Wall detection method, robot and storage medium

Abstract

The present invention discloses a wall detection method, a robot and a storage medium, wherein the wall detection method comprises the following steps: judging whether there is a wall straight line at present, and determining a first straight line according to the judgment result; calculating the distance from the target point cloud data to the first straight line to obtain a corresponding first distance set, wherein the target point cloud data is obtained according to the current frame point cloud data obtained by a laser radar; judging whether the wall corresponding to the first straight line is a valid wall according to the first distance in the first distance set. The method improves the effectiveness of wall detection by adding a distance-based effective wall judgment process on the basis of utilizing a straight line fitting method, and solves the problem that when the laser or point cloud data is distorted due to itself or external factors, or when obstacles appear on the wall path, the accuracy of wall detection will be greatly affected.

Description

Technical Field

[0001] The present invention relates to the field of unmanned driving technology, and in particular to a wall detection method, a robot and a storage medium. Background Art

[0002] In order to reduce the labor intensity of drivers and improve driving safety, the application scenarios of unmanned driving technology cover the field of sanitation, which greatly reduces the burden of sanitation workers and improves the efficiency of sanitation and cleaning. At the same time, the complexity of cleaning scenarios has also promoted the development of unmanned driving technology to a certain extent. In related technologies, during the operation of unmanned driving robots, the wall detection method is to directly perform linear fitting on laser sensor data for detection.

[0003] However, the above wall detection method has the following shortcomings: when the laser or point cloud data is distorted due to itself or external factors, it will greatly affect the accuracy of wall detection; when obstacles appear on the wall path, it will affect the accuracy of the detection method. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems in the related art to a certain extent. To this end, the first object of the present invention is to provide a wall detection method to solve the problem that when laser or point cloud data is distorted due to itself or external factors, or when obstacles appear on the wall path, the accuracy of wall detection will be greatly affected.

[0005] A second object of the present invention is to provide a computer-readable storage medium.

[0006] The third object of the present invention is to provide a robot.

[0007] To achieve the above-mentioned purpose, an embodiment of the first aspect of the present invention proposes a wall detection method, which is used for a robot. The robot is provided with a laser radar, and the method includes: judging whether there is a wall straight line at present, and determining a first straight line according to the judgment result; calculating the distance from the target point cloud data to the first straight line, and obtaining a corresponding first distance set, wherein the target point cloud data is obtained according to the current frame point cloud data acquired by the laser radar; judging whether the wall corresponding to the first straight line is a valid wall according to the first distance in the first distance set.

[0008] According to the wall detection method of the embodiment of the present invention, an effective wall evaluation process based on distance is added on the basis of utilizing the straight line fitting method, thereby improving the effectiveness of wall detection and solving the problem that when laser or point cloud data is distorted due to its own or external factors, or when obstacles appear on the wall path, the accuracy of wall detection will be greatly affected.

[0009] To achieve the above-mentioned purpose, a second aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the above-mentioned wall detection method is implemented.

[0010] According to the computer-readable storage medium of the present invention, when the computer program stored thereon is executed by a processor, the above-mentioned wall detection method is implemented, and an effective wall evaluation process based on distance is added on the basis of utilizing the straight line fitting method, thereby improving the effectiveness of wall detection and solving the problem that when laser or point cloud data is distorted due to its own or external factors, or when obstacles appear on the wall path, the accuracy of wall detection will be greatly affected.

[0011] To achieve the above-mentioned purpose, the third aspect of the present invention proposes a robot, which includes a laser radar and a controller, wherein the controller is connected to the laser radar, and the controller includes a processor, a memory, and a computer program stored in the memory. When the computer program is executed by the processor, the above-mentioned wall detection method is implemented.

[0012] According to the robot of the embodiment of the present invention, the wall detection is performed by the laser radar. When the computer program stored thereon is executed by the processor, an effective wall evaluation process based on distance is added on the basis of the straight line fitting method, thereby improving the effectiveness of the wall detection and solving the problem that the accuracy of the wall detection will be greatly affected when the laser or point cloud data is distorted due to its own or external factors, or when obstacles appear on the wall path.

[0013] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a flow chart of a wall detection method according to an embodiment of the present invention;

[0015] Figure 2 is a flow chart of step S1 of an embodiment of the present invention;

[0016] Figure 3 is a flow chart of step S3 of one embodiment of the present invention;

[0017] Figure 4 is a flow chart of step S3 of another embodiment of the present invention;

[0018] Figure 5 is a flow chart of step S33 of an embodiment of the present invention;

[0019] Figure 6 is a schematic diagram of iterative calculation of an embodiment of the present invention;

[0020] Figure 7 is a flowchart of step S333 of an embodiment of the present invention;

[0021] Figure 8 is a schematic diagram of a robot ROI region according to a specific embodiment of the present invention;

[0022] Fig. 9 4 is a structural block diagram of a robot according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0024] Please refer to the following Figure 1-7 The wall detection method, robot and storage medium according to the embodiments of the present invention are described.

[0025] Figure 1 is a flow chart of a wall detection method according to an embodiment of the present invention. In an embodiment of the present invention, the wall detection method is used for a robot, and a laser radar is provided on the robot. The robot may be a sanitation robot, such as a cleaning robot; and the laser radar may be a single-line laser radar or a multi-line laser radar.

[0026] like Figure 1 As shown, the wall detection method of the embodiment of the present invention includes the following steps:

[0027] S1, judging whether there is a straight line on the wall at present, and determining a first straight line according to the judging result.

[0028] Specifically, if there is a previously stored wall straight line, the wall straight line can be directly used as the first straight line; if there is no previously stored wall straight line, the current frame point cloud data is obtained, and the current frame point cloud data is linearly fitted to obtain the first straight line. The previously stored wall straight line is also obtained by linear fitting.

[0029] Optionally, the straight line fitting method may include a polynomial straight line fitting method, a least squares straight line fitting method, a gradient descent straight line fitting method, and the like.

[0030] S2, calculating the distance from the target point cloud data to the first straight line to obtain a corresponding first distance set, wherein the target point cloud data is obtained based on the current frame point cloud data acquired by the laser radar.

[0031] Specifically, the laser radar or the robot can be used as the origin, and the current frame point cloud data in a preset area around the origin is taken as the target point cloud data.

[0032] S3: Determine whether the wall surface corresponding to the first straight line is a valid wall surface according to the first distance in the first distance set.

[0033] Specifically, if the distance between the point cloud data and the first straight line is closer and the number of points is greater, it means that the wall surface corresponding to the first straight line is more effective. Based on this, in some embodiments, the first distance can be directly compared with the preset value, and the comparison result can be statistically calculated, and then the wall surface corresponding to the first straight line can be judged whether it is a valid wall surface according to the statistical result of the comparison result; in other embodiments, the point cloud data can be split into several rectangular areas according to the preset size, and the average value of the first distance of each rectangular area is calculated, and the average value of the first distance is statistically compared with the preset value, and the comparison result can be statistically calculated, and then the wall surface corresponding to the first straight line can be judged whether it is a valid wall surface according to the statistical result of the comparison result. After determining the valid wall surface, the robot can be controlled to perform wall-sticking operations, such as wall-sticking cleaning.

[0034] The wall detection method adds a distance-based effective wall evaluation process on the basis of the straight line fitting method, thereby improving the effectiveness of wall detection. It solves the problem that when laser or point cloud data is distorted due to its own or external factors, or when obstacles appear on the wall path, the accuracy of wall detection will be greatly affected.

[0035] Figure 2 is a flow chart of step S1 of an embodiment of the present invention:

[0036] like Figure 2 As shown, step S1 may include:

[0037] S101, determining whether there is a straight line on the wall.

[0038] S102: If it exists, take the wall straight line as the first straight line.

[0039] S103: If it does not exist, perform straight line fitting on the target point cloud data to obtain a first straight line.

[0040] In this embodiment, the currently existing wall straight line can be a straight line fitted based on the previous frame of point cloud data, and the previously acquired wall straight line can be used for the subsequent judgment steps. Thus, wall detection is performed using the timing characteristics of the wall, which can improve the effectiveness and reliability of the detection. At the same time, it can also enable the robot to continue to respond to special situations encountered during actual operations (such as falls, sensor damage, etc. that cause data mutations and make it impossible to obtain valid point cloud data).

[0041] Figure 3is a flow chart of step S3 of one embodiment of the present invention.

[0042] like Figure 3 As shown, step S3 determines whether the wall surface corresponding to the first straight line is a valid wall surface according to the first distance in the first distance set, which may include:

[0043] S31, counting the number of first distances in the first distance set that are smaller than a first error judgment threshold to obtain a first number.

[0044] S32, determining whether the first quantity is greater than a first preset value.

[0045] The first preset value can be set according to the area corresponding to the target point cloud data. For example, the larger the area, the larger the first preset value. The area can be set according to the actual scene (such as indoor scene, outdoor scene, open scene, narrow scene, etc.) and equipment parameters (such as robot shape, size, etc.).

[0046] S33: If yes, determine that the wall surface corresponding to the first straight line is a valid wall surface.

[0047] S34: If not, delete the currently existing wall straight line and return to the step of determining the first straight line.

[0048] In this embodiment, if the wall surface corresponding to the first straight line is a valid wall surface, the first distance values ​​in the first distance set are relatively concentrated, and the deviation value from the first error judgment threshold value will be small; if there are multiple or larger obstacles near the wall surface corresponding to the first straight line, the first distance values ​​in the first distance set will be divergent, and there will be multiple first distances with large deviation values ​​from the first error judgment threshold value. Based on this, by judging the number of first distance sets that are less than the first error judgment threshold value, the validity of the fitted wall straight line can be judged. Therefore, the effective wall judgment process based on distance is added on the basis of the straight line fitting method, which can improve the accuracy of wall detection.

[0049] Figure 4 is a flow chart of step S3 of another embodiment of the present invention.

[0050] S301, splitting the target point cloud data into a plurality of rectangular areas according to a preset size.

[0051] Among them, the preset size of the rectangular area can be set according to the actual scene (such as indoor scene, outdoor scene, open scene, narrow scene, etc.) and equipment parameters (such as robot shape, size, etc.).

[0052] S302: Calculate the average value of the first distance corresponding to each rectangular area.

[0053] S303: Count the number of rectangular areas whose average value of the first distance is less than a first average error judgment threshold to obtain a first number of rectangles.

[0054] S304: Determine whether the first rectangle quantity is greater than a rectangle quantity threshold.

[0055] S305: If yes, determine that the wall surface corresponding to the first straight line is a valid wall surface.

[0056] S306: If not, delete the currently existing wall straight line and return to the step of determining the first straight line.

[0057] like Figure 4 As shown, in this embodiment, by splitting the target point cloud data into several rectangular areas according to a preset size, the average value of the first distance corresponding to each rectangular area is obtained. If the wall corresponding to the first straight line is a valid wall, the average value of the first distance corresponding to most rectangular areas is small. If there are multiple or larger obstacles near the wall corresponding to the first straight line, the average value of the first distance corresponding to some rectangular areas is larger. By judging the number of rectangles whose average value of the first distance is less than the first average error judgment threshold, the validity of the fitted wall straight line can be judged.

[0058] Figure 5 is a flow chart of step S33 of one embodiment of the present invention.

[0059] like Figure 5 As shown, after the above step S33 determines that the wall surface corresponding to the first straight line is a valid wall surface, the following steps may be further included:

[0060] S331, determine the relative position relationship between each point in the target point cloud data and the robot.

[0061] S332, iteratively calculating the target point cloud data according to the relative position relationship and the first distance set, so as to eliminate the point cloud data corresponding to the obstacle in the target point cloud data.

[0062] Specifically, the iterative calculation starts from the point in the target point cloud data that is farthest in front of the robot. For each iteration point, if the first distance corresponding to the iteration point is less than the second error judgment threshold, the iteration point is stored in the preset array, otherwise all points in the preset array are cleared until the iteration reaches the farthest point behind the robot. The second error judgment threshold may be less than or equal to the first error judgment threshold. All points in the target point cloud data may be used as iteration points, or one iteration point may be obtained at intervals of one or more points.

[0063] Take all points in the target point cloud data as iteration points as an example, Figure 6 As shown, the first straight line is LP 1, iteratively calculates the target point cloud data ( Figure 6 The point P in front of the robot is the farthest point in the point cloud data in the ROI area. 1 Start iteration. For each iteration point, if the first distance corresponding to the iteration point is less than the second error judgment threshold, the iteration point is stored in the preset array A. Otherwise, all points in the preset array A are cleared until the iteration reaches the farthest point P behind the robot. 5 .like Figure 6 Midpoint P 1 To point P 2 All are stored in the preset array A. When the iteration reaches point P 3 When an obstacle is encountered, the corresponding first distance is greater than or equal to the second error judgment threshold. At this time, all points in A need to be cleared. Until the iteration reaches point P 4 , store the point in A again, and continue iterating until it reaches point P 5 , at this time, the points stored in A include P 4 , P 5 and all points in between.

[0064] S333, verifying the effective wall surface according to the target point cloud data after iterative calculation, and if the verification fails, deleting the currently existing wall straight line, and returning to the step of determining the first straight line.

[0065] Specifically, the above verification step can obtain the second number by counting the number of points in the preset array. Determine whether the second number is greater than the second preset value. If so, it is determined that the verification is passed, and if not, it is determined that the verification is not passed. Among them, the second preset value can be less than or equal to the first preset value. Therefore, by judging whether the target point cloud data after elimination reaches the threshold, not only can the robot's detection accuracy of the effective wall surface be further improved, but also the robot can judge the length of the remaining effective wall surface. Among them, according to the length of the remaining effective wall surface, it can be judged whether to continue to stick to the wall. If so, continue the wall sticking task, otherwise exit the wall sticking task and continue wall detection. It should be noted that the value of the second preset value can be obtained according to the selection method of the iteration point.

[0066] Figure 7 is a flowchart of step S333 of an embodiment of the present invention.

[0067] like Figure 7 As shown, after the above step S333 determines that the verification is passed, it may also include:

[0068] S341, performing straight line fitting on the midpoints of the preset array to obtain a second straight line.

[0069] S342, updating the currently existing wall straight line to a second straight line, and taking the wall corresponding to the second straight line as the final valid wall.

[0070] Therefore, by performing straight line fitting again on the valid wall points screened out in step S332, the wall surface corresponding to the second straight line is taken as the final valid wall surface, so that the wall surface finally detected is smoother and more accurate.

[0071] Figure 8 It is a schematic diagram of a robot ROI area according to a specific embodiment of the present invention.

[0072] It should be noted that, in any of the above embodiments of the wall detection method, the target point cloud data is composed of the projection points of the current frame point cloud data in the ROI (Region of Interest) area on the two-dimensional plane, where the ROI area is a preset area around the robot. The ROI area can be intercepted according to the robot geometry and the requirements of the application scenario. In a specific embodiment of the present invention, Figure 8 As shown, the robot ROI area can take the laser radar as the origin to intercept the area from the first preset distance behind the robot, such as 0.5m, to the second preset distance in front, such as 2.0m, and the third preset thresholds in the left and right directions, such as 4.0m, wherein the first preset distance is smaller than the second preset distance, and the first preset distance is smaller than the third preset distance.

[0073] In summary, the wall detection method of the embodiment of the present invention obtains a first straight line by fitting the point cloud data using polynomial lines, obtains a corresponding first distance set by calculating the distance from the target point cloud data to the first straight line, and judges whether the wall corresponding to the first straight line is a valid wall according to the first distance set. On the basis of the method using polynomial line fitting, a distance-based effective wall judgment process is added, and iterative processing is added for obstacle detection, as well as wall detection using time series features, thereby improving the effectiveness of wall detection and solving the problem that when laser or point cloud data is distorted due to itself or external factors, or when obstacles appear on the wall path, the accuracy of wall detection is greatly affected.

[0074] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the wall detection method of any of the above embodiments is implemented.

[0075] The computer-readable storage medium of an embodiment of the present invention implements the above-mentioned wall detection method when the computer program thereon is executed by a processor. On the basis of the method using polynomial straight line fitting, an effective wall evaluation process based on distance is added, thereby improving the effectiveness of wall detection and solving the problem that the accuracy of wall detection is greatly affected when laser or point cloud data is distorted due to its own or external factors, or when obstacles appear on the wall path.

[0076] The embodiment of the present invention also provides a robot.

[0077] Fig. 9 4 is a structural block diagram of a robot according to an embodiment of the present invention.

[0078] like Fig. 9 As shown, the robot 10 includes a laser radar 1 and a controller 2. The controller 2 is connected to the laser radar 1. The controller 2 includes a processor, a memory, and a computer program stored in the memory. When the computer program is executed by the processor, the wall detection method of any of the above-mentioned embodiments is implemented.

[0079] In addition, other structures and functions of the robot in the embodiment of the present invention are known to those skilled in the art and will not be described in detail here to reduce redundancy.

[0080] The robot 10 of the embodiment of the present invention performs wall detection through the laser radar 1. When the computer program thereon is executed by the processor, an effective wall evaluation process based on distance is added on the basis of the method using polynomial straight line fitting, thereby improving the effectiveness of wall detection and solving the problem that the accuracy of wall detection is greatly affected when the laser or point cloud data is distorted due to its own or external factors, or when obstacles appear on the wall path.

[0081] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0082] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0083] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0084] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0085] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0086] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0087] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0088] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A wall detection method, characterized in that: The method is used for a robot, wherein a laser radar is provided on the robot, and the method comprises: Determine whether there is a wall straight line at present, and determine the first straight line according to the determination result; Calculating the distance from the target point cloud data to the first straight line to obtain a corresponding first distance set, wherein the target point cloud data is obtained according to the current frame point cloud data acquired by the laser radar; Determining whether the wall surface corresponding to the first straight line is a valid wall surface according to the first distance in the first distance set; The determining, according to the first distance in the first distance set, whether the wall surface corresponding to the first straight line is a valid wall surface includes: Counting the number of first distances in the first distance set that are smaller than a first error judgment threshold to obtain a first number; Determining whether the first number is greater than a first preset value; If yes, then determine that the wall surface corresponding to the first straight line is a valid wall surface; If not, the currently existing wall straight line is deleted, and the process returns to the step of determining the first straight line.

2. The wall detection method according to claim 1, characterized in that: The step of determining the first straight line according to the judgment result includes: If there is a wall straight line currently, the wall straight line is used as the first straight line; If there is no wall straight line currently, a straight line fitting is performed on the target point cloud data to obtain the first straight line.

3. The wall detection method according to claim 1, characterized in that: After determining that the wall surface corresponding to the first straight line is a valid wall surface, the method further includes: Determine the relative position relationship between each point in the target point cloud data and the robot; Iteratively calculating the target point cloud data according to the relative position relationship and the first distance set to remove point cloud data corresponding to obstacles in the target point cloud data; The valid wall surface is verified according to the target point cloud data after iterative calculation, and when the verification fails, the currently existing wall surface straight line is deleted, and the process returns to the step of determining the first straight line.

4. The wall detection method according to claim 3, characterized in that: The iterative calculation of the target point cloud data according to the relative position relationship and the first distance set includes: Iteration starts from the point in the target point cloud data that is farthest in front of the robot. For each iteration point, if the first distance corresponding to the iteration point is less than the second error judgment threshold, the iteration point is stored in a preset array, otherwise all points in the preset array are cleared until iteration reaches the farthest point behind the robot.

5. The wall detection method according to claim 4, characterized in that: The points in the preset array are the target point cloud data after the iterative calculation, and the valid wall surface is verified according to the target point cloud data after the iterative calculation, including: Counting the number of points in the preset array to obtain a second number; Determining whether the second number is greater than a second preset value; If yes, the verification is judged to be passed; If not, the verification is determined to have failed.

6. The wall detection method according to claim 4, characterized in that: After the verification is passed, the method further includes: Performing straight line fitting on the midpoints of the preset array to obtain a second straight line; The currently existing wall straight line is updated to the second straight line, and the wall surface corresponding to the second straight line is used as the final valid wall surface.

7. The wall detection method according to any one of claims 1 to 6, characterized in that: The target point cloud data is composed of projection points of the current frame point cloud data in a ROI area on a two-dimensional plane, wherein the ROI area is a preset area around the robot.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the wall detection method according to any one of claims 1 to 7 is implemented.

9. A robot, characterized in that: The robot includes a laser radar and a controller, the controller is connected to the laser radar, the controller includes a processor, a memory and a computer program stored in the memory, and when the computer program is executed by the processor, the wall detection method as described in any one of claims 1 to 7 is implemented.

Images