Wall-climbing robot facade mapping method, system, equipment and medium

Abstract

The invention is suitable for the technical field of map construction, and provides a wall-climbing robot facade mapping method, system and equipment and a medium. The wall-climbing robot facade mapping method comprises the following steps: acquiring point cloud data of a facade environment of a wall-climbing robot, and acquiring a gravity direction vector; preprocessing the point cloud data; in the point cloud data matching process, gravity direction consistency constraint is introduced, and the course angle of the wall-climbing robot is optimized for the facade environment; and constructing a global map based on the optimized point cloud data, and performing global drift correction by using gravity direction information. After the gravity direction constraint is introduced, the stability of the course angle in the point cloud matching process is ensured, the map precision is improved, the problem that the attitude drifts seriously when the wall-climbing robot operates for a long time in the facade environment is solved, the drifting error is reduced through gravity direction correction, and the consistency of long-term mapping is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of map construction, and particularly relates to a method, system, device and medium for a wall-climbing robot to construct an elevation map. Background Art

[0002] A wall-climbing robot is an intelligent device that can stably move and perform tasks on vertical or inclined surfaces. Its core technologies include an adsorption mechanism, motion control, and task execution modules. It overcomes gravity through adsorption force, combines navigation and sensing technologies, and is widely used in fields such as construction, industry, and rescue to replace manual labor in performing high-risk or complex tasks.

[0003] When a wall-climbing robot performs autonomous operations in an elevation environment (such as the outer wall of a building, the side wall of a bridge, the outer wall of an oil tank, etc.), precise three-dimensional mapping is required. However, due to the long-term operation of the robot, attitude drift will occur, especially the cumulative error of the yaw angle, resulting in overall rotation offset or misalignment of the map. Conventional SLAM algorithms mainly rely on the odometer of lidar to estimate the pose. However, in an elevation environment, simply relying on geometric matching is difficult to ensure the consistency and accuracy of long-term mapping. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a method for a wall-climbing robot to construct an elevation map, aiming to ensure the consistency and accuracy of the long-term elevation mapping of the wall-climbing robot.

[0005] The embodiments of the present invention are implemented as follows. A method for a wall-climbing robot to construct an elevation map includes: Obtain the point cloud data of the elevation environment of the wall-climbing robot and obtain the gravity direction vector; Preprocess the point cloud data; During the matching process of the point cloud data, introduce the gravity direction consistency constraint to optimize the yaw angle of the wall-climbing robot for the elevation environment; Construct a global map based on the optimized point cloud data and perform global drift correction using the gravity direction information.

[0006] Furthermore, the step of obtaining the point cloud data of the elevation environment of the wall-climbing robot and obtaining the gravity direction specifically includes: collecting the point cloud data of the elevation environment using a MID360 lidar, obtaining the gravity direction in real time using an IMU sensor, and reducing the drift error of the sensor using the robot adsorption module.

[0007] Furthermore, the preprocessing of the point cloud data specifically includes the following two points: Feature point classification: Divide the ground points, wall points, and edge points according to the scan line. In the elevation environment, focus on the wall points and reduce the dependence on the ground points; Gravity direction consistency filtering: Eliminate the noise points that do not conform to the gravity direction characteristics, and the normal vector of the wall points needs to be consistent with the gravity direction.

[0008] Furthermore, the optimization function for the point cloud data matching is as follows: ; : The objective function value of the overall optimization, representing the error of point cloud registration; : The coordinate of a feature point in the source point cloud; : In the target point cloud, the point that matches ; : The rotation matrix to be optimized, representing the rotation change of the point cloud; : The translation vector to be optimized, representing the translation change of the point cloud; : The normal vector of the feature point in the source point cloud; : The gravity direction vector; : The weight factor, used to balance the influence of the gravity constraint term in the overall optimization; : The heading angle calculated based on the gravity direction; : The heading angle estimated based on point cloud matching; : The heading angle optimization weight.

[0009] Furthermore, constructing a global map based on the optimized point cloud data and performing global drift correction using the gravity direction information specifically includes the following steps: Calculate the gravity direction vector; Analyze the deviation trend of the historical drift trajectory of the wall-climbing robot and identify the systematic error of the historical drift trajectory; Optimize the heading angle of the wall-climbing robot based on the gravity constraint; Dynamically correct the global map in combination with the optimization result.

[0010] Furthermore, optimizing the heading angle of the wall-climbing robot based on the gravity constraint specifically includes the following steps: Set the optimization goal to make the heading angle in the historical drift trajectory consistent with the gravity direction; Adjust the global trajectory by optimizing the rotation and translation parameters to align its heading angle with the gravity direction while maintaining the relative transformation of adjacent key frames consistent; Use graph optimization to solve the problem, so that all key frames can maintain the best registration state after correction, and avoid error accumulation caused by drift.

[0011] Another object of the embodiments of the present invention is a wall-climbing robot facade mapping system, which includes: An acquisition module, configured to acquire point cloud data of the facade environment of the wall-climbing robot and obtain the gravity direction; A preprocessing module, configured to preprocess the point cloud data; An optimization module, configured to introduce a gravity direction consistency constraint during the matching process of the point cloud data, and optimize the heading angle of the wall-climbing robot for the facade environment; A correction module, configured to construct a global map based on the optimized point cloud data and perform global drift correction using the gravity direction information.

[0012] Another object of the embodiments of the present invention is a computer device, including a memory and a processor. When a computer program stored in the memory is executed by the processor, the processor is caused to execute the steps of the wall-climbing robot facade mapping method.

[0013] Another object of the embodiments of the present invention is a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the processor is caused to execute the steps of the wall-climbing robot facade mapping method.

[0014] A wall-climbing robot facade mapping method provided by the embodiments of the present invention. Traditional ICP and NDT algorithms only rely on geometric matching in three-dimensional space and ignore heading angle drift. After introducing the gravity direction constraint in this method, the stability of the heading angle during the point cloud matching process is ensured, the map accuracy is improved, and the problem of serious attitude drift when the wall-climbing robot runs for a long time in the facade environment is solved. The drift error is reduced through gravity direction correction, and the consistency of long-term mapping is ensured. This method is applicable to fields such as industrial inspection, building maintenance, and hazardous environment monitoring, and can significantly improve the long-term mapping accuracy and robustness of the wall-climbing robot in the facade environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is an application environment diagram of the wall-climbing robot facade mapping method provided by the embodiments of the present invention; Figure 2 It is a flowchart of the wall-climbing robot facade mapping method provided by the embodiments of the present invention; Figure 3 It is an internal structural block diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0017] Figure 1 The figure is an application environment diagram of a method for a wall-climbing robot to build a vertical map, as Figure 1 shown. In this application environment, it includes a wall-climbing robot, a MID360 lidar, an IMU sensor, a robot adsorption module, and a computer device.

[0018] The wall-climbing robot, as a mobile platform, performs tasks such as climbing, detecting, or operating on vertical walls or complex curved surfaces, executes detection or reconnaissance tasks according to instructions, and transmits the results back through a wireless network.

[0019] The MID360 lidar supports indoor and outdoor scenarios, resists strong light interference, and can stably output point cloud data in dim or strong light environments for high-precision vertical point cloud acquisition.

[0020] The IMU sensor provides the gravity direction vector in real time to optimize point cloud matching and mapping.

[0021] The robot adsorption module can adopt non-contact permanent magnet adsorption (suitable for metal surfaces such as oil tanks, with stable adsorption force and no need for continuous power supply) or negative pressure adsorption (adapting to non-metal walls, forming an air pressure difference for adsorption through a single suction cup structure) to ensure stability in the vertical environment and reduce sensor drift errors.

[0022] The computer device can be a tablet computer, a laptop computer, or a desktop computer, or an independent physical server or terminal, or a server cluster composed of multiple physical servers, and can be a cloud server providing basic cloud computing services such as cloud servers, cloud databases, cloud storage, and CDN.

[0023] As Figure 2 shown, in one embodiment, a method for a wall-climbing robot to build a vertical map is proposed. In this embodiment, this method is mainly exemplified by being applied to the computer device described above Figure 1 A method for a wall-climbing robot to build a vertical map may specifically include the following steps: Step S202, obtain the point cloud data of the vertical environment of the wall-climbing robot and obtain the gravity direction vector.

[0024] In this embodiment, the facade environment includes, but is not limited to, building exterior walls, bridge side walls, and oil tank outer walls. The MID360 lidar is used for high-precision facade point cloud acquisition. The IMU sensor provides the gravity direction vector in real time to optimize point cloud matching and mapping. The robot adsorption module ensures stability in the facade environment and reduces sensor drift errors.

[0025] Step S204: Preprocess the point cloud data.

[0026] In this embodiment, the point cloud can directly record the original geometric information of the object surface without discretization processing, and can accurately restore the shape, size, and details in the three-dimensional space. Previously, it was necessary to preprocess the point cloud data, which specifically included the following two points: I. Feature point classification: Divide ground points, wall points, and edge points according to scan lines. Dividing ground points according to scan lines can eliminate ground reflection interference and avoid misjudgment of wall features by ground textures. For the building facade environment, separating wall points can focus on vertical structure features (such as doors, windows, and decorative lines), and combined with grid projection or plane fitting algorithms, it can enhance the recognition of the geometric continuity of the wall surface. Edge points usually correspond to object boundaries or contours. By clustering (such as Euclidean clustering) or local normal vector mutation detection, the outer contour of the building or the boundary of obstacles can be accurately extracted, providing key geometric information for three-dimensional reconstruction. Feature point classification focuses on wall points in the facade environment and reduces the dependence on ground points.

[0027] II. Gravity direction consistency filtering: Eliminate noise points that do not conform to the gravity direction characteristics; the normal vector of wall points needs to be consistent with the gravity direction to ensure the rationality of the point cloud direction. When processing the point cloud data of the facade environment, gravity direction consistency filtering is a key step in preprocessing. Its core purpose is to align the point cloud coordinate system with the true gravity direction and eliminate the coordinate system tilt problem caused by sensor pose deviation or scanning angle. Gravity direction consistency filtering significantly improves the geometric consistency and semantic interpretability of the point cloud data by eliminating coordinate system tilt and normal direction deviation.

[0028] Step S206: During the point cloud data matching process, introduce a gravity direction consistency constraint to optimize the heading angle of the wall-climbing robot for the facade environment.

[0029] In this embodiment, in the facade environment, the problem of robot heading angle drift will be significantly exacerbated due to the superposition of environmental characteristics and sensor errors, and the influence of gravity on the heading angle cannot be ignored. Therefore, simply relying on geometric matching is difficult to ensure the consistency of long-term mapping. To this end, during the point cloud matching process, a gravity direction consistency constraint is introduced, and the heading angle calculation is optimized. The optimization objective function is as follows: ; : The objective function value of the overall optimization, representing the error of point cloud registration; : The coordinates of a feature point in the source point cloud (a point in the current frame point cloud); : In the target point cloud, the point that matches (a point in the mapped or previous frame point cloud); : The rotation matrix (3x3) to be optimized, representing the rotational change of the point cloud; : The translation vector (3x1) to be optimized, representing the translational change of the point cloud; : The normal vector of the feature point in the source point cloud (usually used for wall points or ground points); : The gravity direction vector (a unit vector obtained in real-time through the IMU); : The weight factor, used to balance the influence of the gravity constraint term in the overall optimization; : The heading angle calculated based on the gravity direction; : The heading angle estimated based on point cloud matching; : The weight for heading angle optimization.

[0030] During the point cloud matching process, the consistency constraint of the gravity direction is introduced, and the calculation of the heading angle is optimized for the facade environment. The optimized objective function is divided into three terms: The point cloud geometric matching error term , the gravity direction consistency constraint term , and the facade heading angle constraint term . In a conventional point cloud registration algorithm (such as the ICP algorithm), the point cloud geometric matching error term represents the Euclidean distance between the source point cloud after rotation R and translation t and the target point cloud. By minimizing this distance, the precise alignment of the source point cloud and the target point cloud is achieved. In the present invention, the consistency constraint term of the gravity direction and the heading angle constraint term are added to further improve the matching accuracy. The following two items are specifically described: I. The gravity direction consistency constraint term : By taking the dot product of the point cloud normal vector and the gravity direction g, the constraint on the gravity direction during the point cloud registration process is realized. When the normal vector is consistent with the gravity direction, the dot product is close to 1, and the value of this term tends to 0; when the two are perpendicular or deviate, this value increases, and such deviation will be penalized during the optimization process.

[0031] II. The facade heading angle optimization term : Since the robot moves on a vertical surface, its heading angle is greatly affected by gravity and cannot be simply calculated along the horizontal plane. In a planar lidar SLAM system, the heading angle is generally determined by the point cloud features on the horizontal plane. However, in a vertical surface environment, the direction of gravity will affect the rotation of the robot around the vertical axis. Therefore, the heading angle θ needs to be optimized by combining the gravity direction g provided by the IMU to ensure that its estimated value θ does not drift. By adding a heading angle constraint term, the system can suppress the angular error caused by inertial drift, making the pose estimation of the robot in the vertical surface environment more stable and accurate.

[0032] Step S208: Construct a global map based on the optimized point cloud data and perform global drift correction using the gravity direction information.

[0033] In this embodiment, a global drift correction method based on gravity constraint is proposed. The gravity direction information provided by the IMU is used to constrain the heading angle, and combined with the graph optimization framework, the global consistency of the historical trajectory is optimized, thereby reducing the error accumulation in long-term mapping and improving the map accuracy and consistency in the vertical surface environment.

[0034] In an optimization scheme, step S208 specifically includes steps S302 to S308: Step S302: Calculate the gravity direction vector. Extract the gravity direction from the IMU data and filter it to ensure the direction stability; calculate the change of the gravity direction of the robot in the global coordinate system at each moment.

[0035] Step S304: Analyze the deviation trend of the historical drift trajectory of the wall-climbing robot, and identify the systematic error of the historical drift trajectory through cumulative calculation.

[0036] Step S306: Optimize the heading angle of the wall-climbing robot based on gravity constraint. Specifically: Set the optimization goal to make the heading angle in the historical drift trajectory consistent with the gravity direction; Adjust the global trajectory by optimizing the rotation and translation parameters to align its heading angle with the gravity direction while keeping the relative transformation of adjacent key frames consistent; Use graph optimization to solve, so that all key frames can maintain the best registration state after correction and avoid error accumulation caused by drift.

[0037] Step S308: Dynamically correct the global map in combination with the optimization results to make it more in line with the real physical environment; Dynamically adjust the mapping strategy according to the drift correction to improve the map accuracy.

[0038] In this optimization solution, in order to eliminate the global drift caused by cumulative errors during the long-term operation of the wall-climbing robot, this method performs global correction based on the gravity direction while considering the influence of the vertical surface on the heading angle. The gravity constraint mainly affects the rotational part of the attitude, but when driving on the vertical surface, its influence varies in different directions. At the beginning of the optimization, there may already be certain deviations in the original trajectory of the robot; through iterative optimization, the algorithm calculates a correction rotation for each key frame to align its attitude with the gravity direction, and at the same time optimizes the heading angle by combining the normal information of the vertical surface to ensure the stability of the robot on the vertical or inclined wall. In addition, the translation parameters are also adjusted accordingly to ensure that the topological relationship between adjacent key frames is still consistent with the lidar measurement constraints. In the wall environment, the influence of gravity is mainly reflected in the adjustment of the heading angle to meet the operation requirements of different vertical surface postures.

[0039] In actual implementation, this optimization is usually based on a graph optimization framework: taking each key frame pose as a variable to be optimized, establishing relative motion constraints (from laser odometry) and absolute gravity constraints, and then solving a set of corrected pose sets. Through iterative solution, the rotation and displacement of all key frames are updated simultaneously to make the entire trajectory consistent with the gravity direction and maintain the best registration state with each other. The finally obtained correction amount is applied to the original trajectory to complete the global drift correction of the historical trajectory.

[0040] In one embodiment, a wall-climbing robot vertical mapping system is proposed, and the wall-climbing robot vertical mapping system includes: An acquisition module, configured to acquire point cloud data of the vertical environment of the wall-climbing robot and obtain the gravity direction; A preprocessing module, configured to preprocess the point cloud data; An optimization module, configured to introduce a gravity direction consistency constraint during the matching process of the point cloud data and optimize the heading angle of the wall-climbing robot for the vertical environment; A correction module, configured to construct a global map based on the optimized point cloud data and perform global drift correction using the gravity direction information.

[0041] In this embodiment, the wall-climbing robot vertical mapping system can execute any steps and sub-steps of the above-mentioned wall-climbing robot vertical mapping method, which will not be elaborated here.

[0042] Figure 3 The internal structure diagram of a computer device in an embodiment is shown. The computer device can specifically be Figure 1 the computer device in. As Figure 3As shown, the computer device includes a processor, a memory, a network interface, and an input device connected via a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the method for the wall-climbing robot to build a vertical map. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can execute the method for the wall-climbing robot to build a vertical map. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0043] Those skilled in the art can understand that Figure 3 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0044] In one embodiment, a computer device is proposed. The computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: Obtain the point cloud data of the vertical environment of the wall-climbing robot and obtain the gravity direction vector; Preprocess the point cloud data; During the process of matching the point cloud data, introduce the gravity direction consistency constraint to optimize the heading angle of the wall-climbing robot for the vertical environment; Construct a global map based on the optimized point cloud data and perform global drift correction using the gravity direction information.

[0045] In one embodiment, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, the processor is caused to execute the following steps: Obtain the point cloud data of the vertical environment of the wall-climbing robot and obtain the gravity direction vector; Preprocess the point cloud data; During the process of matching the point cloud data, introduce the gravity direction consistency constraint to optimize the heading angle of the wall-climbing robot for the vertical environment; Construct a global map based on the optimized point cloud data and perform global drift correction using the gravity direction information.

[0046] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0047] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0048] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0049] The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A wall-climbing robot facade mapping method, characterized in that: The wall-climbing robot facade mapping method comprises: Obtain point cloud data of the wall-climbing robot's facade environment and obtain the gravity direction vector; Preprocessing the point cloud data; In the point cloud data matching process, a gravity direction consistency constraint is introduced to optimize the heading angle of the wall-climbing robot for the facade environment; A global map is constructed based on the optimized point cloud data, and global drift correction is performed using gravity direction information.

2. The wall-climbing robot elevation mapping method according to claim 1, characterized in that: The step of obtaining the point cloud data of the facade environment of the wall-climbing robot and obtaining the gravity direction specifically includes: using a MID360 laser radar to collect the point cloud data of the facade environment, using an IMU sensor to obtain the gravity direction in real time, and using a robot adsorption module to reduce the drift error of the sensor.

3. The wall-climbing robot elevation mapping method according to claim 1, characterized in that: The preprocessing of the point cloud data specifically includes the following two points: Feature point classification: Segment ground points, wall points and edge points based on the scan line, focus on wall points in the vertical environment, and reduce dependence on ground points; Gravity direction consistency filtering: remove noise points that do not conform to the gravity direction characteristics, and the normal vector of the wall point must be consistent with the gravity direction.

4. The wall-climbing robot elevation mapping method according to claim 1, characterized in that: The optimization function of the point cloud data matching is as follows: ； : The objective function value of the overall optimization, which represents the error of point cloud registration; : Coordinates of a feature point in the source point cloud; :The target point cloud and Matching points; : The rotation matrix to be optimized, representing the rotation change of the point cloud; : The translation vector to be optimized, indicating the translation change of the point cloud; : Normal vector of feature point in source point cloud; : gravity direction vector; : Weight factor, used to balance the influence of gravity constraint in the overall optimization; : Heading angle calculated based on the direction of gravity; : Heading angle estimated based on point cloud matching; : Heading angle optimization weight.

5. The wall-climbing robot elevation mapping method according to claim 1, characterized in that: The global map is constructed based on the optimized point cloud data, and global drift correction is performed using gravity direction information, specifically including the following steps: Calculate the gravity direction vector; Analyze the deviation trend of the historical drift trajectory of the wall-climbing robot and identify the system error of the historical drift trajectory; Optimizing the heading angle of the wall-climbing robot based on gravity constraints; The global map is dynamically corrected in combination with the optimization results.

6. The wall-climbing robot elevation mapping method according to claim 5, characterized in that: The optimization of the heading angle of the wall-climbing robot based on gravity constraint specifically comprises the following steps: An optimization goal is set to make the heading angle in the historical drift trajectory consistent with the gravity direction; By optimizing the rotation and translation parameters, the global trajectory is adjusted so that its heading angle is aligned with the direction of gravity, while keeping the relative transformation of adjacent key frames consistent; Graph optimization is used to solve the problem, so that all key frames can maintain the best registration state after correction and avoid error accumulation caused by drift.

7. A wall-climbing robot facade mapping system, characterized in that: The wall-climbing robot facade mapping system comprises: The acquisition module is used to obtain the point cloud data of the wall-climbing robot's facade environment and obtain the gravity direction; A preprocessing module, used for preprocessing the point cloud data; An optimization module, used to introduce a gravity direction consistency constraint during the point cloud data matching process, and optimize the heading angle of the wall-climbing robot for the facade environment; The correction module is used to construct a global map based on the optimized point cloud data and perform global drift correction using gravity direction information.

8. A computer device, characterized in that: It comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the wall-climbing robot facade mapping method as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the wall-climbing robot facade mapping method according to any one of claims 1 to 6.

Images