Floor detection method and apparatus, storage medium, and cleaning device

Abstract

A floor detection method and apparatus, a storage medium, and a cleaning device. The floor detection method comprises: acquiring current frame point cloud data of a target area collected by a cleaning device, the current frame point cloud data comprising a point cloud corresponding to each point in the target area (210); determining a reference point cloud height value of a floor point corresponding to each point cloud in the current frame point cloud data, the reference point cloud height value being defined as a point cloud height value of a floor point collected by the cleaning device in a reference floor (220); and, on the basis of the reference point cloud height value of the floor point corresponding to each point cloud in the current frame point cloud data and an actual point cloud height value of each point cloud in the current frame point cloud data, performing floor detection on the target area (230).

Description

Ground detection method, device, storage medium and cleaning equipment CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This disclosure claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on March 19, 2024, with application number 202410317488.4 and application name “Ground detection method, device, storage medium and cleaning equipment”, the entire contents of which are incorporated into this application by reference. Technical Field

[0002] The present disclosure relates to the field of data processing technology, and in particular to a ground detection method, device, storage medium, and cleaning equipment. Background Art

[0003] Cleaning equipment usually needs to perform ground detection on the area where it is located in order to plan a matching movement path. At present, cleaning equipment often uses the data collected by the cleaning equipment to perform ground detection on the area.

[0004] However, due to certain unavoidable factors, the data collected by cleaning equipment may contain errors, thereby reducing the accuracy of ground detection of the area where the cleaning equipment is located, and in turn causing the cleaning equipment to plan inaccurate movement paths. For example, if the cleaning equipment collects data through a time-of-flight sensor, the complex diffuse and specular reflections in the real area will cause the data collected by the time-of-flight sensor to be erroneous. Based on this, how to improve the accuracy of ground detection of the area where the cleaning equipment is located is a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The present disclosure provides a ground detection method, device, storage medium and cleaning equipment.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by practice of the present disclosure.

[0007] According to a first aspect of the present disclosure, a ground detection method is provided, the method comprising: acquiring current frame point cloud data of a target area collected by a cleaning device, the current frame point cloud data comprising point clouds corresponding to each point in the target area; determining a reference point cloud height value of a ground point corresponding to each point cloud in the current frame point cloud data, the reference point cloud height value being defined as a point cloud height value of a ground point collected by the cleaning device in a reference ground; and performing ground detection on the target area based on the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data and the actual point cloud height value of each point cloud in the current frame point cloud data.

[0008] In some embodiments of the present disclosure, based on the aforementioned scheme, the current frame point cloud data includes multiple point cloud sets, wherein each point cloud in each point cloud set is distributed in the same divergent direction of the cleaning equipment, and determining the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data includes: determining the initial point cloud height value corresponding to each point cloud set; and based on the initial point cloud height value, determining the reference point cloud height value corresponding to each point cloud in each point cloud set.

[0009] In some embodiments of the present disclosure, based on the aforementioned scheme, the determining of the initial point cloud height value corresponding to each point cloud set includes: for each point cloud set, according to the divergence direction, determining a preset number of point clouds in front of each point cloud set as the initial point cloud; and determining the initial point cloud height value corresponding to each point cloud set based on the actual point cloud height value of each of the initial point clouds.

[0010] In some embodiments of the present disclosure, based on the aforementioned scheme, the determining of the initial point cloud height value corresponding to each point cloud set includes: for each point cloud set, according to the divergence direction, determining the first point cloud in each point cloud set as the target point cloud; obtaining the previous frame of point cloud data of the target area collected by the cleaning equipment, and determining the point cloud set corresponding to each point cloud set from the previous frame of point cloud data as the first point cloud set; calculating the absolute value of the difference between the actual point cloud height value of the target point cloud and the initial point cloud height value corresponding to the first point cloud set; if the absolute value of the difference is greater than a preset threshold, the initial point cloud height value corresponding to the first point cloud set is used as the initial point cloud height value corresponding to each point cloud set; if the absolute value of the difference is less than or equal to the preset threshold, the actual point cloud height value of the target point cloud is used as the initial point cloud height value corresponding to each point cloud set.

[0011] In some embodiments of the present disclosure, based on the aforementioned scheme, the determining of the initial point cloud height value corresponding to each point cloud set includes: for each point cloud set, according to the divergence direction, determining the first point cloud in each point cloud set as the target point cloud; determining a second point cloud set from the multiple point cloud sets, and determining the initial point cloud height value corresponding to the second point cloud set; determining the initial point cloud height value corresponding to each point cloud set based on the initial point cloud height value corresponding to the second point cloud set and the actual point cloud height value of the target point cloud.

[0012] In some embodiments of the present disclosure, based on the aforementioned scheme, the reference point cloud height value corresponding to each point cloud in each point cloud set is determined based on the initial point cloud height value, including: for each point cloud set, according to the divergence direction, the first point cloud in each point cloud set is determined as the target point cloud; the initial point cloud height value is used as the reference point cloud height value corresponding to the target point cloud; according to a preset correction rule, the reference point cloud height value corresponding to the target point cloud is corrected, and the height value obtained after correction is used as the reference point cloud height value corresponding to the next point cloud adjacent to the target point cloud; the next point cloud adjacent to the target point cloud is used as a new target point cloud, and the process of correcting the reference point cloud height value corresponding to the target point cloud according to the preset correction rule is returned to execute until the reference point cloud height value corresponding to each point cloud in each point cloud data is obtained.

[0013] In some embodiments of the present disclosure, based on the aforementioned scheme, the ground detection of the target area is performed based on the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data, and the actual point cloud height value of each point cloud in the current frame point cloud data, including: for each point cloud in the current frame point cloud data, calculating the height difference between the actual point cloud height value and the reference point cloud height value, and obtaining the height difference corresponding to each point cloud in the current frame point cloud data; based on the height difference corresponding to each point cloud in the current frame point cloud data, performing ground detection on the target area.

[0014] In some embodiments of the present disclosure, based on the aforementioned scheme, the ground detection of the target area is performed based on the height difference corresponding to each point cloud in the current frame point cloud data, including: marking the points corresponding to the point clouds in the current frame point cloud data whose height differences meet the first preset condition as ground points; marking the points corresponding to the point clouds in the current frame point cloud data whose height differences meet the second preset condition as obstacle points.

[0015] In some embodiments of the present disclosure, based on the aforementioned scheme, the method also includes: fitting each point marked as a ground point to obtain a plane equation of a target plane corresponding to the target area; and determining the posture data of the cleaning device at the current moment based on the plane equation of the target plane and the plane equation of the reference plane.

[0016] In some embodiments of the present disclosure, based on the aforementioned scheme, the method further includes: projecting the obstacle points in the target area to obtain projection data; and determining the obstacle type of the obstacles in the target area based on the projection data and the height difference corresponding to each obstacle point.

[0017] In some embodiments of the present disclosure, based on the aforementioned scheme, determining the obstacle type of the obstacle in the target area according to the projection data and the height difference corresponding to each of the obstacle points includes: filtering the noise points in each of the obstacle points according to the projection data to obtain the target obstacle point; and determining the obstacle type of the obstacle in the target area according to the projection data and the height difference corresponding to each of the target obstacle points.

[0018] In some embodiments of the present disclosure, based on the aforementioned solution, the obstacle type includes at least one of a cliff obstacle, a wire obstacle, and a low obstacle.

[0019] According to a second aspect of the present disclosure, a ground detection device is provided, which includes: an acquisition unit for acquiring current frame point cloud data of a target area collected by a cleaning device, the current frame point cloud data including point clouds corresponding to each point in the target area; a determination unit for determining a reference point cloud height value of a ground point corresponding to each point cloud in the current frame point cloud data, the reference point cloud height value being defined as a point cloud height value of a ground point collected by the cleaning device in a reference ground; a detection unit for performing ground detection on the target area based on the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data, and the actual point cloud height value of each point cloud in the current frame point cloud data.

[0020] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, characterized in that at least one program code is stored in the computer-readable storage medium, and the at least one program code is loaded and executed by a processor to implement the operations performed by the method described in the first aspect above.

[0021] According to a fourth aspect of the present disclosure, a cleaning device is provided, comprising one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the at least one program code is loaded and executed by the one or more processors to implement the operations performed by the method described in the first aspect above.

[0022] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0024] FIG1 is a schematic diagram showing point cloud data collected by a time-of-flight sensor according to some current embodiments;

[0025] FIG2 shows a schematic flow chart of a ground detection method according to some embodiments of the present disclosure;

[0026] FIG3 shows a schematic diagram of a scene with reference point cloud height values ​​in FIG1 ;

[0027] FIG4 is a schematic diagram showing a detailed process of determining the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data in FIG1 ;

[0028] FIG5 is a schematic diagram showing the point cloud data of the current frame in FIG1 ;

[0029] FIG6 is a schematic diagram showing the point cloud data of the current frame and the point cloud data of the previous frame in FIG1 ;

[0030] FIG7 shows a detailed flowchart of determining the reference point cloud height value corresponding to each point cloud in each point cloud set based on the initial point cloud height value according to the ground detection method of some embodiments of the present disclosure;

[0031] FIG8 is a schematic diagram showing a detailed process of performing ground detection on the target area based on the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data and the actual point cloud height value of each point cloud in the current frame point cloud data according to some embodiments of the present disclosure;

[0032] FIG9 shows a detailed flowchart of determining the obstacle type of an obstacle in a target area according to a ground detection method according to some embodiments of the present disclosure;

[0033] FIG10 is a schematic diagram showing the projection data in FIG9 ;

[0034] FIG11 shows a block diagram of a ground detection device according to some embodiments of the present disclosure;

[0035] FIG12 shows a schematic structural diagram of a cleaning device according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0036] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0037] In addition, the described features, structures or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, well-known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present disclosure.

[0038] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0039] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0040] It should be noted that the term "plurality" used in this document refers to two or more. "And / or" describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. The character " / " generally indicates an "or" relationship between the associated objects.

[0041] It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the present disclosure described herein can be practiced in an order other than that illustrated or described.

[0042] To make the objectives, technical solutions, and advantages of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0043] It should be noted that the cleaning device mentioned in the present disclosure may be a sweeping robot, a mopping robot, or other smart devices with cleaning functions.

[0044] Figure 1 shows a schematic diagram of point cloud data collected by a time-of-flight sensor in some current embodiments. In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the background technology involved in the present disclosure will be described in detail below with reference to Figure 1.

[0045] In the present disclosure, the cleaning equipment can use the data collected by the configured equipment to perform ground detection on the area, wherein the configured equipment can be one or more of a time-of-flight sensor, a single-line laser sensor, a dual-line laser sensor, a lidar, and the like.

[0046] The following uses the time-of-flight sensor as an example to analyze and explain the data errors in the data collected by the cleaning equipment.

[0047] The data collected by a time-of-flight sensor contains two main types of errors: one is the inherent instrument error of the time-of-flight sensor, and the other is MPI (Multi-Path Interference) error, which is caused by diffuse or even specular reflection in the area.

[0048] The instrument error of the time-of-flight sensor is explained below.

[0049] Generally, as the distance between the object to be measured and the cleaning device increases, the instrument error in the point cloud data obtained by the time-of-flight sensor when detecting the object to be measured also increases.

[0050] If the distance between the object to be measured and the cleaning equipment is less than the first distance, the instrument error in the point cloud data obtained by the time-of-flight sensor when detecting the object to be measured is small, and the instrument error of the time-of-flight sensor can be ignored. However, if the distance between the object to be measured and the cleaning equipment is greater than or equal to the first distance, the instrument error in the point cloud data obtained by the time-of-flight sensor when detecting the object to be measured is large, as shown in (1) in Figure 1. Therefore, if the instrument error of the time-of-flight sensor is ignored, the accuracy of ground detection of the area will be greatly reduced. Among them, the first distance can be 4m, 5m, etc., and the specific value of the first distance is related to the model of the time-of-flight sensor.

[0051] The scene corresponding to (1) in FIG1 is as follows: the cleaning device 10 is on a flat ground 12, and there are no obstacles on the flat ground 12. The flat ground 12 is detected by a time-of-flight sensor. There is a wall 11 in the flat ground 12, and the distance between the wall 11 and the cleaning device 10 exceeds a first distance. The cleaning device 10 is on the flat ground as shown in FIG1 (1). The time-of-flight sensor transmits a signal in the direction of the wall 11 and receives a reflected signal from the object to be measured, thereby obtaining point cloud data 13. The point cloud data 13 includes a point cloud corresponding to a ground point in the flat ground 12 and an actual point cloud height value of the point cloud. The actual point cloud height value of the point cloud in the point cloud data 13 is the height value of the point cloud measured by the time-of-flight sensor, and the ground value corresponding to each point cloud in the point cloud data 13 is the same.

[0052] Because there are no obstacles on the flat ground 12, if the time-of-flight sensor does not have any errors, then the actual point cloud height values ​​of each point cloud in the obtained point cloud data 13 should be exactly the same. However, due to the instrument error of the time-of-flight sensor, there are large differences in the actual point cloud height values ​​of each point cloud in the point cloud data 13, causing the actual point cloud height values ​​of the point cloud data to be in a tilted state as shown in (1) in Figure 1, wherein the farther the point in the flat ground 12 is from the cleaning device 10, the greater the error in the actual point cloud height value of the point cloud corresponding to the point cloud. For example, assuming that there is no error in the time-of-flight sensor, the point cloud height value of the ground point in the flat ground 12 is 1.5m, then the error in the actual point cloud height value of point cloud B in the point cloud data 13 is the smallest, which may be 0, and the actual point cloud height value of point cloud A is 1.5m. The error in the actual point cloud height value of point cloud A in the point cloud data 13 is the largest, which may be 2.5m. Therefore, in this case, if the errors in the actual point cloud height values ​​of each point cloud in the point cloud data 13 are not eliminated, then when the cleaning equipment believes that point cloud B is the point cloud corresponding to the ground point in the flat ground 12, it may believe that point cloud A is the point cloud corresponding to the obstacle on the flat ground 12, which will cause the cleaning equipment to plan an inaccurate moving path.

[0053] The following describes the MPI error of the flight sensor:

[0054] If the distance between the object to be measured and the cleaning device is less than the second distance, there is an MPI error in the point cloud data obtained by the time-of-flight sensor when detecting the object to be measured. For example, as shown in (2) in Figure 1, the second distance is less than or equal to the first distance.

[0055] Generally, as the distance between the object to be measured and the cleaning device increases, the MPI error in the point cloud data obtained by the time-of-flight sensor when detecting the object to be measured also increases.

[0056] The scene corresponding to (2) in Figure 1 is: the cleaning device 10 is on the flat ground 12, and there are no obstacles on the flat ground 12. The flat ground 12 is detected by a time-of-flight sensor, wherein there is a wall 11 on the flat ground 12, and the distance between the wall 11 and the cleaning device is less than the second distance. The cleaning device 10 is on the flat ground as shown in (2) in Figure 1, and transmits a signal in the direction of the wall 11 through the time-of-flight sensor, and receives the reflected signal of the object to be tested, thereby obtaining point cloud data 14. The point cloud data 14 includes the point cloud corresponding to the ground point in the flat ground 12, and the actual point cloud height value of the point cloud.

[0057] Because there are no obstacles on the flat ground 12, if the time-of-flight sensor has no errors, the actual point cloud height values ​​of each point cloud in the collected point cloud data 14 should be exactly the same. However, due to the presence of MPI errors, there are large differences in the actual point cloud height values ​​of each point cloud in the point cloud data 14, causing the actual point cloud height values ​​of the point cloud data 14 to appear sunken. The farther the point on the flat ground 12 is from the cleaning device 10, the greater the MPI error in the actual point cloud height value of the point cloud corresponding to the point cloud. For example, assuming that the time-of-flight sensor has no errors and the point cloud height value of the ground point on the flat ground 12 is 1.5m, then the error in the actual point cloud height value of point cloud D in the point cloud data 14 is the smallest, possibly 0, and the actual point cloud height value of point cloud D is 1.5m. The error in the actual point cloud height value of point cloud C in the point cloud data 14 is the largest, possibly 0.5m. Therefore, in this case, if the errors in the actual point cloud height values ​​of each point cloud in the point cloud data 14 are not eliminated, then when the cleaning equipment believes that point cloud D is the point cloud corresponding to the ground point in the flat ground 12, it may believe that point cloud C is the point cloud corresponding to the obstacle below the flat ground 12, that is, it may believe that point cloud C is the point cloud corresponding to the cliff, which will cause the cleaning equipment to plan an inaccurate moving path.

[0058] To sum up, since the cleaning equipment detects the area where it is located, there are inevitable errors in the collected point cloud data. If the errors in the collected point cloud data are not eliminated, the accuracy of ground detection of the area will be reduced, and the cleaning equipment will be forced to plan an incorrect movement path. The incorrect movement path may cause the cleaning equipment to have reduced work efficiency, collide with obstacles, fall off a cliff, etc. Therefore, in response to this defect, the present disclosure proposes a ground detection method to eliminate errors in the data collected by the cleaning equipment, thereby improving the accuracy of ground detection of the area.

[0059] The following will describe some embodiments of the present disclosure in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0060] FIG2 shows a flow chart of a ground detection method according to some embodiments of the present disclosure. Referring to FIG2 , a ground detection method provided by the present disclosure includes the following steps 210 to 230 .

[0061] In step 210 , current frame point cloud data of the target area collected by the cleaning device is acquired, where the current frame point cloud data includes point clouds corresponding to each point in the target area.

[0062] In some embodiments, the cleaning device can acquire the current frame point cloud data of the target area using a time-of-flight sensor, or can acquire the current frame point cloud data of the target area using a lidar. The present disclosure does not limit the specific method by which the cleaning device acquires the current frame point cloud data.

[0063] It should be noted that the current frame point cloud data includes several point clouds, where each point cloud corresponds to each point in the target area, and each point cloud has an actual point cloud height value, which is the height value of the point cloud in the current frame point cloud data collected by the cleaning equipment.

[0064] Continuing to refer to FIG2 , in step 220 , the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data is determined. The reference point cloud height value is defined as the point cloud height value of the ground point collected by the cleaning device in the reference ground.

[0065] It should be noted that the ground points collected in the reference ground have corresponding reference point clouds, and the height value of the reference point cloud is the reference point cloud height value.

[0066] In some embodiments, the target area corresponds to a real ground plane, which contains ground points, i.e., the ground points corresponding to each point cloud in the current frame of point cloud data. To eliminate errors in the collected point cloud data of the current frame, each point cloud in the current frame of point cloud data is not assumed to be located on the plane of the real ground plane. Instead, each point cloud in the current frame of point cloud data is assumed to be located on the corresponding reference ground plane. In some embodiments, point cloud 1 in the current frame of point cloud data is assumed to be on reference ground plane 1, point cloud 2 is assumed to be on reference ground plane 2, and point cloud 3 is assumed to be on reference ground plane 3.

[0067] Because there are ground points in the real ground and ground points in the reference ground, if point cloud 1 in the current frame point cloud data is set to be on reference ground 1, ground point 11 corresponding to point cloud 11 can be collected from reference ground 1, and there is ground point 12 corresponding to point cloud 1 on the real ground, then the point cloud of ground point 11 is the reference point cloud 1, and the height value of reference point cloud 1 is the reference point cloud height value of ground point 12 corresponding to point cloud 1 in the current frame point cloud data.

[0068] Fig. 3 is a schematic diagram of a scene of the reference point cloud height value in Fig. 1. In order to enable those skilled in the art to better understand this embodiment, the reference point cloud height value of this embodiment will be explained below with reference to Fig. 3.

[0069] The scenario corresponding to (1) in Figure 3 is: the cleaning device 30 detects the target area on the ground 32, wherein there are obstacles on the ground 32 and there is a wall 31, and the distance between the wall 31 and the cleaning device 30 is greater than the first distance. The time-of-flight sensor in the cleaning device 30 transmits a signal in the direction of the wall 31 and receives the reflected signal of the object to be tested, thereby obtaining the current frame point cloud data 33.

[0070] In order to eliminate the errors existing in the current frame point cloud data 33, it is set that each point cloud in the current frame point cloud data 33 has a corresponding reference ground, that is, it is set that each point cloud in the current frame point cloud data 33 is not all on the ground 32, and point cloud data 34 is obtained based on the point cloud corresponding to the ground point collected from the reference ground.

[0071] For example, the point cloud A31 in the current frame point cloud data 33 corresponds to the reference ground A31, and the point cloud of the ground points collected from the reference ground A31 is set as the reference point cloud A32. In addition, the ground point A33 on the ground 32 corresponds to the point cloud A31. Therefore, the reference point cloud height value of the ground point A33 corresponding to the point cloud A31 in the current frame point cloud data 33 is the height value of the reference point cloud A32.

[0072] In some embodiments, the point cloud B31 in the current frame point cloud data 33 corresponds to the reference ground B31, and the point cloud of the ground points collected from the reference ground B31 is set as the reference point cloud B32. In addition, the ground point B33 on the ground 32 corresponds to the point cloud B31. Therefore, the reference point cloud height value of the ground point B33 corresponding to the point cloud B31 in the current frame point cloud data 33 is the height value of the reference point cloud B32.

[0073] As can be seen from Figure 3 (1), the reference ground corresponding to point cloud A31 is different from the reference ground corresponding to point cloud B31, the reference point cloud A32 corresponding to point cloud A31 is different from the reference point cloud B32 corresponding to point cloud B31, and the height values ​​of reference point cloud A32 and reference point cloud B32 are different. Therefore, the reference point cloud height value of ground point A33 corresponding to point cloud A31 in the current frame point cloud data is the height value of reference point cloud A32, and the reference point cloud height value of ground point B33 corresponding to point cloud B31 in the current frame point cloud data is the height value of reference point cloud B32.

[0074] In summary, in the present disclosure, since the data collected by the time-of-flight sensor has instrument errors, it is not assumed that each point cloud in the current frame point cloud data 33 is on the ground 32, but on a stable reference ground corresponding to itself.

[0075] The scene corresponding to (2) in Figure 3 is: the cleaning device 30 detects the target area on the ground 36, wherein there are obstacles on the ground 36 and there is a wall 35, and the distance between the wall 35 and the cleaning device 30 is less than the second distance. The time-of-flight sensor in the cleaning device 30 transmits a signal in the direction of the wall 35 and receives the reflected signal of the object to be detected, thereby obtaining the current frame point cloud data 37. Among them, based on the point cloud of the ground points collected from the reference ground surface, point cloud data 38 is constructed. Among them, the point cloud C31 in the current frame point cloud data 37 corresponds to the reference ground C31, and the point cloud of the ground points collected from the reference ground C31 is set as the reference point cloud C32. In addition, the ground point C33 on the ground 36 corresponds to the point cloud C31. Therefore, the reference point cloud height value of the ground point C33 corresponding to the point cloud C31 in the current frame point cloud data 37 is the height value of the reference point cloud C32.

[0076] In summary, in the present disclosure, due to the MPI error of the time-of-flight sensor, it is not assumed that each point cloud in the current frame point cloud data 37 is located on the ground 36, but on a stable reference ground corresponding to itself.

[0077] The above is an explanation of the definition of the reference point cloud height value. The following is an explanation of the implementation method for determining the reference point cloud height value.

[0078] FIG4 illustrates a detailed flowchart of determining the reference point cloud height values ​​for ground points corresponding to each point cloud in the current frame of point cloud data in FIG1. ​​In some embodiments, in step 220, determining the reference point cloud height values ​​for ground points corresponding to each point cloud in the current frame of point cloud data may be performed in accordance with steps 221 to 222 as shown in FIG4.

[0079] FIG5 is a schematic diagram showing the point cloud data of the current frame in FIG1. ​​Before introducing steps 221 to 222, the representation of the point cloud data of the current frame in some embodiments of the present disclosure is first described with reference to FIG5:

[0080] In the present disclosure, the current frame point cloud data may include multiple point cloud sets, wherein the individual point clouds in each point cloud set are distributed in the same divergent direction of the cleaning device. The cleaning device detects the target area to obtain the current frame point cloud data as shown in Figure 5. The current frame point cloud data in Figure 5 includes 18 point cloud sets, each of which includes multiple point clouds. For example, point cloud set 51 contains multiple point clouds, and point cloud set 52 also contains multiple point clouds. It can be seen from Figure 5 that the individual point clouds in point cloud set 51 are distributed in the same divergent direction of the cleaning device, and the individual point clouds in point cloud set 52 are also distributed in the same divergent direction of the cleaning device, that is, in Figure 5, there are 18 divergent directions corresponding to the cleaning device, and thus 18 point cloud sets are obtained. Point cloud A51 in point cloud set 51 is the first point cloud in one divergent direction of the cleaning equipment. The point corresponding to point cloud A51 is closest to the location of the cleaning equipment, and the point corresponding to point cloud A52 is farthest from the location of the cleaning equipment. Point cloud B51 in point cloud set 52 is the first point cloud in another divergent direction of the cleaning equipment. The point corresponding to point cloud B51 is closest to the location of the cleaning equipment, and the point corresponding to point cloud B52 is farthest from the location of the cleaning equipment.

[0081] Continuing to refer to FIG. 4 , in step 221 , the initial point cloud height value corresponding to each point cloud set is determined.

[0082] The following will explain the interpretation of the initial point cloud height value in conjunction with Figure 5.

[0083] Assuming that there is a point cloud set A in the current frame point cloud data, the initial point cloud height value corresponding to the point cloud set A can be considered as the point cloud height value of the ground point on the real flat ground corresponding to the point cloud set A.

[0084] Based on the above explanation of Figure 1, it can be seen that the farther away from the cleaning equipment a point in the target area is, the greater the error in the actual point cloud height value corresponding to the point cloud. Therefore, in Figure 5, within point cloud set 51, the error in the actual point cloud height value of point cloud A51 is the smallest, while the error in the actual point cloud height value of point cloud A52 is the largest. Therefore, the initial point cloud height value corresponding to point cloud set 51 can be determined based on the actual point cloud height values ​​of one or more preceding point clouds in point cloud set 51.

[0085] It should be noted that the initial point cloud height values ​​corresponding to the various point cloud sets in the current frame point cloud data may be all different, all the same, or partially the same.

[0086] In the present disclosure, there are at least three implementation methods for determining the initial point cloud height value corresponding to each point cloud set.

[0087] In some embodiments, step 221 may be performed as follows: step 2211A to step 2215A:

[0088] Step 2211A: for each point cloud set, according to the divergence direction, determine the first point cloud in each point cloud set as the target point cloud.

[0089] Step 2212A: Acquire the last frame of point cloud data of the target area collected by the cleaning device, and determine a point cloud set corresponding to each point cloud set from the last frame of point cloud data as the first point cloud set.

[0090] Step 2213A: Calculate the absolute value of the difference between the actual point cloud height value of the target point cloud and the initial point cloud height value corresponding to the first point cloud set.

[0091] Step 2214A: If the absolute value of the difference is greater than a preset threshold, the initial point cloud height value corresponding to the first point cloud set is used as the initial point cloud height value corresponding to each point cloud set.

[0092] Step 2215A: If the absolute value of the difference is less than or equal to the preset threshold, the actual point cloud height value of the target point cloud is used as the initial point cloud height value corresponding to each point cloud set.

[0093] In the embodiment including steps 2211A to 2215A, according to the above description of FIG1 , since the error in the actual point cloud height value of the target point cloud in each point cloud set is minimal, then if the point corresponding to the target point cloud is a ground point, the actual height value of the target point cloud can be reflected as the point cloud height value of the ground point of the real ground corresponding to the point cloud set in which it is located. Therefore, the initial point cloud height value corresponding to each point cloud set can be determined based on the actual point cloud height value of the target point cloud.

[0094] FIG6 is a schematic diagram showing the point cloud data of the current frame and the point cloud data of the previous frame in FIG1. ​​The present embodiment will be described below in conjunction with FIG6:

[0095] In Figure 6, (1) is the previous frame of point cloud data of the target area collected by the cleaning equipment, and in Figure 6, (2) is the current frame of point cloud data of the target area collected by the cleaning equipment. Since both the previous frame of point cloud data and the current frame of point cloud data are collected by the cleaning equipment, the number of point cloud sets contained in the previous frame of point cloud data and the current frame of point cloud data is the same. As can be seen from Figure 6, Figure 6 (1) contains 18 point cloud sets, and Figure 6 (2) also contains 18 point cloud sets. Therefore, according to the divergent direction of the cleaning equipment, a correspondence between the multiple point cloud sets contained in the current frame of point cloud data and the multiple point cloud sets contained in the previous frame of point cloud data can be established. The dotted line in Figure 6 is used to indicate the correspondence between the point cloud sets in the previous frame of point cloud data and the point cloud sets in the current frame of point cloud data.

[0096] In some embodiments, the point cloud set 61 in the current frame point cloud data in Figure 6 corresponds to the point cloud set 62 in the previous frame point cloud data, that is, the point clouds in the point cloud set 61 are distributed in the divergent direction 1 of the cleaning equipment, and the point clouds in the point cloud set 62 are also distributed in the divergent direction 1 of the cleaning equipment.

[0097] Because the cleaning equipment needs to perform ground detection of the area in real time during operation, it is necessary to collect point cloud data for the area in real time and process the collected point cloud data. Therefore, when the cleaning equipment collects the previous frame of point cloud data, it will also process the previous frame of point cloud data, that is, it can determine the initial point cloud height value corresponding to each point cloud set in the previous frame of point cloud data. Therefore, in the previous frame of point cloud data (1) in Figure 6, each point cloud set has a corresponding initial point cloud height value, that is, point cloud set 62 has a corresponding initial point cloud height value, and point cloud set 63 also has a corresponding initial point cloud height value.

[0098] Combined with the above explanation of Figure 5, it can be seen that: in Figure 6 (2), point cloud A61 is the first point cloud of point cloud set 61, that is, point cloud A61 is determined as the target point cloud. Similarly, there are target point clouds in other point cloud sets in Figure 6 (2).

[0099] In Figure 6, if the absolute value of the difference between the actual point cloud height value of point cloud A61 and the initial point cloud height value corresponding to point cloud set 62 is greater than the preset threshold, the initial point cloud height value corresponding to point cloud set 62 is used as the initial point cloud height value corresponding to point cloud set 61; otherwise, the actual point cloud height value of point cloud A61 is used as the initial point cloud height value corresponding to point cloud set 61.

[0100] In some embodiments, the preset threshold value can be set to a value such as 0.09 cm, 1 cm, or 1.1 cm.

[0101] If the absolute value of the difference between the actual point cloud height value of point cloud A61 and the initial point cloud height value corresponding to point cloud set 62 is greater than the preset threshold, it means that the point corresponding to point cloud A61 is an obstacle point, and the actual point cloud height value of point cloud A61 cannot be directly used as the initial point cloud height value corresponding to point cloud set 61; if the absolute value of the difference between the actual point cloud height value of point cloud A61 and the initial point cloud height value corresponding to point cloud set 62 is less than or equal to the preset threshold, it means that the point corresponding to point cloud A61 is a ground point, and the actual point cloud height value of point cloud A61 can be used as the initial point cloud height value corresponding to point cloud set 61.

[0102] In other embodiments, step 221 may be performed according to steps 2211B to 2212B as follows:

[0103] Step 2211B: for each point cloud set, according to the divergence direction, determine a preset number of point clouds in front of each point cloud set as the initial point cloud.

[0104] Step 2212B: Determine the initial point cloud height value corresponding to each point cloud set based on the actual point cloud height value of each initial point cloud.

[0105] It can be understood that in the embodiment including steps 2211B to 2212B, because the error of the actual point cloud height value of the front point cloud in each point cloud set is small, the initial point cloud height value corresponding to each point cloud set can be determined based on the actual point cloud height value of each initial point cloud.

[0106] In some embodiments, the preset number can be 1, 2, 3, etc., which is not limited in this disclosure. Assuming that the preset number is 3, in FIG5 , point cloud A51 , point cloud A53 , and point cloud A54 are all initial point clouds.

[0107] The following is an example of the implementation of step 2212B in conjunction with Figure 5: In Figure 5, the preset number is 3, and point cloud A51, point cloud A53, and point cloud A54 in point cloud set 51 are initial point clouds. In some embodiments, it can be determined first whether the point corresponding to point cloud A51 is a ground point. If so, the actual point cloud height of point cloud A51 is directly used as the initial point cloud height value corresponding to point cloud set 51. If not, it is determined whether the point corresponding to point cloud A53 is a ground point. If so, the actual point cloud height of point cloud A53 is directly used as the initial point cloud height value corresponding to point cloud set 51. If not, it is determined whether the point corresponding to point cloud A54 is a ground point. If so, the actual point cloud height value of point cloud A54 is used as the initial point cloud height value corresponding to point cloud set 51. If not, the initial point cloud height value of the point cloud set corresponding to point cloud set 51 in the previous frame of point cloud data set is used as the initial point cloud height value corresponding to point cloud set 51. In other embodiments, if it is determined that the points corresponding to point cloud A51, point cloud A53, and point cloud A54 are all ground points, then the average of the actual point cloud height values ​​of point cloud A51, point cloud A53, and point cloud A54 can be used as the initial point cloud height value corresponding to point cloud set 51.

[0108] Two implementations of step 2212B are described above by way of example. Those skilled in the art may design other implementations according to actual circumstances, and this disclosure does not limit the implementations herein.

[0109] In some further embodiments, step 221 may be performed according to steps 2211C to 2213C as follows:

[0110] Step 2211C: for each point cloud set, according to the divergence direction, determine the first point cloud in each point cloud set as the target point cloud.

[0111] Step 2212C: determine a second point cloud set from the multiple point cloud sets, and determine an initial point cloud height value corresponding to the second point cloud set.

[0112] Step 2213C: Determine the initial point cloud height value corresponding to each point cloud set according to the initial point cloud height value corresponding to the second point cloud set and the actual point cloud height value of the target point cloud.

[0113] In step 2211C, any one of the multiple point cloud sets can be used as the second point cloud set, or a point cloud set in which only one adjacent point cloud set exists among the multiple point cloud sets can be used as the second point cloud set. That is, in Figure 5, point cloud set 51 can be used as the second point cloud set, or point cloud set 52 can be used as the second point cloud set.

[0114] In step 2212C, the initial point cloud height value corresponding to the second point cloud set may be determined according to any one of the above embodiments of step 221 .

[0115] Those skilled in the art can design the implementation of step 2213C according to actual conditions, and this disclosure does not limit it here.

[0116] In some embodiments, step 2213C can be performed as follows: calculate the first absolute value of the difference between the actual point cloud height value of the target point cloud of the third point cloud set and the initial point cloud height value corresponding to the second point cloud set, where the second point cloud set is a point cloud set adjacent to the target point cloud set; if the first absolute value of the difference is greater than a preset threshold, then use the initial point cloud height value corresponding to the second point cloud set as the initial point cloud height value corresponding to the third point cloud set; if the first absolute value of the difference is less than or equal to the preset threshold, then use the actual point cloud height value of the target point cloud of the third point cloud set as the initial point cloud height value corresponding to the third point cloud set; use the third point cloud set as the new second point cloud set, and return to execute the step of calculating the first absolute value of the difference between the actual point cloud height value of the target point cloud of the third point cloud set and the initial point cloud height value corresponding to the second point cloud set, until the initial point cloud height value corresponding to each point cloud set is obtained.

[0117] In Figure 5, assuming that point cloud set 51 is determined as the second point cloud set, then point cloud set 53 is adjacent to point cloud set 51, and point cloud set 54 is adjacent to point cloud set 53. After determining the initial point cloud height value corresponding to point cloud set 51, the initial point cloud height value corresponding to point cloud set 53 can be determined based on the initial point cloud height value corresponding to point cloud set 51 and the actual point cloud height value of the target point cloud in point cloud set 53. The initial point cloud height value corresponding to point cloud set 54 can be determined based on the initial point cloud height value corresponding to point cloud set 53 and the actual point cloud height value of the target point cloud in point cloud set 54.

[0118] In summary, according to step 221 , the initial point cloud height value corresponding to each point cloud set can be determined. After determining the initial point cloud height value corresponding to each point cloud set, step 222 can be performed according to the steps shown in FIG. 4 .

[0119] Continuing to refer to FIG. 4 , in step 222 , based on the initial point cloud height value, a reference point cloud height value corresponding to each point cloud in each point cloud set is determined.

[0120] Figure 7 illustrates a detailed flowchart of a ground detection method according to some embodiments of the present disclosure, which determines the reference point cloud height value corresponding to each point cloud in each point cloud set based on the initial point cloud height value. In some embodiments, step 222 can be performed according to the steps shown in Figure 7. Referring to Figure 7, step 222 includes the following steps 2221 to 2224.

[0121] In step 2221, for each point cloud set, according to the divergence direction, the first point cloud in each point cloud set is determined as the target point cloud;

[0122] In step 2222, the initial point cloud height value is used as a reference point cloud height value corresponding to the target point cloud.

[0123] According to the above description in Figure 1, in each point cloud set, the error of the actual point cloud height value of the target point cloud will be smaller than the error of the actual point cloud height value of the next adjacent point cloud, and so on. That is, in each point cloud set, the error of the actual point cloud height value of the next point cloud is greater than the error of the actual point cloud height value of the previous point cloud. Therefore, it can be determined that the error of the actual point cloud height value of the target point cloud in each point cloud set is the smallest, so the initial point cloud height value can be used as the reference point cloud height value corresponding to the target point cloud.

[0124] In step 2223, the height value of the reference point cloud corresponding to the target point cloud is corrected according to a preset correction rule, and the height value obtained after correction is used as the height value of the reference point cloud corresponding to the next point cloud adjacent to the target point cloud.

[0125] Continuing to refer to Figure 7, step 2224, the next point cloud adjacent to the target point cloud is used as the new target point cloud, and the process returns to execute the correction of the reference point cloud height value corresponding to the target point cloud according to the preset correction rule until the reference point cloud height value corresponding to each point cloud in each point cloud data is obtained.

[0126] In the present disclosure, a plurality of setting correction rules may be pre-established, and then a setting correction rule matching the current frame point cloud data may be selected according to the data type of the current frame point cloud data as a preset correction rule.

[0127] The correction rules include increasing and decreasing rules. First, the points corresponding to each point cloud in the current frame point cloud data are determined as a point set. Second, the point in the point set farthest from the location of the cleaning device is determined as the target point. If the distance from the target point to the cleaning device is greater than a first distance, the increasing rule is used as the preset rule. If the distance from the target point to the cleaning device is less than or equal to the first distance, the decreasing rule is used as the preset rule.

[0128] The decreasing rule means that the reference point cloud height value corresponding to the next point cloud in each point cloud set is smaller than the reference point cloud height value corresponding to the previous adjacent point cloud, that is, in step 2223, the reference point cloud height value corresponding to the target point cloud is corrected to reduce the reference point cloud height value corresponding to the target point cloud. The increasing rule means that the reference point cloud height value corresponding to the next point cloud in each point cloud set is larger than the reference point cloud height value corresponding to the previous adjacent point cloud, that is, in step 2223, the reference point cloud height value corresponding to the target point cloud is corrected to increase the reference point cloud height value corresponding to the target point cloud.

[0129] It should be noted that in the increasing rule and the decreasing rule, how to specifically correct the reference point cloud height value corresponding to the target point cloud can be determined based on pre-calibrated data. For example, in Figure 1, the cleaning equipment 10 can be controlled to collect point cloud data at different positions on the flat ground 12, and then the reference point cloud height value corresponding to the target point cloud can be corrected based on the collected multi-frame point cloud data.

[0130] If the preset correction rule is an incremental rule, in Figure 5, for point cloud set 51, if the initial point cloud height value corresponding to point cloud set 51 is 1.5m, then the reference point cloud height value corresponding to point cloud A51 is 1.5m, and then the reference point cloud height value of 1.5m of point cloud A51 is corrected. If the corrected height value is 1.51m, then the reference point cloud height value corresponding to point cloud A53 is 1.51m, and then the reference point cloud height value of 1.51m of point cloud A53 is further corrected. If the corrected point cloud height value is 1.53m, then the reference point cloud height value corresponding to point cloud A54 is 1.53m, and so on, the reference point cloud height value corresponding to each point cloud in point cloud set 51 can be obtained.

[0131] In summary, according to the technical solution provided by the present disclosure, the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data can be determined.

[0132] Continuing to refer to FIG2 , in step 230 , ground detection is performed on the target area based on the reference point cloud height values ​​of the ground points corresponding to each point cloud in the current frame point cloud data and the actual point cloud height values ​​of each point cloud in the current frame point cloud data.

[0133] It should be noted that the actual point cloud height value of each point cloud in the current frame point cloud data is the height value of the point cloud collected by the cleaning equipment.

[0134] Figure 8 illustrates a detailed flow chart of a ground detection method for performing ground detection on a target area based on the reference point cloud height values ​​of ground points corresponding to each point cloud in the current frame of point cloud data and the actual point cloud height values ​​of each point cloud in the current frame of point cloud data, according to some embodiments of the present disclosure. In some embodiments, step 230 can be performed according to the steps shown in Figure 8. Referring to Figure 8, step 230 can include the following steps 231 to 232.

[0135] In step 231 , for each point cloud in the current frame point cloud data, the height difference between the actual point cloud height value and the reference point cloud height value is calculated to obtain the height difference corresponding to each point cloud in the current frame point cloud data.

[0136] It should be noted that the height difference corresponding to each point cloud is the true height value of the point corresponding to each point.

[0137] It should be noted that, for each point cloud in the current frame point cloud data, the height difference corresponding to each point cloud can be determined when the reference point cloud height value of each point cloud is calculated; or the height difference corresponding to each point cloud in the current frame point cloud data can be determined after the reference point cloud height value of each point cloud in the current frame point cloud is calculated. Specifically, the timing of executing step 231 is not limited in this disclosure.

[0138] The height difference is explained below in conjunction with Figure 3: In Figure 3, assuming that the actual point cloud height value of point cloud A31 is 2.0m, and the height value of reference point cloud A32 corresponding to point cloud A31 is 1.6m, that is, the reference point cloud height value corresponding to point cloud A31 is 1.6m, then the height difference between the actual point cloud height value corresponding to point cloud A31 and the reference point cloud height value is 0.4m, that is, the true height of the point corresponding to point cloud A31 is 0.4m.

[0139] Continuing to refer to FIG8 , in step 232 , ground detection is performed on the target area based on the height difference corresponding to each point cloud in the current frame point cloud data.

[0140] In some embodiments, step 232 may include the following steps 2321 and 2322:

[0141] Step 2321: Mark the points corresponding to the point clouds whose height differences satisfy the first preset condition in the current frame point cloud data as ground points;

[0142] Step 2322: Mark the points corresponding to the point clouds whose height differences in the current frame point cloud data meet the second preset condition as obstacle points.

[0143] It should be noted that, for each point cloud in the current frame point cloud data, the point corresponding to each point can be marked when the height difference of each point cloud is calculated; or after the height difference of each point cloud in the current frame point cloud is calculated, the point corresponding to each point cloud in the current frame point cloud data can be marked. Specifically, the timing of executing steps 2321 and 2322 is not limited in this disclosure.

[0144] In some embodiments, the first preset condition may include: the height difference is greater than a first height threshold and less than a second height threshold, wherein the first height threshold can be set to a value less than 0, such as -0.05cm, -0.04cm, etc., and the second height threshold can be set to a value greater than 0, such as 0.04cm, 0.05cm, etc.

[0145] In this embodiment, the second preset condition may include the height difference being less than the first height threshold, and the height difference being greater than the second height threshold and less than the third height threshold. It is understood that if the height difference is less than the first height threshold, the corresponding point is below the ground, possibly a cliff point; if the height difference is greater than the second height threshold, the corresponding point is above the ground, possibly a low obstacle point, a wire obstacle point, etc. Therefore, the point corresponding to the point cloud whose height difference meets the second preset condition is marked as an obstacle point.

[0146] In summary, according to the above steps 2321 and 2322, the points corresponding to each point cloud in the current frame point cloud data can be marked.

[0147] In the present disclosure, the current posture of the cleaning device can also be determined based on the result of ground detection of the target area. Therefore, in other embodiments, step 232 can be performed according to the following steps 2323 to 2324:

[0148] Step 2323: Fit each point marked as a ground point to obtain a plane equation of a target plane corresponding to the target area.

[0149] Step 2324: Determine the posture data of the cleaning device at the current moment based on the plane equation of the target plane and the plane equation of the reference plane.

[0150] In some embodiments, the attitude data includes at least one of a roll angle, a pitch angle, and a yaw angle.

[0151] It can be understood that by fitting the points in the target area that are marked as ground points, a target plane can be obtained. The target plane can be considered as the ground in the target area observed by the cleaning device.

[0152] In some embodiments, the reference plane may be the actual ground of the target area, that is, the normal vector of the reference plane is (0, 0, 1).

[0153] In step 2324, the normal vector of the target plane may be determined based on the plane equation of the target plane; and the posture data of the cleaning device at the current moment may be determined based on the normal vector of the target plane and the normal vector of the reference plane.

[0154] It is understandable that based on the determined posture data, it can be determined whether the cleaning device is tilted, including left and right tilt, front and back tilt, etc., and then it can be determined whether the posture of the cleaning device at the current moment is normal.

[0155] FIG9 shows a detailed flowchart of determining the obstacle type of obstacles in a target area according to a ground detection method in some embodiments of the present disclosure. In the present disclosure, in order to further determine the obstacle type of each obstacle in the target area, the steps shown in FIG9 may be further performed. Referring to FIG9, the ground detection method in some embodiments of the disclosure further includes steps 910 to 920:

[0156] Step 910: Project the obstacle points in the target area to obtain projection data.

[0157] It should be noted that the obtained projection data includes projection shape feature data, and the projection shape feature parameters include but are not limited to shape size, shape area, etc.

[0158] Fig. 10 is a schematic diagram showing the projection data in Fig. 9. The projection data will be described below with reference to Fig. 10 .

[0159] Referring to Figure 10, after projecting the obstacles in the target area, the projection data obtained is shown in Figure 10. As can be seen from Figure 10, there are eight projection shapes.

[0160] Continuing to refer to FIG. 9 , in step 920 , the obstacle type of the obstacle in the target area is determined based on the projection data and the height difference corresponding to each target obstacle point.

[0161] In order to further improve the accuracy of ground detection of the target area, in step 920, the following steps 921 to 922 may be performed:

[0162] Step 921: Filter noise points in each obstacle point according to the projection data to obtain a target obstacle point.

[0163] Step 922: Determine the obstacle type of the obstacle in the target area based on the projection data and the height difference corresponding to each target obstacle point.

[0164] In some embodiments, because the cleaning device may mark floating dust in the target area as an obstacle point when detecting the target area, the obstacle point corresponding to the floating dust is a noise point.

[0165] In some embodiments, noise points among the various obstacle points can be filtered based on the shape area corresponding to each projection shape recorded in the projection data. For example, shapes with an area less than a preset area threshold can be selected from the projection data as first shapes, and obstacle points corresponding to the first shapes can then be filtered as noise points. For example, shapes 107 and 108 in Figure 10 are first shapes and should be filtered as noise points.

[0166] In this embodiment, it can be understood that after noise points are filtered out for each obstacle point, the remaining obstacle points are target obstacle points.

[0167] In the present disclosure, the types of obstacles that can be determined include at least one of cliff obstacles, wire obstacles, and low obstacles, among which data cables, electrical wires, etc. are wire obstacles.

[0168] In some embodiments, the method for determining whether the obstacle is a cliff obstacle in step 922 may be: directly determining the obstacle corresponding to the target obstacle point whose height difference is less than the first height threshold as a cliff obstacle.

[0169] In other embodiments, the method for determining whether the obstacle is a cliff obstacle in step 922 may include: determining obstacle A corresponding to a target obstacle point whose height difference is less than a first height threshold, and marking obstacle A as a cliff obstacle; determining whether obstacle A has been marked as a cliff obstacle multiple times, and if so, determining obstacle A as a cliff obstacle. For example, the obstacle corresponding to shape 106 in Figure 10 may be determined to be a cliff obstacle.

[0170] In the present disclosure, if the cleaning device detects the target area through time-of-flight sensing, then obstacle A is marked as a cliff obstacle based on the current frame point cloud data obtained by the time-of-flight sensor. In addition, the cleaning device can also detect the target area through other line sensors, such as single-line laser or dual-line laser. If the data detected by other line sensors also considers obstacle A to be a cliff obstacle, then obstacle A will also be marked as a cliff obstacle. Then, obstacle A is marked as a cliff obstacle multiple times, and the cleaning device can determine that obstacle A is a cliff obstacle.

[0171] In some embodiments, determining whether an obstacle is a wire obstacle in step 922 may be performed by: identifying target obstacle points whose height difference is greater than a second height threshold and less than a fourth height threshold, as a first obstacle point set; and determining, in the projection data, that the obstacle corresponding to target obstacle point B in the first obstacle point set satisfies a preset requirement if the second shape corresponding to target obstacle point B satisfies the preset requirement, wherein the fourth height threshold is less than the third height threshold. For example, in Figure 10, if the height difference between target obstacle points corresponding to shapes 103, 104, and 101 is greater than the second height threshold and less than the fourth height threshold, then the obstacles corresponding to shapes 103, 104, and 101 may be marked as wire obstacles.

[0172] In some embodiments, the method for determining whether the obstacle is a low obstacle in step 922 can be: marking the obstacles corresponding to the target obstacle points other than the target obstacle point B in the first obstacle point set as low obstacles; and determining the target obstacle points among the target obstacle points whose height differences are greater than the fourth height threshold and less than the third height threshold as the second obstacle point set, and determining the obstacles corresponding to the second obstacle point set as low obstacles.

[0173] In some embodiments of the present disclosure, in order to better assist the cleaning equipment in planning the mobile path, after determining the obstacle type of the obstacles in the target area, each obstacle can be marked with the obstacle type on the obstacle map. Furthermore, the obstacle map can be published, so that the cleaning equipment can accurately plan the mobile path according to the published obstacle map.

[0174] According to the ground detection method provided by some embodiments of the present disclosure, in the process of performing ground detection on the target area, first, the current frame point cloud data of the target area collected by the cleaning equipment is obtained, and the current frame point cloud data includes the point cloud corresponding to each point in the target area; secondly, the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data is determined, and the reference point cloud height value is defined as the point cloud height value of the ground point collected by the cleaning equipment in the reference ground; finally, based on the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data, and the actual point cloud height value of each point cloud in the current frame point cloud data, the target area is subjected to ground detection.

[0175] Based on the technical solution disclosed in the present invention, it is not assumed that all point clouds in the current frame point cloud data are on the same plane, that is, the corresponding ground values ​​are different. Instead, it is assumed that each point cloud in the current frame point cloud data has a corresponding reference ground. Thus, the target area is detected according to the reference point cloud height value of the ground point corresponding to each point cloud and the actual point cloud height value of each point cloud. This can eliminate the data errors in the current frame point cloud data collected by the cleaning equipment, thereby improving the accuracy of ground detection of the target area, and helping the cleaning equipment to plan an accurate moving path, avoiding situations such as the cleaning equipment falling off a cliff and colliding with obstacles.

[0176] Based on the same inventive concept, the present disclosure provides a ground detection device that can be used to perform the ground detection method in the above-mentioned embodiments of the present disclosure. For details not disclosed in the present disclosure, please refer to the above-mentioned embodiments of the ground detection method of the present disclosure.

[0177] FIG11 shows a block diagram of a ground detection device according to some embodiments of the present disclosure. Referring to FIG11 , the ground detection device 1100 provided by the present disclosure includes: an acquisition unit 1101 , a determination unit 1102 , and a detection unit 1103 .

[0178] The acquisition unit 1101 is used to acquire the current frame point cloud data of the target area collected by the cleaning equipment, and the current frame point cloud data includes the point cloud corresponding to each point in the target area; the determination unit 1102 is used to determine the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data, and the reference point cloud height value is defined as the point cloud height value of the ground point collected by the cleaning equipment in the reference ground; the detection unit 1103 is used to perform ground detection on the target area based on the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data, and the actual point cloud height value of each point cloud in the current frame point cloud data.

[0179] In some embodiments of the present disclosure, based on the aforementioned scheme, the current frame point cloud data includes multiple point cloud sets, wherein the point clouds in each point cloud set are distributed in the same divergent direction of the cleaning equipment, and the determination unit 1102 is also used to: determine the initial point cloud height value corresponding to each point cloud set; based on the initial point cloud height value, determine the reference point cloud height value corresponding to each point cloud in each point cloud set.

[0180] In some embodiments of the present disclosure, based on the aforementioned scheme, the determination unit 1102 is further used to: for each point cloud set, determine a preset number of point clouds in front of each point cloud set as the initial point cloud according to the divergence direction; and determine the initial point cloud height value corresponding to each point cloud set based on the actual point cloud height value of each initial point cloud.

[0181] In some embodiments of the present disclosure, based on the aforementioned scheme, the determination unit 1102 is also used to: for each point cloud set, determine the first point cloud in each point cloud set as the target point cloud according to the divergence direction; obtain the previous frame of point cloud data of the target area collected by the cleaning equipment, and determine the point cloud set corresponding to each point cloud set from the previous frame of point cloud data as the first point cloud set; calculate the absolute value of the difference between the actual point cloud height value of the target point cloud and the initial point cloud height value corresponding to the first point cloud set; if the absolute value of the difference is greater than a preset threshold, then use the initial point cloud height value corresponding to the first point cloud set as the initial point cloud height value corresponding to each point cloud set; if the absolute value of the difference is less than or equal to the preset threshold, then use the actual point cloud height value of the target point cloud as the initial point cloud height value corresponding to each point cloud set.

[0182] In some embodiments of the present disclosure, based on the aforementioned scheme, the determination unit 1102 is also used to: for each point cloud set, determine the first point cloud in each point cloud set as the target point cloud according to the divergence direction; determine a second point cloud set from the multiple point cloud sets, and determine the initial point cloud height value corresponding to the second point cloud set; determine the initial point cloud height value corresponding to each point cloud set based on the initial point cloud height value corresponding to the second point cloud set and the actual point cloud height value of the target point cloud.

[0183] In some embodiments of the present disclosure, based on the aforementioned scheme, the determination unit 1102 is also used to: for each point cloud set, determine the first point cloud in each point cloud set as the target point cloud according to the divergence direction; use the initial point cloud height value as the reference point cloud height value corresponding to the target point cloud; correct the reference point cloud height value corresponding to the target point cloud according to a preset correction rule, and use the corrected height value as the reference point cloud height value corresponding to the next point cloud adjacent to the target point cloud; use the next point cloud adjacent to the target point cloud as the new target point cloud, and return to execute the correction of the reference point cloud height value corresponding to the target point cloud according to the preset correction rule, until the reference point cloud height value corresponding to each point cloud in each point cloud data is obtained.

[0184] In some embodiments of the present disclosure, based on the aforementioned scheme, the detection unit 1103 is also used to: calculate the height difference between the actual point cloud height value and the reference point cloud height value for each point cloud in the current frame point cloud data, and obtain the height difference corresponding to each point cloud in the current frame point cloud data; and perform ground detection on the target area based on the height difference corresponding to each point cloud in the current frame point cloud data.

[0185] In some embodiments of the present disclosure, based on the aforementioned scheme, the detection unit 1103 is also used to: mark the points corresponding to the point clouds in the current frame point cloud data whose height differences satisfy the first preset conditions as ground points; and mark the points corresponding to the point clouds in the current frame point cloud data whose height differences satisfy the second preset conditions as obstacle points.

[0186] In some embodiments of the present disclosure, based on the aforementioned scheme, the detection unit 1103 is also used to: fit each point marked as a ground point to obtain the plane equation of the target plane corresponding to the target area; based on the plane equation of the target plane and the plane equation of the reference plane, determine the posture data of the cleaning device at the current moment.

[0187] In some embodiments of the present disclosure, based on the aforementioned scheme, the detection unit 1103 is further used to: project the obstacle points in the target area to obtain projection data; and determine the obstacle type of the obstacles in the target area based on the projection data and the height difference corresponding to each obstacle point.

[0188] In some embodiments of the present disclosure, based on the above solution, the detection unit 1103 is further configured to: filter noise points in each obstacle point according to the projection data to obtain a target obstacle point;

[0189] Obstacle types of obstacles in the target area are determined according to the projection data and height differences corresponding to the target obstacle points.

[0190] In some embodiments of the present disclosure, based on the aforementioned solution, the obstacle type includes at least one of a cliff obstacle, a wire obstacle, and a low obstacle.

[0191] Based on the same inventive concept, the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores at least one computer program instruction, and the at least one computer program instruction is loaded and executed by a processor to implement the operations performed by the aforementioned method.

[0192] Based on the same inventive concept, the present disclosure also provides a cleaning device. FIG12 shows a schematic diagram of the structure of a cleaning device according to some embodiments of the present disclosure. Referring to FIG12 , a schematic diagram of the structure of a cleaning device according to one embodiment of the present disclosure is shown. The cleaning device includes one or more memories 1204, one or more processors 1202, and at least one computer program (computer program instructions) stored in the memories 1204 and executable on the processors 1202. When the processors 1202 execute the computer program, the method described above is implemented.

[0193] In Figure 12, a bus architecture (represented by bus 1200) is shown. Bus 1200 may include any number of interconnected buses and bridges, and bus 1200 links various circuits together, including one or more processors represented by processor 1202 and memory represented by memory 1204. Bus 1200 may also link various other circuits together, such as peripherals, voltage regulators, and power management circuits, all of which are well known in the art and, therefore, will not be described further herein. Bus interface 1205 provides an interface between bus 1200 and receiver 1201 and transmitter 1203. Receiver 1201 and transmitter 1203 may be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 1202 is responsible for managing bus 1200 and general processing, while memory 1204 may be used to store data used by processor 1202 when performing operations.

[0194] According to the technical solution provided by one or more embodiments of the present disclosure, in the process of ground detection of the target area, the current frame point cloud data of the target area collected by the cleaning equipment is first obtained, and the current frame point cloud data includes the point cloud corresponding to each point in the target area; secondly, the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data is determined, and the reference point cloud height value is defined as the point cloud height value of the ground point collected by the cleaning equipment in the reference ground; finally, based on the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data, and the actual point cloud height value of each point cloud in the current frame point cloud data, ground detection of the target area is performed.

[0195] Based on the technical solution disclosed in the present invention, it is not assumed that all point clouds in the current frame point cloud data are on the same plane, that is, the corresponding ground values ​​are different. Instead, it is assumed that each point cloud in the current frame point cloud data has a corresponding reference ground. Thus, the target area is detected according to the reference point cloud height value of the ground point corresponding to each point cloud and the actual point cloud height value of each point cloud. This can eliminate the data errors in the current frame point cloud data collected by the cleaning equipment, thereby improving the accuracy of ground detection of the target area, and helping the cleaning equipment to plan an accurate moving path, avoiding situations such as the cleaning equipment falling off a cliff and colliding with obstacles.

[0196] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on or transmitted via a computer-readable medium as one or more instructions or code. Other examples and implementations are within the scope and spirit of the present disclosure and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwiring, or a combination of any of these. Furthermore, the functional units may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0197] In the several embodiments provided in the present disclosure, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0198] The units described as separate components may or may not be physically separate, and the components of the control device may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0199] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store computer program instructions, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0200] The foregoing description is merely an embodiment of the present disclosure and is not intended to limit the present disclosure. Various modifications and variations are readily apparent to those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present disclosure are intended to be within the scope of the claims of the present disclosure.

Claims

1. A ground detection method, comprising: Acquire current frame point cloud data of the target area collected by the cleaning device, wherein the current frame point cloud data includes point clouds corresponding to each point in the target area; Determine a reference point cloud height value of a ground point corresponding to each point cloud in the current frame point cloud data, wherein the reference point cloud height value is defined as a point cloud height value of a ground point collected by the cleaning device in the reference ground; Based on the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data and the actual point cloud height value of each point cloud in the current frame point cloud data, ground detection is performed on the target area.

2. The method according to claim 1, wherein The current frame point cloud data includes a plurality of point cloud sets, wherein each point cloud in each point cloud set is distributed in the same divergent direction of the cleaning device, and determining a reference point cloud height value of a ground point corresponding to each point cloud in the current frame point cloud data includes: Determine the initial point cloud height value corresponding to each point cloud set; Based on the initial point cloud height value, a reference point cloud height value corresponding to each point cloud in each point cloud set is determined.

3. The method according to claim 2, wherein: Determining the initial point cloud height value corresponding to each point cloud set includes: For each point cloud set, according to the divergence direction, determining a preset number of point clouds at the front of each point cloud set as initial point clouds; The initial point cloud height value corresponding to each point cloud set is determined according to the actual point cloud height value of each initial point cloud.

4. The method according to claim 2, wherein: Determining the initial point cloud height value corresponding to each point cloud set includes: For each point cloud set, according to the divergence direction, determining the first point cloud in each point cloud set as the target point cloud; Acquire a previous frame of point cloud data of the target area collected by the cleaning device, and determine a point cloud set corresponding to each point cloud set from the previous frame of point cloud data as a first point cloud set; Calculating the absolute value of the difference between the actual point cloud height value of the target point cloud and the initial point cloud height value corresponding to the first point cloud set; If the absolute value of the difference is greater than a preset threshold, the initial point cloud height value corresponding to the first point cloud set is used as the initial point cloud height value corresponding to each point cloud set; If the absolute value of the difference is less than or equal to a preset threshold, the actual point cloud height value of the target point cloud is used as the initial point cloud height value corresponding to each point cloud set.

5. The method according to claim 2, wherein: Determining the initial point cloud height value corresponding to each point cloud set includes: For each point cloud set, according to the divergence direction, determining the first point cloud in each point cloud set as the target point cloud; Determining a second point cloud set from the plurality of point cloud sets, and determining an initial point cloud height value corresponding to the second point cloud set; The initial point cloud height value corresponding to each point cloud set is determined according to the initial point cloud height value corresponding to the second point cloud set and the actual point cloud height value of the target point cloud.

6. The method according to claim 2, wherein: The step of determining a reference point cloud height value corresponding to each point cloud in each point cloud set based on the initial point cloud height value includes: For each point cloud set, according to the divergence direction, determining the first point cloud in each point cloud set as the target point cloud; Using the initial point cloud height value as the reference point cloud height value corresponding to the target point cloud; Correcting the reference point cloud height value corresponding to the target point cloud according to a preset correction rule, and using the corrected height value as the reference point cloud height value corresponding to the next point cloud adjacent to the target point cloud; The next point cloud adjacent to the target point cloud is used as a new target point cloud, and the process of correcting the reference point cloud height value corresponding to the target point cloud according to the preset correction rule is returned to execute until the reference point cloud height value corresponding to each point cloud in each point cloud data is obtained.

7. The method according to claim 1, wherein The performing ground detection on the target area based on the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data and the actual point cloud height value of each point cloud in the current frame point cloud data includes: For each point cloud in the current frame point cloud data, calculating the height difference between the actual point cloud height value and the reference point cloud height value to obtain the height difference corresponding to each point cloud in the current frame point cloud data; Based on the height difference corresponding to each point cloud in the current frame point cloud data, ground detection is performed on the target area.

8. The method according to claim 7, wherein: The performing ground detection on the target area based on the height difference corresponding to each point cloud in the current frame point cloud data includes: Marking the points corresponding to the point clouds whose height differences in the current frame point cloud data satisfy the first preset condition as ground points; The points corresponding to the point clouds whose height differences in the current frame point cloud data meet the second preset condition are marked as obstacle points.

9. The method according to claim 8, further comprising: Fitting each point marked as a ground point to obtain a plane equation of a target plane corresponding to the target area; Based on the plane equation of the target plane and the plane equation of the reference plane, the posture data of the cleaning device at the current moment is determined.

10. The method according to claim 8, further comprising: Projecting obstacle points within the target area to obtain projection data; Obstacle types of obstacles in the target area are determined according to the projection data and height differences corresponding to the obstacle points.

11. The method according to claim 10, wherein: The determining, based on the projection data and the height difference corresponding to each obstacle point, the obstacle type of the obstacle in the target area includes: filtering noise points in each obstacle point according to the projection data to obtain a target obstacle point; Obstacle types of obstacles in the target area are determined according to the projection data and height differences corresponding to the target obstacle points.

12. The method according to claim 10 or 11, wherein: The obstacle type includes at least one of a cliff obstacle, a wire obstacle, and a low obstacle.

13. A ground detection device comprising: An acquisition unit, configured to acquire current frame point cloud data of a target area collected by a cleaning device, wherein the current frame point cloud data includes a point cloud corresponding to each point in the target area; a determining unit, configured to determine a reference point cloud height value of a ground point corresponding to each point cloud in the current frame point cloud data, wherein the reference point cloud height value is defined as a point cloud height value of a ground point collected by the cleaning device in a reference ground; The detection unit is used to perform ground detection on the target area based on the reference point cloud height value of the ground point corresponding to each point cloud in the current frame point cloud data and the actual point cloud height value of each point cloud in the current frame point cloud data.

14. The ground detection device according to claim 13, wherein: The current frame point cloud data includes a plurality of point cloud sets, wherein each point cloud in each point cloud set is distributed in the same divergent direction of the cleaning device, and the determining unit is further configured to: Determine an initial point cloud height value corresponding to each point cloud set; and determine a reference point cloud height value corresponding to each point cloud in each point cloud set based on the initial point cloud height value.

15. The ground detection device according to claim 14, wherein: The determining unit is further configured to: For each point cloud set, a preset number of point clouds in front of each point cloud set are determined as initial point clouds according to the divergence direction; and the initial point cloud height value corresponding to each point cloud set is determined based on the actual point cloud height value of each initial point cloud.

16. The ground detection device according to claim 14, wherein: The determining unit is further configured to: For each point cloud set, determining the first point cloud in each point cloud set as a target point cloud according to the divergent direction; obtaining a previous frame of point cloud data of the target area collected by the cleaning device, and determining a point cloud set corresponding to each point cloud set from the previous frame of point cloud data as the first point cloud set; Calculating the absolute value of the difference between the actual point cloud height value of the target point cloud and the initial point cloud height value corresponding to the first point cloud set; If the absolute value of the difference is greater than a preset threshold, the initial point cloud height value corresponding to the first point cloud set is used as the initial point cloud height value corresponding to each point cloud set; If the absolute value of the difference is less than or equal to a preset threshold, the actual point cloud height value of the target point cloud is used as the initial point cloud height value corresponding to each point cloud set.

17. The ground detection device according to claim 14, wherein: The determining unit is further configured to: For each point cloud set, determining the first point cloud in each point cloud set as the target point cloud according to the divergence direction; determining a second point cloud set from the multiple point cloud sets, and determining an initial point cloud height value corresponding to the second point cloud set; The initial point cloud height value corresponding to each point cloud set is determined according to the initial point cloud height value corresponding to the second point cloud set and the actual point cloud height value of the target point cloud.

18. The ground detection device according to claim 14, wherein: The determining unit is further configured to: For each point cloud set, according to the divergence direction, the first point cloud in each point cloud set is determined as the target point cloud; the initial point cloud height value is used as the reference point cloud height value corresponding to the target point cloud; according to a preset correction rule, the reference point cloud height value corresponding to the target point cloud is corrected, and the corrected height value is used as the reference point cloud height value corresponding to the next point cloud adjacent to the target point cloud; The next point cloud adjacent to the target point cloud is used as a new target point cloud, and the process of correcting the reference point cloud height value corresponding to the target point cloud according to the preset correction rule is returned to execute until the reference point cloud height value corresponding to each point cloud in each point cloud data is obtained.

19. The ground detection device according to claim 13, wherein: The detection unit is further used for: For each point cloud in the current frame point cloud data, calculate the height difference between the actual point cloud height value and the reference point cloud height value to obtain the height difference corresponding to each point cloud in the current frame point cloud data; based on the height difference corresponding to each point cloud in the current frame point cloud data, perform ground detection on the target area.

20. The ground detection device according to claim 19, wherein: The detection unit is further used for: The points corresponding to the point clouds whose height differences in the current frame point cloud data meet the first preset conditions are marked as ground points; the points corresponding to the point clouds whose height differences in the current frame point cloud data meet the second preset conditions are marked as obstacle points.

21. The ground detection device according to claim 20, wherein: The detection unit is further used for: Fitting is performed on each point marked as a ground point to obtain a plane equation of a target plane corresponding to the target area; and based on the plane equation of the target plane and the plane equation of the reference plane, the posture data of the cleaning device at the current moment is determined.

22. The ground detection device according to claim 20, wherein: The detection unit is further used for: Projecting the obstacle points in the target area to obtain projection data; and determining the obstacle type of the obstacle in the target area according to the projection data and the height difference corresponding to each obstacle point.

23. The ground detection device according to claim 22, wherein: The detection unit is further configured to: filter noise points in each obstacle point according to the projection data to obtain a target obstacle point; Obstacle types of obstacles in the target area are determined according to the projection data and height differences corresponding to the target obstacle points.

24. The ground detection device according to claim 22 or 23, wherein: The obstacle type includes at least one of a cliff obstacle, a wire obstacle, and a low obstacle.

25. A computer-readable storage medium, wherein at least one program code is stored in the computer-readable storage medium, wherein the at least one program code is loaded and executed by a processor to implement the operations performed by the method according to any one of claims 1 to 12.

26. A cleaning device, comprising one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the at least one program code is loaded and executed by the one or more processors to implement the method according to any one of claims 1 to 12.

Images