, wherein the second image imaging region includes the image imaging region that matches the image imaging features with the preset obstacle imaging features.

[0015] When the image imaging features match the preset cleaning object imaging features, the mapping mode information of the fourth image imaging region in the image feedback environment information is determined to be the first mapping mode, wherein the fourth image imaging region includes the image imaging region whose image imaging features match the preset cleaning object imaging features.

[0016] In one embodiment, the step of determining the image imaging region in the image feedback environment information and the image imaging features corresponding to the image imaging region includes:

[0017] Based on preset image segmentation imaging features, the image in the image feedback environment information is divided into multiple initial regions, wherein the image segmentation imaging features include preset planar imaging features, preset inclined plane imaging features, preset obstacle imaging features, and preset clean object imaging features.

[0018] A first image connection relationship is determined between each initial region, and each initial region is expanded or shrunk based on the first image connection relationship to obtain multiple image imaging regions. Each image imaging region uniquely corresponds to a segmentation image imaging feature as an image imaging feature.

[0019] In one embodiment, the mapping mode information includes the target image imaging region and the target mapping mode corresponding to the target image imaging region. After the step of determining the mapping mode information based on the image feedback environment information, the method includes:

[0020] When the target mapping mode is the first mapping mode and the image imaging features of the target image imaging area match the preset planar imaging features, the azimuth angle and range information of the target image imaging area are written into the mapping mode information.

[0021] When the target mapping mode is the first mapping mode and the image imaging features of the target image imaging area match the preset cleaning object imaging features, the azimuth angle of the target image imaging area is written into the mapping mode information.

[0022] In one embodiment, the step of rapidly constructing a 3D map based on the laser feedback environment information or the image feedback environment information includes:

[0023] When the first mapping mode is to map the first image imaging region in the image feedback environment information, the image distance corresponding to the azimuth angle in the image feedback environment information is determined, and the first actual distance corresponding to the image distance is determined based on a preset image imaging ratio; the image range corresponding to the range information in the image feedback environment information is determined, and the actual range corresponding to the image range is determined based on a preset image imaging ratio; and the first image imaging region is quickly mapped in three dimensions based on the first actual distance and the actual range.

[0024] When the first mapping mode is to map the fourth image imaging area in the image feedback environment information, the second actual distance corresponding to the azimuth angle in the laser feedback environment information is determined, and the fourth image imaging area is quickly mapped based on the second actual distance.

[0025] In one embodiment, the step of rapidly constructing a 3D map based on the laser feedback environment information and the image feedback environment information includes:

[0026] When the second mapping mode is to map the second image imaging area in the image feedback environment information, the third actual distance of the entire second image imaging area in the laser feedback environment information is determined, and the first theoretical change distance of the second image imaging area in the image feedback environment information is determined.

[0027] When the third actual distance matches the first theoretical change distance, a rapid three-dimensional map is constructed on the second image imaging area based on the third actual distance.

[0028] In one embodiment, the step of rapidly constructing a 3D map based on the laser feedback environment information and the image feedback environment information further includes:

[0029] When the second mapping mode is to map the third image imaging region in the image feedback environment information, the fourth actual distance of the entire third image imaging region in the laser feedback environment information is determined, and the second theoretical change distance of the third image imaging region in the image feedback environment information is determined.

[0030] When the third actual distance matches the second theoretical change distance, a rapid three-dimensional map is constructed on the third image imaging area based on the fourth actual distance.

[0031] In one embodiment, the rapid mapping method for cleaning robots further includes:

[0032] Determine the target mapping corresponding to each image imaging region in the image feedback environment information, and determine the second image connection relationship corresponding to each image imaging region;

[0033] When the second image connection relationship is a preset distance matching connection relationship, the image imaging areas corresponding to the second image connection relationship are linked to obtain the cleaning robot map;

[0034] When the second image connection relationship is not a preset distance matching connection relationship, the image imaging area corresponding to the second image connection relationship is layered and then linked to obtain the cleaning robot map. The layering process includes layering based on the actual distance of the image imaging area corresponding to the second image connection relationship.

[0035] Furthermore, to achieve the above objectives, this application also proposes a rapid mapping system for a cleaning robot. The rapid mapping system for a cleaning robot includes a laser device, an image acquisition device, and a controller. The controller is connected to the laser device and the image acquisition device respectively. The controller includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the rapid mapping method for a cleaning robot as described above.

[0036] In addition, to achieve the above objectives, this application also proposes a medium, which is a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the rapid mapping method for cleaning robots described above.

[0037] This application provides a rapid mapping method for a cleaning robot, applied to a rapid mapping system for a cleaning robot. The rapid mapping system includes a laser device and an image acquisition device. The method acquires mapping environment information of the cleaning robot, including laser feedback environment information acquired by the laser device and image feedback environment information acquired by the image acquisition device. Mapping mode information is determined based on the image feedback environment information, including a first mapping mode with single feedback information and a second mapping mode with multiple feedback information. When the mapping mode is the first mapping mode, rapid 3D mapping is performed based on either the laser feedback environment information or the image feedback environment information. When the mapping mode information is the second mapping mode, rapid 3D mapping is performed based on the laser feedback environment information and the image feedback environment information. This rapid mapping method for cleaning robots obtains laser feedback environment information collected by laser devices and image feedback environment information collected by image acquisition devices. Based on the image feedback environment information, the mapping mode information is determined. Then, under the control of different mapping mode information, mapping is started based on at least one of the laser feedback environment information and image feedback environment information, thus avoiding the phenomenon of incorrectly filtering out small objects, which leads to inaccurate map construction (e.g., missing objects). Therefore, the mapping accuracy of cleaning robots can be improved based on the laser feedback environment information collected by laser devices and the image feedback environment information collected by image acquisition devices. Attached Figure Description

[0038] Figure 1 This is a flowchart illustrating the first embodiment of the rapid mapping method for cleaning robots according to this application;

[0039] Figure 2 This is a schematic diagram illustrating an implementation process of the rapid mapping method for cleaning robots in this application;

[0040] Figure 3 This is a flowchart illustrating the second embodiment of the rapid mapping method for cleaning robots according to this application;

[0041] Figure 4 This is a schematic diagram of the module of the rapid mapping device for cleaning robots in this application;

[0042] Figure 5 This is a schematic diagram of the hardware operating environment involved in the device in this application.

[0043] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0044] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0045] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0046] As cleaning robots develop, their mapping methods are constantly evolving. A common approach is to use algorithms, such as the K-MEANS algorithm. However, this algorithm frequently filters out small objects, leading to inaccurate map construction (e.g., missing elements). For instance, if a table leg exists in the environment, and the laser points hitting it are few and far from other laser points in the environment, these points must be grouped separately. Because these few points are numerous, they are often filtered out, resulting in the table leg not appearing in the constructed map. This missing element contributes to the low accuracy of the cleaning robot's mapping.

[0047] Therefore, based on the shortcomings of the above-mentioned mapping schemes for cleaning robots, this application proposes a rapid mapping method for cleaning robots. The solution of this application is as follows: by acquiring laser feedback environment information collected by a laser device and image feedback environment information collected by an image acquisition device, mapping mode information is determined based on the image feedback environment information. Then, under the control of different mapping mode information, mapping begins based on at least one of the laser feedback environment information and the image feedback environment information, thus avoiding the erroneous filtering out of small objects, which leads to inaccurate map construction (e.g., missing objects). Therefore, the mapping accuracy of the cleaning robot can be improved by using the laser feedback environment information collected by the laser device and the image feedback environment information collected by the image acquisition device.

[0048] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a device or controller capable of performing the above functions. The following description uses a controller as an example to illustrate this embodiment and the subsequent embodiments.

[0049] Based on this, embodiments of this application provide a method for rapid mapping of cleaning robots, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the rapid mapping method for cleaning robots according to this application.

[0050] Reference Figure 1This application provides a method for rapid mapping of a cleaning robot. In a first embodiment of the method, the method is applied to a rapid mapping system for a cleaning robot, which includes a laser device and an image acquisition device. The method includes:

[0051] Step S10: Obtain the mapping environment information of the cleaning robot, wherein the mapping environment information includes the laser feedback environment information collected by the laser device and the image feedback environment information collected by the image acquisition device;

[0052] Step S20: Determine mapping mode information based on the image feedback environment information, wherein the mapping mode information includes a first mapping mode with single feedback information and a second mapping mode with multiple feedback information.

[0053] In this embodiment, the rapid mapping method for cleaning robots is applied to a rapid mapping system for cleaning robots. This system includes laser devices and image acquisition devices, such as commonly used laser rangefinders and cameras. Mapping can be performed based on both laser devices and image acquisition devices, avoiding the limitations of using only laser devices. During mapping, the mapping environment information of the cleaning robot is acquired. This information includes relevant details about the robot's environment, such as objects, cleaning materials, and walls. This information includes laser feedback environment information acquired by the laser device and image feedback environment information acquired by the image acquisition device. Mapping is performed based on at least one of these two types of information, thus avoiding the problem of filtering out a small number of laser points. By comprehensively considering the image feedback environment information, the mapping accuracy of the cleaning robot can be improved. Specifically, the image feedback environment information refers to the acquired image of the area surrounding the cleaning robot, which at least defines the characteristics of the objects in the image and the areas they encompass. The laser feedback environment information refers to the acquired information such as the distance and size of the objects around the cleaning robot. After obtaining the mapping environment information, the mapping mode information is determined based on the image feedback environment information. This means determining whether the first mapping mode (single feedback information mapping) or the first mapping mode (multiple feedback information mapping) is more suitable for the area. For example, if mapping a single wall, image feedback environment information can be used directly, greatly improving mapping efficiency. Using laser feedback environment information requires determining not only the distance but also whether it's a wall and its size. If mapping a cleaning object, only its position and basic size need to be determined, which can be easily done using laser feedback environment information. If mapping a spatial object, both image and laser feedback environment information can be used together. This allows for different mapping methods based on different situations, improving the accuracy and efficiency of the cleaning robot's mapping.

[0054] Step S30: When the mapping mode information is the first mapping mode, perform rapid 3D mapping based on the laser feedback environment information or the image feedback environment information.

[0055] Step S40: When the mapping mode information is the second mapping mode, perform rapid 3D mapping based on the laser feedback environment information and the image feedback environment information.

[0056] In this embodiment, after determining the mapping mode, at least one of laser feedback environmental information and image feedback environmental information is used for mapping based on different mapping modes. The purpose of distinguishing based on the mapping mode is to process different mapping targets through different mode control, thereby improving the accuracy of mapping. It is worth noting that because there are cases where mapping is based solely on image feedback environmental information, in extreme cases (such as placing the cleaning robot in an empty room for the first time for mapping), image feedback environmental information can be used directly for mode determination. After mode determination, it is then determined whether to collect laser feedback environmental information to ensure the effective utilization of internal resources.

[0057] In one embodiment, reference is made to Figure 2 , Figure 2 This is a schematic diagram illustrating the implementation process of the rapid mapping method for cleaning robots according to this application. After mapping begins, information is collected using image acquisition devices such as laser devices and cameras. The subsequent processing is then determined based on the information collected by the camera, i.e., the mapping mode is determined based on the image feedback environment information collected by the camera. Finally, rapid 3D mapping is performed based on the information collected by the laser device (laser feedback environment information), the information collected by the camera (image feedback environment information), and the determined processing method (mapping mode). On the one hand, different information can be used for mapping, avoiding the limitation of using only laser mapping; that is, different areas can be mapped simultaneously to achieve rapid mapping for the cleaning robot. On the other hand, different mapping modes are selected based on different situations to avoid errors caused by mapping, thereby improving the mapping accuracy of the cleaning robot.

[0058] In this embodiment, a rapid mapping method for a cleaning robot is provided, applied to a rapid mapping system for a cleaning robot. The rapid mapping system includes a laser device and an image acquisition device. The method acquires mapping environment information of the cleaning robot, including laser feedback environment information acquired by the laser device and image feedback environment information acquired by the image acquisition device. Mapping mode information is determined based on the image feedback environment information, including a first mapping mode with single feedback information and a second mapping mode with multiple feedback information. When the mapping mode information is the first mapping mode, rapid 3D mapping is performed based on either the laser feedback environment information or the image feedback environment information. When the mapping mode information is the second mapping mode, rapid 3D mapping is performed based on the laser feedback environment information and the image feedback environment information. This rapid mapping method for cleaning robots obtains laser feedback environment information collected by laser devices and image feedback environment information collected by image acquisition devices. Based on the image feedback environment information, the mapping mode information is determined. Then, under the control of different mapping mode information, mapping is started based on at least one of the laser feedback environment information and image feedback environment information, thus avoiding the phenomenon of incorrectly filtering out small objects, which leads to inaccurate map construction (e.g., missing objects). Therefore, the mapping accuracy of cleaning robots can be improved based on the laser feedback environment information collected by laser devices and the image feedback environment information collected by image acquisition devices.

[0059] Furthermore, based on the first embodiment of this application described above, a second embodiment of the rapid mapping method for cleaning robots of this application is proposed. In this embodiment, step S20, the step of determining the mapping mode information based on the image feedback environmental information, includes:

[0060] Step S21: Determine the image imaging region in the image feedback environment information and the image imaging features corresponding to the image imaging region;

[0061] Step S22: When the image imaging features match the preset planar imaging features, the mapping mode information of the first image imaging region in the image feedback environment information is determined to be the first mapping mode, wherein the first image imaging region includes the image imaging region that matches the image imaging features with the preset planar imaging features.

[0062] Step S23: When the image imaging features match the preset inclined plane imaging features, the mapping mode information of the second image imaging region in the image feedback environment information is determined to be the second mapping mode, wherein the second image imaging region includes the image imaging region that matches the image imaging features with the preset inclined plane imaging features.

[0063] Step S24: When the image imaging features match the preset obstacle imaging features, the mapping mode information of the third image imaging region in the image feedback environment information is determined to be the second mapping mode, wherein the second image imaging region includes the image imaging region that matches the image imaging features with the preset obstacle imaging features.

[0064] Step S25: When the image imaging features match the preset cleaning object imaging features, the mapping mode information of the fourth image imaging region in the image feedback environment information is determined to be the first mapping mode, wherein the fourth image imaging region includes the image imaging region whose image imaging features match the preset cleaning object imaging features.

[0065] In this embodiment, when determining the mapping mode, the image imaging region and its corresponding image imaging features in the image feedback environment information are determined. Then, based on these image imaging features, the mapping mode to be used for each image imaging region is determined. The image imaging region refers to a whole image divided into multiple smaller image regions based on rules. These rules can be based on size or mapping features within the image. Image imaging features refer to the characteristics of various objects or boundary images in the image, such as planes, concave surfaces, spatial objects, and inclined planes. The image imaging features of each image imaging region are then assessed to determine which mapping mode should be used. When the image imaging features match a preset planar imaging feature, the mapping mode information of the first image imaging region in the image feedback environment information is determined as the first mapping mode. The first image imaging region includes the image imaging region whose image imaging features match the preset planar imaging features. The preset planar imaging features refer to the features of the planar image set by the user, such as consistent pixel values. Matching means that the features are the same or extremely similar. When the image imaging features match a preset inclined plane imaging feature, the mapping mode information of the second image imaging region in the image feedback environment information is determined as the second mapping mode. The second image imaging region includes the image imaging region whose image imaging features match the preset inclined plane imaging features. The preset inclined plane imaging features refer to the features of the inclined plane image set by the user, such as uniform pixel value variation. When the image imaging features match a preset obstacle imaging feature, the mapping mode information of the third obstacle in the image feedback environment information is determined as the second mapping mode. The mapping mode information of the image imaging area is the second mapping mode. The third image imaging area includes an image imaging area whose image imaging features match the preset obstacle imaging features. The preset obstacle imaging features refer to the characteristics of the obstacle image set by the user, such as drastic changes in pixel values ​​and three-dimensional objects in the image. When the image imaging features match the preset cleaning object imaging features, the mapping mode information of the fourth image imaging area in the image feedback environment information is determined to be the first mapping mode. The fourth image imaging area includes an image imaging area whose image imaging features match the preset cleaning object imaging features. The preset cleaning object imaging features refer to the characteristics of the cleaning object image set by the user, such as drastic changes in pixel values ​​and cleaning objects on the ground in the image. Different mapping modes can be performed on the image imaging area based on different image imaging features to improve the mapping accuracy and efficiency of the cleaning robot through targeted mapping.

[0066] Furthermore, the step of determining the image imaging region in the image feedback environment information and the image imaging features corresponding to the image imaging region includes:

[0067] Step S211: Based on preset image segmentation imaging features, the image in the image feedback environment information is divided into multiple initial regions, wherein the image segmentation imaging features include preset planar imaging features, preset inclined plane imaging features, preset obstacle imaging features, and preset clean object imaging features.

[0068] Step S212: Determine the first image connection relationship between each initial region, and perform expansion and contraction processing on each initial region based on the first image connection relationship to obtain multiple image imaging regions, wherein each image imaging region uniquely corresponds to a segmentation image imaging feature as an image imaging feature.

[0069] In this embodiment, after determining the image feedback environment information, the image feedback environment information is processed to obtain at least one image imaging region and the image imaging feature uniquely corresponding to that image imaging region. Based on preset image imaging features, the image in the image feedback environment information is divided into multiple initial regions. These image imaging features include preset planar imaging features, preset oblique plane imaging features, preset obstacle imaging features, and preset clean object imaging features. In other words, the overall large image is divided into multiple smaller images based on these features. For example, if the image is planar, the planar portion is divided into an initial region. The priority of dividing the initial region is: preset clean object imaging features, preset obstacle imaging features, then preset planar imaging features, and finally preset oblique plane imaging features. This avoids the phenomenon of directly dividing the initial region into the preset planar imaging features and preset oblique plane imaging features, and avoids mapping errors caused by the presence of preset clean object imaging features and preset obstacle imaging features (only one of these will be present in the preset planar imaging features or preset oblique plane imaging features). An initial region refers to a small region containing only one type of image imaging feature. At this point, some regions may remain undivided because they may not possess any of the four features mentioned above. Therefore, it is necessary to determine the first image connection relationship between the initial regions. Based on this first image connection relationship, the initial regions are then expanded or reduced to obtain multiple image imaging regions. The first image connection relationship refers to the connection between the initial regions, i.e., the connection within the overall large image. Based on this connection relationship, undivided or repeatedly divided parts are processed. That is, the initial region is expanded to extend to the undivided parts, or the initial region is reduced to remove the repeatedly divided parts. The principle of expansion and reduction is to minimize the impact on the regions with image imaging features in the initial region. At this point, each image imaging region will uniquely correspond to an image imaging feature as its image imaging feature, so that the mapping mode can be determined subsequently based on the image imaging region and its uniquely corresponding image imaging feature.

[0070] Furthermore, based on the first and / or second embodiments of this application described above, a third embodiment of the rapid mapping method for cleaning robots of this application is proposed. In this embodiment, step S20, where the mapping mode information includes the target image imaging area and the target mapping mode corresponding to the target image imaging area, after the step of determining the mapping mode information based on the image feedback environment information, includes:

[0071] Step S201: When the target mapping mode is the first mapping mode and the image imaging features of the target image imaging area match the preset planar imaging features, the azimuth angle and range information of the target image imaging area are written into the mapping mode information.

[0072] Step S202: When the target mapping mode is the first mapping mode and the image imaging features of the target image imaging area match the preset cleaning object imaging features, the azimuth angle of the target image imaging area is written into the mapping mode information.

[0073] In this embodiment, after determining the mapping mode, the image determined to be the first mapping mode will be processed. This is because the mapping mode information at this time also includes the target image imaging area and the target mapping mode corresponding to the target image imaging area. The target image imaging area can be any one of the first image imaging area, the second image imaging area, the third image imaging area, and the fourth image imaging area mentioned above. However, at this time, only the image of the first mapping mode needs to be processed because the first mapping mode can directly use the laser feedback environment information or the single information of the image feedback environment to perform mapping, so it needs to be processed in advance. When the image imaging features of the target image imaging area match the preset planar imaging features (i.e., this is the first image imaging area), the azimuth angle and range information of the target image imaging area are written into the mapping mode information. This facilitates subsequent mapping based on the written azimuth angle and range information. Here, the azimuth angle refers to the angle of the image (cleaning robot) where the plane is located, and the range information refers to the range occupied by the plane, which can be obtained based on the relationship between the image and the object in the first image imaging area. When the image imaging features of the target image imaging area match the preset cleaning object imaging features (i.e., this is the fourth image imaging area), the azimuth angle of the target image imaging area is written into the mapping mode information. This facilitates subsequent mapping based on the written azimuth angle. Here, mapping can be performed on a single azimuth angle. Since the cleaning object is the item to be cleaned, there is no need for detailed mapping (because its maximum range can be roughly known when it is determined to be a cleaning object). Therefore, after targeted processing based on different image imaging areas in the first mapping mode, the mapping mode information can be used for subsequent processing to ensure the specificity of subsequent processing and thus guarantee the specificity of the mapping.

[0074] Furthermore, the step of rapidly constructing a 3D map based on the laser feedback environment information or the image feedback environment information includes:

[0075] Step S31: When the first mapping mode is to map the first image imaging region in the image feedback environment information, the image distance corresponding to the azimuth angle in the image feedback environment information is determined, and the first actual distance corresponding to the image distance is determined based on a preset image imaging ratio; the image range corresponding to the range information in the image feedback environment information is determined, and the actual range corresponding to the image range is determined based on a preset image imaging ratio; and the first image imaging region is quickly mapped in three dimensions based on the first actual distance and the actual range.

[0076] Step S32: When the first mapping mode is to map the fourth image imaging area in the image feedback environment information, the second actual distance corresponding to the azimuth angle in the laser feedback environment information is determined, and the fourth image imaging area is quickly mapped based on the second actual distance.

[0077] In this embodiment, when the mapping mode is the first mapping mode, different information based on the image feedback environment information is processed accordingly. Different information written in the image feedback environment information implies different processing requirements and methods for mapping. When the image feedback environment information includes azimuth angle and range information (i.e., mapping the first image imaging area), the corresponding image distance is determined based on the azimuth angle. Then, the first actual distance is determined based on the image distance and a preset image imaging ratio. Simultaneously, the corresponding actual range is determined by combining the image range corresponding to the range information. Finally, the first image imaging area can be quickly mapped in three dimensions by combining the actual range and the first actual distance. Here, image distance refers to the distance between the plane at that azimuth angle and the cleaning robot on the image; preset image imaging ratio refers to the scaling ratio during image imaging, which can be a known fixed value; first actual distance refers to the distance from the actual plane to the cleaning robot; image range refers to the range of the plane on the image; and actual range refers to the range of the actual plane. Because subsequent mapping requires combining the actual distance from the laser feedback environment information, it is necessary to determine the actual range and distance of the plane here to facilitate subsequent processing of the entire map. When only the orientation angle is written in the image feedback environment information (i.e., mapping is performed on the fourth image imaging area), the second actual distance corresponding to that orientation angle will be directly determined in the laser feedback environment information. Then, the fourth image imaging area will be quickly mapped based on the second actual distance. Here, the second actual distance refers to the distance between the cleaning object and the cleaning robot. At this time, only the approximate distance needs to be determined because the specific size of the items to be cleaned does not need to be determined. Therefore, the mapping of the plane and the cleaning object can be completed in a targeted manner based on the first mapping mode to ensure the accuracy of the mapping of the plane and the cleaning object.

[0078] Furthermore, based on the first, second, and / or third embodiments of this application described above, a fourth embodiment of the rapid mapping method for cleaning robots of this application is proposed. In this embodiment, the step of rapidly constructing a three-dimensional map based on the laser feedback environment information and the image feedback environment information includes:

[0079] Step S401: When the second mapping mode is to map the second image imaging area in the image feedback environment information, determine the third actual distance of the entire second image imaging area in the laser feedback environment information, and determine the first theoretical change distance of the second image imaging area in the image feedback environment information.

[0080] Step S402: When the third actual distance matches the first theoretical change distance, perform rapid three-dimensional mapping of the second image imaging area based on the third actual distance.

[0081] In this embodiment, under the second mapping mode, there is a scheme for mapping the inclined plane in the second image imaging area. At this time, on the one hand, the third actual distance of the entire second image imaging area in the laser feedback environment information is determined. The third actual distance refers to the actual distance between the cleaning robot and the inclined plane. On the other hand, the first theoretical change distance of the second image imaging area is determined in the image feedback environment information. The first theoretical change distance refers to the theoretical change distance of the inclined plane, that is, the actual distance of the inclined plane is determined. At the same time, it is judged whether the actual distance is the same as the theoretical change in the image. That is, when it is determined that the third actual distance matches the first theoretical change distance, the second image imaging area can be quickly mapped in three dimensions based on the third actual distance. For example, if the first theoretical change distance changes by 3°, it can be determined that the actual distance should change by 'a' meters. However, if the third actual distance changes by about 'a' meters in a certain area, it is determined that the inclined plane can be mapped. But if it changes by 0 meters in a certain area (this is the end area of ​​the inclined plane), it is determined that this area is not an inclined plane. This can avoid the error of mapping the second image imaging area and ensure the accuracy of mapping the entire area where the cleaning robot is located.

[0082] In one embodiment, the step of rapidly constructing a 3D map based on the laser feedback environment information and the image feedback environment information further includes:

[0083] Step S411: When the second mapping mode is to map the third image imaging area in the image feedback environment information, determine the fourth actual distance of the entire third image imaging area in the laser feedback environment information, and determine the second theoretical change distance of the third image imaging area in the image feedback environment information.

[0084] Step S412: When the third actual distance matches the second theoretical change distance, perform rapid three-dimensional mapping of the third image imaging area based on the fourth actual distance.

[0085] In this embodiment, under the second mapping mode, there is a scheme for mapping obstacles in the third image imaging area. The mapping object is the obstacle, such as a chair or table in the space where the cleaning robot is located. At this time, the fourth actual distance of the entire third image imaging area in the laser feedback environment information is determined. The fourth actual distance refers to the actual distance from the cleaning robot to the obstacle. Simultaneously, the second theoretical change distance of the third image imaging area in the image feedback environment information is determined. The second theoretical change distance refers to the distance from the obstacle to the cleaning robot. When the third actual distance matches the second theoretical change distance (the change pattern is the same; for example, if the change in the third actual distance is determined to be from 5 meters to 10 meters, this position is determined to be the boundary of the obstacle), a rapid 3D mapping of the third image imaging area can be performed based on the fourth actual distance. For each laser point, by setting the number of laser point data selected in the preset window to be less than or equal to the number of laser point data detected by the laser range sensor for an object of a preset size, at least one of the laser point data detected by the laser range sensor from the object of the preset size can be used to calculate a correlation coefficient. Then, based on the correlation coefficient, it can be determined whether the laser point data is needed, and the object represented by the laser point data can be displayed on the map without filtering out the laser point data, thereby improving the integrity of the map.

[0086] Furthermore, based on the first, second, third, and / or fourth embodiments of this application described above, a fifth embodiment of the rapid mapping method for cleaning robots of this application is proposed. In this embodiment, reference is made to... Figure 3 , Figure 3 This is a flowchart illustrating a second embodiment of the rapid mapping method for cleaning robots according to this application. The rapid mapping method for cleaning robots further includes:

[0087] Step S50: Determine the target mapping corresponding to each image imaging region in the image feedback environment information, and determine the second image connection relationship corresponding to each image imaging region;

[0088] Step S60: When the second image connection relationship is a preset distance matching connection relationship, the image imaging areas corresponding to the second image connection relationship are linked to obtain a cleaning robot map;

[0089] Step S70: When the second image connection relationship is not a preset distance matching connection relationship, the image imaging area corresponding to the second image connection relationship is layered and then linked to obtain a cleaning robot map. The layering process includes layering based on the actual distance of the image imaging area corresponding to the second image connection relationship.

[0090] In this embodiment, after obtaining the target mapping corresponding to each image imaging region, i.e., the mapping determined based on the first or second mapping mode, the second image connection relationship corresponding to each image imaging region is determined, i.e., the connection relationship between image imaging regions. When it differs from the first image connection relationship, the second image connection relationship refers to the connection relationship between image imaging regions. At this time, it is divided into normal image connection relationships and abnormal image connection relationships for separate processing. When it is a normal image connection relationship, i.e., the second image connection relationship is a preset distance matching connection relationship, i.e., the connection position distance of the image imaging regions is determined to be the same, i.e., the distance matching connection relationship refers to the relationship of the same distance defined by the user, and the cleaning robot map is obtained directly based on the image imaging regions corresponding to the second image connection relationship, i.e., the mapping image of the entire region is obtained; when it is an abnormal image connection relationship, i.e., the second image connection relationship is not a preset distance matching connection relationship, the image imaging regions corresponding to the second image connection relationship are first processed in layers before being linked to obtain the cleaning robot map. The layer processing includes layering based on the actual distance of the image imaging regions corresponding to the second image connection relationship, i.e., if the connection position is a corner, the mapping image of the entire region is determined based on the layer processing to ensure the accuracy of image connection.

[0091] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the rapid mapping method for cleaning robots in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0092] This application also provides a rapid mapping device for cleaning robots; please refer to [reference needed]. Figure 4 The rapid mapping device for the cleaning robot includes:

[0093] The information acquisition module 10 is used to acquire the mapping environment information of the cleaning robot, wherein the mapping environment information includes the laser feedback environment information collected by the laser device and the image feedback environment information collected by the image acquisition device;

[0094] The mode determination module 20 is used to determine mapping mode information based on the image feedback environment information, wherein the mapping mode information includes a first mapping mode with single feedback information and a second mapping mode with multiple feedback information.

[0095] The first mapping module 30 is used to perform rapid three-dimensional mapping based on the laser feedback environment information or the image feedback environment information when the mapping mode information is the first mapping mode.

[0096] The second mapping module 40 is used to perform rapid three-dimensional mapping based on the laser feedback environment information and the image feedback environment information when the mapping mode information is the second mapping mode.

[0097] The rapid mapping device for cleaning robots provided in this application, employing the rapid mapping method for cleaning robots in the above embodiments, can solve the technical problem of low mapping accuracy for cleaning robots. Compared with the prior art, the beneficial effects of the rapid mapping device for cleaning robots provided in this application are the same as those of the rapid mapping method for cleaning robots provided in the above embodiments, and other technical features in the rapid mapping device for cleaning robots are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0098] This application provides a rapid mapping system for a cleaning robot. The system includes a laser device, an image acquisition device, and a controller. The controller is connected to both the laser device and the image acquisition device. The controller includes at least one processor and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which are then executed to enable the at least one processor to perform the rapid mapping method for the cleaning robot described in Embodiment 1. It is worth noting that other devices shared with the cleaning robot, such as a power supply, may also be present in the rapid mapping system; these will not be described in detail here.

[0099] The following is for reference. Figure 5 The diagram illustrates a structural schematic of a controller suitable for implementing embodiments of this application. The controller in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The controller shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0100] like Figure 5As shown, the controller may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for controller operation. The processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following devices can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the controller to communicate wirelessly or wiredly with other devices to exchange data. Although a controller with various devices is shown in the figure, it should be understood that implementation or possession of all the devices shown is not required. More or fewer devices may be implemented alternatively.

[0101] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0102] The controller provided in this application employs the rapid mapping method for cleaning robots described in the above embodiments, which can solve the technical problem of low mapping accuracy of cleaning robots. Compared with the prior art, the beneficial effects of the controller provided in this application are the same as those of the rapid mapping method for cleaning robots provided in the above embodiments, and other technical features of the controller are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0103] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0104] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0105] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the rapid mapping method for cleaning robots in the above embodiments.

[0106] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor devices, apparatuses, or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution apparatus, device, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0107] The aforementioned computer-readable storage medium may be included in the controller; or it may exist independently and not be assembled into the controller.

[0108] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the controller, cause the controller to:

[0109] The mapping environment information of the cleaning robot is obtained, wherein the mapping environment information includes the laser feedback environment information collected by the laser device and the image feedback environment information collected by the image acquisition device;

[0110] Mapping mode information is determined based on the image feedback environment information, wherein the mapping mode information includes a first mapping mode with single feedback information and a second mapping mode with multiple feedback information.

[0111] When the mapping mode information is the first mapping mode, rapid three-dimensional mapping is performed based on the laser feedback environment information or the image feedback environment information.

[0112] When the mapping mode information is the second mapping mode, rapid 3D mapping is performed based on the laser feedback environment information and the image feedback environment information.

[0113] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0114] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using dedicated hardware-based apparatus to perform the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0115] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0116] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described rapid mapping method for cleaning robots, thereby solving the technical problem of low mapping accuracy of cleaning robots. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the rapid mapping method for cleaning robots provided in the above embodiments, and will not be repeated here.

[0117] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the rapid mapping method for cleaning robots described above.

[0118] The computer program product provided in this application can solve the technical problem of low mapping accuracy of cleaning robots. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the rapid mapping method for cleaning robots provided in the above embodiments, and will not be repeated here.

[0119] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for rapid mapping of a cleaning robot, characterized in that, The rapid mapping method for cleaning robots is applied to a rapid mapping system for cleaning robots, which includes laser devices and image acquisition devices. The rapid mapping method for cleaning robots includes: The mapping environment information of the cleaning robot is obtained, wherein the mapping environment information includes the laser feedback environment information collected by the laser device and the image feedback environment information collected by the image acquisition device; Mapping mode information is determined based on the image feedback environment information, wherein the mapping mode information includes a first mapping mode with single feedback information and a second mapping mode with multiple feedback information, and wherein the step of determining the mapping mode information based on the image feedback environment information includes: The image imaging region and the corresponding image imaging features in the image feedback environment information are determined. When the image imaging features match a preset planar imaging feature, the mapping mode information of the first image imaging region in the image feedback environment information is determined as a first mapping mode, wherein the first image imaging region includes the image imaging region whose image imaging features match the preset planar imaging feature. When the image imaging features match a preset inclined plane imaging feature, the mapping mode information of the second image imaging region in the image feedback environment information is determined as a second mapping mode, wherein the second image imaging region includes the image imaging features whose image imaging features match the preset planar imaging feature. The image imaging region is set to match the inclined plane imaging feature. When the image imaging feature matches the preset obstacle imaging feature, the mapping mode information of the third image imaging region in the image feedback environment information is determined as the second mapping mode, wherein the second image imaging region includes the image imaging region that matches the image imaging feature with the preset obstacle imaging feature. When the image imaging feature matches the preset cleaning object imaging feature, the mapping mode information of the fourth image imaging region in the image feedback environment information is determined as the first mapping mode, wherein the fourth image imaging region includes the image imaging region that matches the image imaging feature with the preset cleaning object imaging feature. When the mapping mode information is the first mapping mode, rapid three-dimensional mapping is performed based on the laser feedback environment information or the image feedback environment information. When the mapping mode information is the second mapping mode, rapid 3D mapping is performed based on the laser feedback environment information and the image feedback environment information.

2. The rapid mapping method for cleaning robots as described in claim 1, characterized in that, The step of determining the image imaging region in the image feedback environment information and the image imaging features corresponding to the image imaging region includes: Based on preset image segmentation imaging features, the image in the image feedback environment information is divided into multiple initial regions, wherein the image segmentation imaging features include preset planar imaging features, preset inclined plane imaging features, preset obstacle imaging features, and preset clean object imaging features. A first image connection relationship is determined between each initial region, and each initial region is expanded or shrunk based on the first image connection relationship to obtain multiple image imaging regions. Each image imaging region uniquely corresponds to a segmentation image imaging feature as an image imaging feature.

3. The rapid mapping method for cleaning robots as described in claim 1, characterized in that, The mapping mode information includes the target image imaging region and the target mapping mode corresponding to the target image imaging region. Following the step of determining the mapping mode information based on the image feedback environment information, the following steps are included: When the target mapping mode is the first mapping mode and the image imaging features of the target image imaging area match the preset planar imaging features, the azimuth angle and range information of the target image imaging area are written into the mapping mode information. When the target mapping mode is the first mapping mode and the image imaging features of the target image imaging area match the preset cleaning object imaging features, the azimuth angle of the target image imaging area is written into the mapping mode information.

4. The rapid mapping method for cleaning robots as described in claim 3, characterized in that, The step of rapidly constructing a 3D map based on the laser feedback environment information or the image feedback environment information includes: When the first mapping mode is to map the first image imaging region in the image feedback environment information, the image distance corresponding to the azimuth angle in the image feedback environment information is determined, and the first actual distance corresponding to the image distance is determined based on a preset image imaging ratio; the image range corresponding to the range information in the image feedback environment information is determined, and the actual range corresponding to the image range is determined based on a preset image imaging ratio; and the first image imaging region is quickly mapped in three dimensions based on the first actual distance and the actual range. When the first mapping mode is to map the fourth image imaging area in the image feedback environment information, the second actual distance corresponding to the azimuth angle in the laser feedback environment information is determined, and the fourth image imaging area is quickly mapped based on the second actual distance.

5. The rapid mapping method for cleaning robots as described in claim 1, characterized in that, The step of rapidly constructing a 3D map based on the laser feedback environment information and the image feedback environment information includes: When the second mapping mode is to map the second image imaging area in the image feedback environment information, the third actual distance of the entire second image imaging area in the laser feedback environment information is determined, and the first theoretical change distance of the second image imaging area in the image feedback environment information is determined. When the third actual distance matches the first theoretical change distance, a rapid three-dimensional map is constructed on the second image imaging area based on the third actual distance.

6. The rapid mapping method for cleaning robots as described in claim 5, characterized in that, The step of rapidly constructing a 3D map based on the laser feedback environment information and the image feedback environment information further includes: When the second mapping mode is to map the third image imaging region in the image feedback environment information, the fourth actual distance of the entire third image imaging region in the laser feedback environment information is determined, and the second theoretical change distance of the third image imaging region in the image feedback environment information is determined. When the third actual distance matches the second theoretical change distance, a rapid three-dimensional map is constructed on the third image imaging area based on the fourth actual distance.

7. The rapid mapping method for cleaning robots as described in any one of claims 1 to 6, characterized in that, The rapid mapping method for cleaning robots also includes: Determine the target mapping corresponding to each image imaging region in the image feedback environment information, and determine the second image connection relationship corresponding to each image imaging region; When the second image connection relationship is a preset distance matching connection relationship, the image imaging areas corresponding to the second image connection relationship are linked to obtain the cleaning robot map; When the second image connection relationship is not a preset distance matching connection relationship, the image imaging area corresponding to the second image connection relationship is layered and then linked to obtain the cleaning robot map. The layering process includes layering based on the actual distance of the image imaging area corresponding to the second image connection relationship.

8. A rapid mapping system for cleaning robots, characterized in that, The rapid mapping system for the cleaning robot includes a laser device, an image acquisition device, and a controller. The controller is connected to the laser device and the image acquisition device respectively. The controller includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the rapid mapping method for the cleaning robot as described in any one of claims 1 to 7.

9. A medium, characterized in that, The medium is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the rapid mapping method for a cleaning robot as described in any one of claims 1 to 7.

Images