Control method and equipment of wall surface recognition system and storage medium

Abstract

The invention discloses a control method and device of a wall surface recognition system and a storage medium, and relates to the technical field of sensor positioning, and the method comprises the steps: determining target point cloud data corresponding to a wall surface according to a wall surface boundary in point cloud data; determining a boundary point set of the target point cloud data on a horizontal projection plane; all subsets of the boundary point set are traversed, circumcircles corresponding to the subsets are determined, a circumcircle sequence is obtained, and the subsets comprise a preset number of boundary points; in the circumcircle sequence, determining a minimum circumcircle surrounding the boundary point set; and comparing the radius of the minimum circumcircle with a preset radius threshold, and generating obstacle detection information according to a comparison result. According to the method, the wall surface is judged by carrying out transverse straight line detection through the top laser radar and recognizing the vertical direction of the wall surface through the multi-frame line laser, then wall surface obstacle recognition is carried out based on the algorithm of the method, and the recognition capability of the sweeping robot on the wall surface obstacle is improved.

Description

Technical Field

[0001] The present application relates to the field of sensor positioning technology, and in particular to a control method, device, and storage medium for a wall recognition system. Background Art

[0002] The core functions of a sweeping robot are autonomous navigation and obstacle avoidance, and wall recognition is a key technology for achieving this. Furthermore, walls not only define the boundaries of the cleaning path but also present various obstacles. In related technologies, sweeping robots typically place wall recognition sensors near the axis of the drive wheels, resulting in a smaller point cloud acquisition area and, in turn, poor obstacle recognition accuracy.

[0003] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a control method, device and storage medium for a wall recognition system, aiming to solve the technical problem in the related art that the sweeping robot is limited by the physical installation position and detection field of view of the sensor, so that the recognition sensor cannot provide complete wall information, which in turn causes the sweeping robot to collide with obstacles.

[0005] To achieve the above objectives, the present application proposes a method for a multi-sensor time-series wall recognition system, the method comprising: According to the wall boundary line in the point cloud data, determine the target point cloud data corresponding to the wall; Determining a boundary point set of the target point cloud data on a horizontal projection plane; Traversing all subsets of the boundary point set, determining the circumscribed circle corresponding to each subset, and obtaining a circumscribed circle sequence, wherein the subset includes a preset number of boundary points; In the circumscribed circle sequence, determining a minimum circumscribed circle that encloses the boundary point set; The radius of the minimum circumscribed circle is compared with a preset radius threshold, and obstacle detection information is generated according to the comparison result.

[0006] In one embodiment, the collected point cloud data is subjected to straight line fitting using a random sampling consistency algorithm, multiple random straight line generation is performed, and the straight line with the highest proportion of inliers is selected as the initial baseline; Splitting the portion of the initial baseline where the angle change is greater than a preset angle change threshold into a plurality of sub-segments; Based on the initial baseline and the multiple sub-line segments, the initial baseline is partially corrected to generate the wall boundary line.

[0007] In one embodiment, the point cloud data is divided into first point cloud data and second point cloud data based on the wall boundary line; Combined with the lateral projection result of the top laser radar, the part of the first point cloud data and the second point cloud data that is above the ground is determined as the target point cloud data.

[0008] In one embodiment, based on the radius corresponding to each of the minimum circumscribed circles, the radius is compared with the radius threshold to determine each target circumscribed circle whose radius is smaller than the radius threshold; Determining the center coordinates of each target circumscribed circle based on the target circumscribed circle and the horizontal projection plane; Based on the center coordinates of the target circumscribed circle, the obstacle detection information including the center coordinates is generated.

[0009] In one embodiment, based on the circle center coordinates in the obstacle detection information, a distance calculation is performed on any two adjacent circle center coordinates to obtain a plurality of circle center distances; Comparing and screening a number of the circle center distances, and taking the circle center distance with the largest corresponding value as the target distance; Based on the target distance, the distance is compared with a preset distance threshold, and the wall recognition result is determined according to the comparison result.

[0010] In one embodiment, if the comparison result shows that the target distance is less than the distance threshold, a notification including a successful wall detection and the wall recognition result of the target point cloud data is issued to indicate that the wall detection complies with a preset protection rule; If the comparison result shows that the target distance is greater than the distance threshold, the wall recognition result including a wall detection failure notification is issued to indicate that the wall does not meet the preset protection rules.

[0011] In one embodiment, based on the laser irradiation of the line laser radar perpendicular to the ground and the horizontal laser irradiation of the top laser radar, a projection result corresponding to the line laser radar and a horizontal projection result corresponding to the top laser radar are generated; The projection result and the horizontal projection result are identified and judged. If both the projection result and the horizontal projection result appear as straight lines, then a wall exists at the sampling position in the projection result.

[0012] In one embodiment, a projection surface is formed based on the line laser straight line projected by the line laser radar and the horizontal projection result of the top laser radar; Based on the projection plane, controlling the robot to move in a direction parallel to the wall to obtain multiple time-series projection planes; Projection is performed on a horizontal plane according to the multi-time-sequential projection plane to generate the horizontal projection plane.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a wall recognition device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the control method of the wall recognition system as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the control method of the wall recognition system as described above are implemented.

[0015] The present application provides a control method for a wall recognition system, comprising determining target point cloud data corresponding to a wall based on a wall boundary line in point cloud data; determining a boundary point set of the target point cloud data on a horizontal projection plane; traversing all subsets of the boundary point set, determining the circumscribed circle corresponding to each subset, and obtaining a circumscribed circle sequence, wherein the subset contains a preset number of boundary points; determining a minimum circumscribed circle in the circumscribed circle sequence that surrounds the boundary point set; comparing the radius of the minimum circumscribed circle with a preset radius threshold, and generating obstacle detection information based on the comparison result. This method utilizes a laser radar to illuminate a wall, identifies the wall position based on the generated point cloud data, and then uses an algorithm to identify obstacles on the wall, thereby improving the sweeping robot's ability to identify wall obstacles.

[0016] To sum up, this application uses a top laser radar to perform horizontal straight line detection and a multi-frame line laser to identify the vertical direction of the wall to determine the wall surface, as well as the length and position of the wall, and then identifies wall obstacles based on the algorithm of this method, thereby improving the sweeping robot's ability to identify wall obstacles. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 This is a flow chart of a first embodiment of a control method for a wall recognition system of the present application; Figure 2 This is a top view of the point cloud when there are obstacles; Figure 3 Looking down at the point cloud when there are no obstacles; Figure 4 This is a flow chart of a second embodiment of the control method of the wall recognition system of the present application; Figure 5 Diagram of the arrangement of sensors for this application; Figure 6 A cross-sectional view of the sensor arrangement method for this application; Figure 7 This is a flow chart of a fourth embodiment of the control method of the wall recognition system of the present application; Figure 8 This is a flowchart of a fifth embodiment of a control method for a wall recognition system of the present application; Figure 9 This is the effect diagram of vertical wall sampling after the robot moves; Figure 10 This is a flow chart of the control method of the wall recognition system of this application; Figure 11 This is a structural diagram of the wall recognition device of this application.

[0020] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0022] In related technologies, sweeping robots generally place wall recognition sensors near the axis of the driving wheels, resulting in a smaller point cloud collection area and poor obstacle recognition accuracy.

[0023] The present application provides a solution: first, according to the wall boundary line in the point cloud data, the target point cloud data corresponding to the wall is determined, then, the boundary point set of the target point cloud data on the horizontal projection plane is determined, and then all subsets of the boundary point set are traversed to determine the circumscribed circle corresponding to each subset to obtain a circumscribed circle sequence, wherein the subset contains a preset number of boundary points, and then, in the circumscribed circle sequence, the minimum circumscribed circle surrounding the boundary point set is determined, and finally, the radius of the minimum circumscribed circle is compared with a preset radius threshold, and obstacle detection information is generated according to the comparison result.

[0024] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of implementing the above functions, such as a wall recognition device. The following uses the wall recognition device as an example to illustrate this embodiment and the following embodiments.

[0025] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0026] The present application embodiment provides a control method for a wall recognition system, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the control method of the wall recognition system of the present application.

[0027] In this embodiment, the control method of the wall recognition system includes steps S10 to S50: Step S10: determining target point cloud data corresponding to the wall according to the wall boundary line in the point cloud data.

[0028] In this embodiment, point cloud data refers to a collection of discrete three-dimensional coordinate points that characterize the spatial distribution characteristics of the scanned object's surface. A wall refers to a spatial region above the ground, with vertical coordinates exceeding the ground baseline, relative to the ground reference height. A boundary line refers to a valid line segment that has been geometrically verified and represents the wall baseline. The target point cloud data refers to a subset of the point cloud representing the wall surface, which must meet height continuity, flatness, and relative position constraints with the robot.

[0029] As an optional implementation, in a scenario where the robot vacuum is cruising parallel to a wall, a coordinate system is established based on the straight line segment corresponding to the wall dividing line, using the straight line segment as the dividing line. In this coordinate system, the point cloud data above the ground is defined as the target point cloud data corresponding to the wall, and the point cloud data parallel to the dividing line is defined as the ground point cloud data.

[0030] Step S20: determining a boundary point set of the target point cloud data on a horizontal projection plane.

[0031] In this embodiment, the horizontal projection plane refers to the two-dimensional coordinate space obtained by projecting the three-dimensional point cloud onto the two-dimensional plane along the vertical axis, ignoring the height information. The boundary point set refers to the set of discrete points on the projection plane that form the boundary of the point cloud outline, typically located at the outer edge of the point cloud or where the shape suddenly changes.

[0032] As an optional implementation method, in a scenario where the sweeping robot is cruising parallel to the wall, a two-dimensional scatter plot is generated based on the target point cloud data and projected onto a horizontal projection plane along the height direction of the wall. The discrete points of the point cloud contour boundary are filtered out based on the two-dimensional scatter plot, and the discrete points are aggregated to generate a boundary point set.

[0033] Step S30 , traversing all subsets of the boundary point set, determining the circumscribed circle corresponding to each subset, and obtaining a circumscribed circle sequence, wherein the subset includes a preset number of boundary points.

[0034] In this embodiment, a subset refers to a continuous or discontinuous segment of points sequentially extracted from a boundary point set. The preset number refers to the user-defined number of points in the subset, used to construct the circumscribed circle. A circumscribed circle is the smallest closed circle that completely encloses all points in the subset, with its center and radius determined by the extreme points. A circumscribed circle sequence is a collection of multiple circumscribed circles generated in the order of subset traversal, used to characterize the local geometric features of the boundary contour.

[0035] As an optional implementation, in a scenario where the sweeping robot is cruising parallel to the wall, a circumscribed circle is constructed based on a customized subset containing a preset number of boundary points. A circumscribed circle is determined by the boundary points in the subset, and the circumscribed circle construction process is repeated for each subset to obtain several circumscribed circles. These several circumscribed circles are grouped together to generate a circumscribed circle sequence.

[0036] Step S40: determining the minimum circumscribed circle that surrounds the boundary point set in the circumscribed circle sequence.

[0037] In this embodiment, the minimum circumscribed circle refers to a circle with the smallest radius that can completely enclose all points in the boundary point set, and is dynamically determined by the extreme point. The Welzl algorithm is a geometric algorithm that recursively solves the minimum enclosing circle of a point set.

[0038] As an optional implementation, in a scenario where the sweeping robot is cruising parallel to the wall, all circumscribed circles in the circumscribed circle sequence are traversed, and after arranging them in ascending order of radius, the top ten with the smallest radius are preferentially selected as candidate circles. The candidate circles are verified to verify whether all points in the boundary point set are located on or inside the candidate circle. Those that meet the requirements are regarded as valid candidate circles, and the one with the smallest radius is selected from the valid candidate circles as the minimum circumscribed circle.

[0039] As an optional implementation method for screening circumscribed circles, in a scenario where the sweeping robot is cruising parallel to the wall, if there is no circumscribed circle containing the boundary point set among the candidate circles, verification is performed in a sequence of circumscribed circles arranged in ascending order of radius, and all points in the boundary point set are verified from small to large radius to see whether they are on or inside the circle until a circumscribed circle that meets the requirements appears, and the circumscribed circle that meets the requirements is used as the minimum circumscribed circle.

[0040] As an optional implementation, in a scenario where the sweeping robot is cruising parallel to the wall, based on the target point cloud data, the projection data of the target point cloud data on the horizontal projection plane is obtained, and the Weltz minimum enclosing circle algorithm is applied to the projection data corresponding to the target point cloud data. The unique minimum circumscribed circle is calculated and determined by any three non-collinear points on the projection data.

[0041] Step S50 : comparing the radius of the minimum circumscribed circle with a preset radius threshold, and generating obstacle detection information according to the comparison result.

[0042] In this embodiment, the preset radius threshold refers to a critical radius value customized based on the application scenario. Comparison judgment refers to comparing the actual calculated minimum circumscribed circle radius with the threshold to determine whether it meets the preset conditions. The detection result refers to the classification result output based on the threshold comparison.

[0043] As an optional implementation, in a scenario where the sweeping robot is cruising parallel to the wall, a comparative judgment is performed based on the minimum circumscribed circles calculated through projection data and a preset radius threshold. The radius size corresponding to each minimum circumscribed circle is compared with the radius threshold, and obstacle detection information is generated according to the comparison result.

[0044] As an optional implementation method for generating obstacle detection information, in a scenario where the sweeping robot is cruising parallel to the wall, if the radius corresponding to each minimum circumscribed circle has a radius value greater than a radius threshold, an operation of clearing the wall detection result is generated according to the comparison result, and obstacle detection information indicating that there is an obvious obstacle is generated.

[0045] As an optional implementation method for generating obstacle detection information, in a scenario where the sweeping robot is cruising parallel to the wall, the radius corresponding to each minimum circumscribed circle is smaller than the radius threshold. Based on the comparison results, point cloud data of the corresponding wall and detection information of no obvious obstacles are generated. The corresponding point cloud data for the wall is generated, and obstacle detection information without obvious obstacles is obtained.

[0046] For example, referring to Figure 2 and Figure 3 , Figure 2 This is the top view of the point cloud when there are obstacles. Figure 3 This is a point cloud image from a bird's-eye view when there are no obstacles. This is a T-shaped projection formed by the LiDAR and line laser beams when the robot vacuum is cruising parallel to a wall. When both the LiDAR's lateral projection and the line laser's projection perpendicular to the ground are straight lines, the sampled location of the line laser beam is considered part of the wall. As the robot moves, multiple sampled line laser beams form a plane. The higher the line laser sampling frequency and the smaller the spacing between lines, the lower the probability of missing small obstacles.

[0047] Based on the point cloud data generated by the line LiDAR, a random sampling consensus algorithm is used to perform line fitting. Any two points in the point cloud are selected to generate a candidate line equation y = kx + b. The number of inliers whose distance from the line is less than a set threshold is then counted. If the number of inliers is 100 and after 50 attempts, the line with the equation y = kx + b is the largest, the line is selected as the initial baseline. The initial baseline is then segmented using the random sampling consensus algorithm. Local corrections are made to the fitted initial baseline to account for corners or unevenness in the actual wall surface. A sliding window is used to calculate the angular change of adjacent point sets (for example, the angle difference between the first and last points is calculated for each group of five points). Split points are inserted when the angle changes by more than 5 degrees, breaking the long line into multiple sub-segments. Physical constraints are also applied (for example, the length of a sub-segment must exceed 1.2 times the robot width) to filter out invalid segments. Local corrections are made to the initial baseline using these sub-segments to identify at least one line segment that passes through the robot's side close to the wall. The point cloud data is separated by straight line segments to identify and obtain target point cloud data above the horizontal plane. Initial projection data of the target point cloud data on the horizontal projection plane is obtained, and the projection data is secondary screened based on the distribution of the target point cloud data. Isolated points with discrete distribution after projection are eliminated, and a core set of points with continuous distribution is retained to obtain projection data. The projection data is then applied to the Weltz minimum enclosing circle algorithm, and a unique minimum circumscribed circle is calculated and determined by any three non-collinear points on the projection data. The process of selecting points and calculating the minimum circumscribed circle is repeated to obtain several minimum circumscribed circles. These minimum circumscribed circles are then compared with a preset radius threshold (e.g., 3mm) to obtain comparison results where the radii corresponding to the minimum circumscribed circles are all less than the radius threshold (3mm). Based on this comparison result, obstacle detection information is generated corresponding to the point cloud data of the wall and the absence of obvious obstacles.

[0048] The wall surface, length and position are determined by using the top laser radar for horizontal straight line detection and multi-frame line laser for identifying the vertical direction of the wall. The wall obstacle recognition algorithm is then used to identify the wall obstacle, which improves the sweeping robot's ability to recognize wall obstacles.

[0049] Based on any of the above embodiments, in the second embodiment of the present application, refer to Figure 4 , Figure 4 This is a flow chart of the second embodiment of the control method of the wall recognition system of the present application. Before step S10, steps A11 to A13 are also included: In step A11, the collected point cloud data is fitted with a straight line using a random sampling consistency algorithm, multiple random straight lines are generated, and the straight line with the highest proportion of inliers is selected as the initial baseline.

[0050] In this embodiment, the Random Sample Consensus Algorithm (RANSAC) algorithm is an iterative optimization algorithm that establishes candidate models by repeatedly randomly sampling a minimum data set and evaluates the model's reliability based on the number of inliers. Line fitting is a mathematical modeling process that solves the optimal line equation from a set of discrete points based on the least squares method or geometric optimization criteria. Inliers are data points that meet a preset error threshold and are considered support points for a valid fit. The initial baseline is the preliminary fit result determined by the candidate line with the highest proportion of inliers, which serves as the basis for subsequent optimization.

[0051] As an optional implementation, in a scenario where the sweeping robot is cruising parallel to the wall, the collected point cloud data is preprocessed, including calibration based on height features and filtering outliers, retaining the valid area point set. By initializing the random sampling algorithm parameters, the maximum number of iterations and the dynamically adjusted inlier distance threshold are set. In each iteration, two non-collinear points are randomly selected to generate a candidate line model. The geometric distance from all points to the line is calculated and the number of supporting points that meet the threshold conditions is counted. The current optimal model and its corresponding number of inliers are simultaneously recorded, and the candidate line with the highest proportion of inliers is selected as the initial baseline.

[0052] Furthermore, in scenarios where the robot vacuum is cruising parallel to a wall, a line is fitted based on the point cloud data generated by the line laser radar illuminating the wall, using the principle of a random sampling consensus algorithm. Two points are randomly selected to generate a candidate line equation, and the number of inliers whose distance from the line is less than a set threshold is counted. After several random attempts, the line with the highest proportion of inliers is selected as the initial baseline. Line segmentation is then performed based on the principle of a random sampling consensus algorithm. For bends or bumps in the wall, local corrections are made to the fitted initial baseline. A sliding window is used to calculate the angular change of adjacent point sets. When the angle suddenly changes and exceeds a preset angular change threshold, a split point is inserted, breaking the long line into several sub-segments. The initial baseline is then locally corrected using these sub-segments to obtain and identify at least one line segment that passes through the robot's side close to the wall, which is used as the wall boundary.

[0053] Step A12: splitting the portion of the initial baseline whose angle change is greater than a preset angle change threshold into multiple sub-segments.

[0054] In this embodiment, segment splitting refers to the process of detecting points of curvature mutation on a fitted line and then segmenting the continuous line into multiple subsegments that satisfy local linear constraints. Angle change refers to the directional offset of adjacent points relative to the baseline, and the degree of structural mutation is characterized by the vector angle calculation. The preset angle change threshold is the critical angle deviation that determines whether segmentation is necessary. The line with the highest proportion of inliers is the candidate model that has the largest proportion of supporting points and meets the error range in multiple random samplings.

[0055] As an optional implementation, when the robot vacuum is cruising parallel to a wall, local corrections are made to the fitted initial baseline to account for any bends or bumps in the actual wall. A sliding window is used to calculate the angular change between adjacent points. When the angle suddenly changes, exceeding a preset threshold, the system inserts dynamic segmentation points along the sudden change location, breaking the original long line segment into several sub-segments.

[0056] Step A13: Based on the initial baseline and the multiple sub-line segments, locally correct the initial baseline to generate the wall boundary line.

[0057] In this embodiment, local correction refers to segmented adjustment of the initial baseline based on the spatial distribution of sub-segments to improve the continuity of the baseline at the corners.

[0058] As an optional implementation, in a scenario where the sweeping robot is cruising parallel to the wall, the baseline coverage area is analyzed along the robot's movement direction based on the initial baseline and the set of disassembled sub-segments. Density clustering and directional consistency verification are performed on the point cloud subset corresponding to each sub-segment, discrete noise points are removed, the continuously distributed core point group is retained, and the geometric continuity between adjacent sub-segments is checked. If the angle difference at the connection is less than the preset merging threshold, each sub-segment is fused with the initial baseline into a single straight line segment. The robot identifies the straight line segment that passes through one side of itself and uses this straight line segment as the wall boundary.

[0059] For example, in a scenario where the sweeping robot is cruising parallel to the wall, the point cloud data collected by the sensor is denoised and highly filtered, and then projected onto a horizontal two-dimensional plane. A random sampling consistency algorithm is used to randomly select two points in the point cloud multiple times to generate candidate lines and the inlier support rate of each model is counted, and the line with the densest inlier distribution is selected as the initial baseline. The angle change of the normal vector of the point cloud is analyzed segment by segment in the form of a sliding window along the direction of the initial baseline. When the angle offset of the local area exceeds the preset threshold, a dynamic segmentation point is inserted to split the long baseline into multiple geometrically coherent sub-segments, and a secondary clustering verification is performed based on the inlier density and direction consistency of the sub-segments. Based on the initial baseline and the set of sub-segments, a priority analysis area is delineated near the real-time posture of the robot, and each sub-segment is sorted by lateral distance and evaluated for fit to the direction of motion, and the candidate segment with the closest distance and the smallest angle with the body trajectory is selected. After verifying its physical existence through multi-sensor feedback, endpoint extension and curvature smoothing are performed, and the final output is an optimized baseline that fits the actual shape of the wall and meets the obstacle avoidance distance constraints. It is synchronously updated to the environmental map as a reliable basis for navigation control.

[0060] By performing straight line fitting and line segment splitting based on the principle of random sampling consistency algorithm, the wall baseline can be accurately identified, thereby improving the accuracy of the sweeping robot in identifying wall obstacles.

[0061] Based on any of the above embodiments, in the third embodiment of the present application, step S10 includes steps B11 to B12: Step B11: Separate the point cloud data into first point cloud data and second point cloud data based on the wall boundary line.

[0062] In this embodiment, segmentation refers to a data segmentation operation that divides a mixed point cloud into different semantic categories, including ground or wall, based on geometric features. The first point cloud data and the second point cloud data refer to the point cloud data generated by the line laser radar being divided into two parts by the wall dividing line.

[0063] As an optional implementation, in a scenario where the sweeping robot is cruising parallel to the wall, based on the wall dividing line, the point cloud data is divided into two parts according to the straight line segment corresponding to the wall dividing line. One side of the straight line segment is the ground point cloud data, and the other side of the straight line segment is the target point cloud data.

[0064] Step B12: Combined with the lateral projection result of the top laser radar, determine the portion of the first point cloud data and the second point cloud data that is above the ground as the target point cloud data.

[0065] In this embodiment, the lateral projection result of the top laser radar refers to the result of horizontal irradiation by the laser radar installed on the top of the robot, which projects the laser vertically onto the wall to supplement the environmental structure information in the vertical direction.

[0066] As an optional implementation, in a scenario where the sweeping robot is cruising parallel to the wall, based on the horizontal laser that is irradiated vertically to the wall by the top lidar, it is judged through the projection result of the horizontal laser irradiation that the projection result corresponding to the horizontal laser intersects with part of the point cloud data on one side of the straight line segment. This part of the point cloud data is identified as the target point cloud data, and the part of the point cloud data on the other side of the straight line segment is identified as the ground point cloud data.

[0067] For example, in a scenario where the sweeping robot is cruising parallel to the wall, refer to Figure 5 and Figure 6 , Figure 5 This is the layout diagram of the sensors for this application. Figure 6This is a cross-sectional view of the sensor arrangement method for this application. Line laser is a type of 2D solid-state laser sensor with a limited field of view (FOV limitation), generally around 100°. When arranging the sensor, the line laser is emitted obliquely to the right front, and is tilted at a certain angle from top to bottom, so that the line laser can cover the entire wall. When performing edge-fitting operations, the line laser needs to hit the highest point of the wall, and it cannot be lower than the height of the top laser radar emitting surface, so that the line laser and the top laser radar can form an intersection, so that the movement of the robot can be used to determine whether the results of multiple frames can form a surface. The point cloud data is divided into two parts by identifying straight line segments, and then the target point cloud data and the ground point cloud data are identified by combining the projection results of the top laser with the intersection of the point cloud data.

[0068] By combining the projection results of the top lidar and the line lidar, the ground point cloud data and the target point cloud data can be effectively distinguished, thereby improving the accuracy of the sweeping robot in identifying the target point cloud data.

[0069] Based on any of the above embodiments, in the fourth embodiment of the present application, refer to Figure 7 , Figure 7 This is a flow chart of the fourth embodiment of the control method of the wall recognition system of the present application. Step S50 includes steps C11 to C13: Step C11 : comparing the radius corresponding to each minimum circumscribed circle with the radius threshold to determine each target circumscribed circle whose radius is smaller than the radius threshold.

[0070] In this embodiment, the target circumscribed circle refers to a circumscribed circle that is determined to be abnormal or in need of attention after threshold screening.

[0071] As an optional implementation, in scenarios where the robot vacuum is cruising parallel to a wall, a radius threshold is dynamically calculated based on the minimum circumscribed circle radius of each point set, combined with the robot's real-time motion state. By comparing the radius of each minimum circumscribed circle with a preset radius threshold, any target circumscribed circles with radii exceeding the limit are identified and marked.

[0072] Step C12: Determine the center coordinates of each target circumscribed circle based on each target circumscribed circle and in combination with the horizontal projection plane.

[0073] In this embodiment, the circle center coordinates refer to the position parameters of the geometric center of the circumscribed circle, and are used to describe the absolute or relative spatial positioning of the target area.

[0074] As an optional implementation, in a scenario where the robot vacuum is cruising parallel to a wall, coordinates are established on a horizontal projection plane based on the point cloud covered by each target circumcircle. The coordinates of the center of the target circumcircle on the horizontal projection plane are determined using the coordinate system constructed on the horizontal projection plane.

[0075] Step C13: generating the obstacle detection information including the center coordinates of the target circumscribed circle based on the center coordinates of the target circumscribed circle.

[0076] In this embodiment, the detection result including the circle center coordinates means that the circle center coordinates are written into the corresponding detection result to determine the coordinates of the obstacle on the wall.

[0077] As an optional implementation, in a scenario where the sweeping robot cruises parallel to a wall, the center coordinates of each target circumscribed circle are associated with the position of the obstacle based on the center coordinates corresponding to the circle, and obstacle detection information including the center coordinates is generated.

[0078] As an optional implementation of the preset obstacle condition, when the robot vacuum is cruising parallel to a wall, dynamic circle center coordinates are generated based on the identified dynamic point cloud data. Combined with the temporary obstacle determination criteria in the preset obstacle determination conditions, when the circle center coordinates are detected to be passing dynamically, they are filtered out as temporary obstacles.

[0079] For example, in a scenario where the sweeping robot is cruising parallel to the wall, the radius of each point cloud cluster is calculated based on its minimum circumscribed circle parameters and compared with the dynamic radius threshold. After screening out the valid target circumscribed circle with a radius lower than the threshold, the target circumscribed circle is mapped to the global coordinate system through multi-frame data alignment and coordinate transformation, combining the spatial distribution and normal vector characteristics of the target point cloud data, and eliminating abnormal circles caused by projection distortion or instantaneous occlusion. For the valid target circumscribed circle, the height gradient distribution of the target point cloud data and the lateral scanning results of the top laser radar are integrated, and the center coordinates are reversely checked and dynamically compensated to determine the updated center coordinates. By associating obstacles with the center coordinates, the obstacle detection information including the center coordinates is generated.

[0080] Due to the cooperation of the Weltz minimum enclosing circle algorithm and the preset radius threshold, wall obstacles can be effectively identified, which improves the accuracy of the sweeping robot in identifying wall obstacles.

[0081] Based on any of the above embodiments, in the fifth embodiment of the present application, refer to Figure 8 , Figure 8 This is a flowchart of the fifth embodiment of the control method of the wall recognition system of the present application. After step C13, it also includes steps D11 to D13: Step D11 , based on the circle center coordinates in the obstacle detection information, performing distance calculation on any two adjacent circle center coordinates to obtain a plurality of circle center distances.

[0082] In this embodiment, adjacent circle center coordinates refer to two consecutive circle center locations in spatial distribution or temporal order. Distance calculation refers to the process of numerically quantifying the linear distance between two points through geometric operations. Center distance refers to the actual spatial separation between adjacent circle centers and is used to analyze environmental structural continuity or obstacle density.

[0083] As an optional implementation, in a scenario where the robot vacuum is cruising parallel to a wall, based on the circle center coordinates in the detection results, any two adjacent circle center coordinates are selected for coordinate distance calculation to determine the distance between the adjacent circle center coordinates. This distance calculation step is repeated to generate multiple circle center distances.

[0084] Step D12: compare and select the center distances of the circle, and take the center distance with the largest corresponding value as the target distance.

[0085] In this embodiment, the multiple center distances refer to multiple spatial interval values obtained by calculating the coordinates of adjacent center points. The target distance refers to the maximum center distance determined after screening, which is a core parameter used for decision-making or path planning.

[0086] As an optional implementation, in a scenario where the sweeping robot is cruising parallel to a wall, the numerical values of several circle center distances are compared, and the circle center distance with the largest numerical value is selected as the target distance.

[0087] As an optional implementation method for excessive center distance, in a scenario where the sweeping robot is cruising parallel to the wall, if the target distance reaches a first preset threshold, local point cloud resampling and center coordinate interpolation correction are triggered to generate a corrected target distance.

[0088] Step D13: comparing the target distance with a preset distance threshold, and determining a wall recognition result according to the comparison result.

[0089] In this embodiment, the preset distance threshold refers to the distance threshold between adjacent circle centers, custom-defined based on scenario requirements. The comparison result refers to the decision conclusion generated based on the threshold comparison, used to determine whether the current wall obstacle detection is successful. The wall recognition result refers to the corresponding recognition result generated based on the comparison result, indicating whether an obstacle is present.

[0090] As an optional implementation, when the robot vacuum is cruising parallel to a wall, the center-center distance between any two adjacent circles is compared with a preset distance threshold, and a judgment is made according to the preset center-center distance rule. A corresponding judgment result is generated based on whether the center-center distance is greater than or less than the distance threshold.

[0091] For example, in a scenario where the sweeping robot is cruising parallel to the wall, two adjacent circle center coordinates are arbitrarily selected based on the center coordinates of each circle in the detection results. The center distance between two adjacent circle center coordinates is calculated using the coordinate distance formula to obtain several center distances. Numerical comparisons are performed on the several center distances, and the center distance with the largest value is selected. This center distance is used as the target distance, which is 1 cm. This distance is compared with a preset distance threshold of 1.5 cm. The target distance is less than the preset distance threshold. Therefore, a judgment result corresponding to the target distance being less than the distance threshold is generated.

[0092] Because the distance between adjacent circle center coordinates is judged by a preset distance threshold, the success or failure of the target point cloud data detection result can be identified. The accuracy of the sweeping robot in identifying wall obstacles is improved through conditional judgment of the distance threshold.

[0093] Based on any of the above embodiments, in the sixth embodiment of the present application, step D13 includes steps E11 and E12: Step E11: If the comparison result shows that the target distance is less than the distance threshold, a notification including a successful wall detection and the wall recognition result of the target point cloud data is issued to indicate that the wall detection complies with the preset protection rule.

[0094] In this embodiment, successful wall detection means that the target point cloud data meets the preset detection rules when the target distance is less than the threshold. The preset protection rules refer to the set protection measures. If the distance between the two detection frames is large, any obstacles that may appear in between will be skipped and the detection will be considered a failure.

[0095] As an optional implementation, when the robot vacuum is cruising parallel to a wall, based on a preset circle center distance judgment rule, if the judgment result shows that the target distance is less than the distance threshold, a notification of successful wall detection is issued, and the target point cloud data generated by the wall detection is released.

[0096] As an implementation method of sending notifications, in a scenario where the sweeping robot is cruising parallel to the wall, after the judgment result is generated, a corresponding notification is issued based on the judgment result, and the robot broadcasts the corresponding notification, or sends the notification to the mobile terminal.

[0097] Step E12: If the comparison result shows that the target distance is greater than the distance threshold, the wall recognition result including a wall detection failure notification is issued to indicate that the wall does not meet the preset protection rule.

[0098] In this embodiment, wall detection failure means that when the target distance exceeds a threshold, it is determined that the target point cloud data does not comply with a preset determination rule.

[0099] As an optional implementation, in a scenario where the sweeping robot is cruising parallel to a wall, according to the preset center distance judgment rule, if the judgment result shows that the target distance is greater than the distance threshold, a notification of wall detection failure is issued, and the target point cloud data generated by the wall detection is cleared.

[0100] For example, in a scenario where a sweeping robot is cruising parallel to a wall, based on the real-time comparison results of the target distance and the dynamic distance threshold, if the target distance is determined to be less than the threshold, the wall detection process is triggered successfully. A sliding window is used to trace back the spatiotemporal consistency of the center coordinates of the last three frames, verifying the continuity of the target point cloud data (e.g., azimuth fluctuation less than 5°, center spacing standard deviation less than 0.1W). Upon confirmation, a notification containing the normalized wall azimuth, fitted boundary points, and confidence labels is issued, which are then injected into the navigation system to generate a wall tracking path. The top lidar height gradient distribution and inertial navigation attitude angle data are simultaneously integrated to compensate for motion distortion of the wall coordinates. If the deviation between the infrared ranging feedback and the target distance exceeds 15%, local point cloud resampling is initiated, and a random sampling consensus algorithm is used to fit and correct the wall straight line within a preset range around the center of the circle. Conversely, if the target distance exceeds the threshold, the wall detection is judged to have failed.

[0101] By setting the distance threshold and combining it with the circle center distance judgment rule, the validity and accuracy of the target point cloud data can be detected, and the target point cloud data can be judged and corrected in a timely manner, thereby improving the accuracy of the sweeping robot in identifying wall obstacles.

[0102] Based on any of the above embodiments, in the seventh embodiment of the present application, before step S10, steps F11 to F12 are further included: Step F11, based on the laser irradiation of the line laser radar perpendicular to the ground and the horizontal laser irradiation of the top laser radar, generate the projection result corresponding to the line laser radar and the horizontal projection result corresponding to the top laser radar.

[0103] In this embodiment, a line laser radar refers to a sensor device that generates three-dimensional coordinate data of an object's surface by emitting a fan-shaped laser beam to scan the environment and receiving reflected signals. Laser irradiation perpendicular to the ground refers to a scanning method in which a laser beam is pointed at a 90° angle toward the ground, and is used to capture height and distance information of vertical structures such as walls and columns. A top laser radar refers to a horizontal scanning radar installed on the top of the robot. Horizontal laser irradiation refers to a detection mode in which a laser beam is scanned in a horizontal direction, and is used to measure the distance to obstacles or the width of a channel in the horizontal plane. The projection result refers to the projection result formed by the laser radar irradiating the wall after scanning. The horizontal projection result is a set of horizontal spatial point clouds output by the horizontal scanning of the top laser radar.

[0104] As an optional implementation, when the robot vacuum is cruising parallel to a wall, the line laser radar emits a laser perpendicular to the ground and illuminates the wall, generating a projection result corresponding to the line laser radar. The top laser radar emits a horizontal laser that illuminates the wall horizontally, generating a horizontal projection result corresponding to the top laser.

[0105] Step F12 : identifying and judging the projection result and the horizontal projection result. If both the projection result and the horizontal projection result appear as straight lines, then a wall exists at the sampling position in the projection result.

[0106] In this embodiment, recognition and judgment refers to a classification process of performing geometric feature analysis on point cloud data.

[0107] As an optional implementation, when the robot vacuum is cruising parallel to a wall, the projection results corresponding to the line LiDAR and the horizontal projection results corresponding to the top LiDAR are identified to determine whether the projection results and the horizontal projection results are straight lines. If the projection results and the horizontal projection results do not appear to be straight lines, dynamic distortion compensation is performed based on the robot's motion state. If the projection results and the horizontal projection results appear to be straight lines after compensation, a wall is present at the location used in the projection results.

[0108] For example, in a scenario where a sweeping robot cruises parallel to a wall, coordinate transformation and height gradient filtering are performed based on the vertical scanning data from the line lidar to extract the vertical point cloud projection results. After removing ground reflection noise, a random sampling consensus algorithm is used to fit candidate wall lines (with a residual threshold set to 0.03m). The horizontal cross-scan data from the top lidar is simultaneously processed, and a cross-projection result is generated through motion distortion compensation and dynamic clustering. The horizontal line is then fitted using the least squares method. A spatial logic check is performed on the line fitting results from the dual lidars: if the angle between the normal vectors of the vertical and horizontal lines is less than 5° and the extension direction is consistent with the robot's motion trajectory, a valid wall is determined to exist. Multi-level verification is performed on the fitting results, using a time window to backtrack the line parameters of the last three frames (with a tolerance of ±3° in azimuth fluctuation and a length change rate of <15%) to confirm the wall's continuity.

[0109] Due to the cooperation of the line laser radar and the top laser radar, projection results and horizontal projection results are formed, which effectively identify the existence of the wall and improve the accuracy of the sweeping robot in identifying wall obstacles.

[0110] Based on any of the above embodiments, in the eighth embodiment of the present application, before step S20, steps G11 to G13 are further included: Step G11: Based on the line laser straight line projected by the line laser radar and combined with the horizontal projection result of the top laser radar, a projection surface is formed.

[0111] In this embodiment, the projection surface refers to a three-dimensional space plane model constructed by fusing vertical and horizontal laser scanning data, and is used to describe the geometric continuity of the environment structure.

[0112] As an optional implementation, in a scenario where the sweeping robot is cruising parallel to the wall, the line laser line is extracted by performing height gradient filtering and random sampling consensus algorithm straight line fitting based on the line laser data of the line laser radar. The line laser line is mapped to the global coordinate system after removing dynamic obstacle noise points, and the horizontal scanning data of the top laser radar is processed synchronously. The horizontal projection result is generated based on motion distortion compensation and cluster analysis. The vertical fitting line and the horizontal channel boundary line are spatially aligned, and the normal vector angle is checked and the extension direction consistency is judged. If both meet the plane constraint conditions in three-dimensional space, they are determined to be a valid projection surface.

[0113] Step G12: Based on the projection plane, control the robot to move in a direction parallel to the wall to obtain a multi-time series projection plane.

[0114] In this embodiment, the direction parallel to the wall refers to the direction of the motion trajectory that is perpendicular to the wall normal and maintains a constant distance. The multi-time series projection plane refers to the plane generated by the projection plane based on the displacement and time during the robot's movement parallel to the wall.

[0115] As an optional implementation, when the robot vacuum is cruising parallel to a wall, the robot's heading angle is adjusted by controlling operating parameters based on the wall plane parameters fitted in the projection surface, keeping its motion parallel to the wall. During motion, the projection surfaces formed by the line LiDAR and top LiDAR are acquired in real time, and a horizontal projection plane is generated through continuous mapping of the projection surfaces.

[0116] Step G13: Projecting the multi-time-sequential projection planes onto a horizontal plane to generate the horizontal projection plane.

[0117] In this embodiment, the horizontal plane refers to a two-dimensional reference plane defined by the X and Y axes of the robot or global coordinate system, used for projection calculations. Projection is a dimensionality reduction operation that orthogonally maps a 3D point cloud onto a horizontal plane along its vertical axis, preserving the X and Y coordinate information. The horizontal projection plane is the resulting two-dimensional point set, representing the horizontal geometric distribution of the 3D spatial data.

[0118] As an optional implementation, in a scenario where the sweeping robot cruises parallel to a wall, the multi-time-series projection plane is projected in a top-down direction onto a horizontal plane to form a horizontal projection plane.

[0119] For example, referring to Figure 9 , Figure 9This image shows the effect of vertical wall sampling after the robot moves. In a scenario where the robot vacuum is cruising parallel to the wall, the linear laser lines projected onto the wall by the line LiDAR are mapped onto the wall as the robot moves parallel to the wall. An initial surface is generated by calibrating these linear laser lines and combining them with the horizontal projection results from the top LiDAR. Point cloud data is interpolated from this initial surface to generate a projection surface. Based on this projection surface, the robot vacuum moves parallel to the wall to generate a continuous projection surface. By synthesizing these continuous projection surfaces, a multi-sequence projection plane is generated. These multi-sequence projection planes are projected onto a horizontal plane to form a horizontal projection plane.

[0120] Due to the mutual cooperation between the line laser radar and the top laser radar, the projection forms a horizontal projection plane, which facilitates the calculation of the minimum circumscribed circle and the identification of wall obstacles, thereby improving the accuracy of the sweeping robot in identifying wall obstacles.

[0121] Based on any of the above embodiments, in the ninth embodiment of the present application, refer to Figure 10 , Figure 10 This is a flow chart of the control method of the wall recognition system of this application.

[0122] For example, the system first extracts the right front LiDAR point cloud from the robot vacuum. Polar coordinate filtering conditions (azimuth angle 60°-120°, distance 0.1-2.0m) are set to extract valid point cloud clusters on the right side. The filtered point cloud is then fitted with the RANSAC algorithm (500 iterations, with an inlier distance threshold of 0.02m). After fitting, the point cloud is segmented into independent line segments according to the line segmentation rule (sudden changes in the distance between adjacent points exceeding 0.1m or angular deviation exceeding 3°). A check is performed to determine whether a valid line segment with a length ≥ 0.8m and extending across the robot's right geometric boundary (with the robot's center as the origin and the right boundary X = +0.25m) exists. If no valid line segment is detected, the current frame's wall detection result cache is cleared. If a valid line segment is detected, data points with a Z-axis height greater than 0.05m are extracted from the LiDAR point cloud in that area (filtering out ground reflection interference). The XY projection points are then input into the Welzl algorithm (Welz's minimum enclosing circle algorithm) to calculate the minimum circumscribed circle. When the circle radius r is ≤ 0.15m, the circle center coordinates (cx, cy) are added to the wall detection result queue; otherwise, the queue is cleared. The Euclidean distance between adjacent circle center coordinates in the queue is calculated in time series. If the maximum distance between two consecutive points exceeds the threshold of 0.4m, a "wall detection failed" command is issued and the queue data is cleared. If the maximum distance between two consecutive points exceeds the threshold, a "wall detection successful" command is issued and the coordinates of all circle centers and the corresponding wall point cloud collection are output. At the end of the process, the current frame processing status (success / failure flag, circle center coordinate list) is written to a log file for offline verification of algorithm validity.

[0123] The present application provides a wall recognition device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the control method of the wall recognition system in the above-mentioned embodiment 1.

[0124] Reference below Figure 11 , which shows a schematic diagram of the structure of a wall recognition device suitable for implementing the embodiments of the present application. The wall recognition device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, sweeping robots, personal digital assistants (PDAs), tablet computers (PADs), portable multimedia players (PMPs), linear laser radars, and fixed terminals such as intelligent sweeping robots and desktop computers. Figure 11 The wall recognition device shown is only an example and should not limit the functions and scope of use of the embodiments of the present application.

[0125] like Figure 11As shown, the wall recognition device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the wall recognition device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007, such as a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003, such as a magnetic tape, hard disk, etc.; and communication devices 1009. Communication devices 1009 can allow the wall recognition device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a wall recognition device with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0126] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0127] The wall recognition device provided in this application utilizes the control method for the wall recognition system in the aforementioned embodiment, resolving the technical issue in related art where sweeping robots generally place their wall recognition sensors near the drive wheel axis, resulting in a smaller point cloud acquisition area and, in turn, poor obstacle recognition accuracy. Compared to the prior art, the beneficial effects of the wall recognition device provided in this application are the same as those of the control method for the wall recognition system in the aforementioned embodiment, and the other technical features of this wall recognition device are the same as those disclosed in the method in the previous embodiment, and are not further elaborated here.

[0128] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0129] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0130] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, and the computer-readable program instructions are used to execute the control method of the wall recognition system in the above-mentioned embodiment.

[0131] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0132] The computer-readable storage medium may be included in the wall recognition device, or may exist independently without being assembled into the wall recognition device.

[0133] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the wall recognition device, the wall recognition device: determines the target point cloud data corresponding to the wall based on the wall boundary line in the point cloud data; determines the boundary point set of the target point cloud data on the horizontal projection plane; traverses all subsets of the boundary point set, determines the circumscribed circle corresponding to each subset, and obtains a circumscribed circle sequence, wherein the subset contains a preset number of boundary points; in the circumscribed circle sequence, determines the minimum circumscribed circle surrounding the boundary point set; compares the radius of the minimum circumscribed circle with a preset radius threshold, and generates obstacle detection information based on the comparison result.

[0134] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0135] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0136] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0137] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the control method for the wall recognition system described above. This computer-readable storage medium can address the technical issue in related art where sweeping robots commonly place wall recognition sensors near the drive wheel axis, resulting in a smaller point cloud acquisition area and, in turn, poor obstacle recognition accuracy. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the control method for the wall recognition system provided in the above-mentioned embodiments, and are not further elaborated here.

[0138] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A control method for a wall recognition system, characterized in that: The method comprises: According to the wall boundary line in the point cloud data, determine the target point cloud data corresponding to the wall; Determining a boundary point set of the target point cloud data on a horizontal projection plane; Traversing all subsets of the boundary point set, determining the circumscribed circle corresponding to each subset, and obtaining a circumscribed circle sequence, wherein the subset includes a preset number of boundary points; In the circumscribed circle sequence, determining a minimum circumscribed circle that encloses the boundary point set; The radius of the minimum circumscribed circle is compared with a preset radius threshold, and obstacle detection information is generated according to the comparison result.

2. The control method of the wall recognition system according to claim 1, characterized in that: Before the step of determining target point cloud data corresponding to the wall according to the wall boundary line in the point cloud data, the method further includes: The collected point cloud data is fitted with a straight line using a random sampling consistency algorithm. Multiple random straight lines are generated, and the straight line with the highest proportion of inliers is selected as the initial baseline. Splitting the portion of the initial baseline where the angle change is greater than a preset angle change threshold into a plurality of sub-segments; Based on the initial baseline and the multiple sub-line segments, the initial baseline is partially corrected to generate the wall boundary line.

3. The control method of the wall recognition system according to claim 1, characterized in that: The step of determining target point cloud data corresponding to the wall according to the wall boundary line in the point cloud data includes: Based on the wall boundary line, the point cloud data is divided into first point cloud data and second point cloud data; Combined with the lateral projection result of the top laser radar, the part of the first point cloud data and the second point cloud data that is above the ground is determined as the target point cloud data.

4. The control method of the wall recognition system according to claim 1, characterized in that: The step of comparing the radius of the minimum circumscribed circle with a preset radius threshold and generating obstacle detection information according to the comparison result includes: Based on the radius corresponding to each of the minimum circumscribed circles, the radius is compared with the radius threshold to determine each target circumscribed circle whose radius is smaller than the radius threshold; Determining the center coordinates of each target circumscribed circle based on the target circumscribed circle and the horizontal projection plane; Based on the center coordinates of the target circumscribed circle, the obstacle detection information including the center coordinates is generated.

5. The control method of the wall recognition system according to claim 4, characterized in that: After the step of generating the obstacle detection information including the center coordinates of the target circumscribed circle based on the center coordinates of the target circumscribed circle, the method further includes: Based on the circle center coordinates in the obstacle detection information, performing distance calculation on any two adjacent circle center coordinates to obtain a plurality of circle center distances; Comparing and screening a number of the circle center distances, and taking the circle center distance with the largest corresponding value as the target distance; Based on the target distance, the distance is compared with a preset distance threshold, and the wall recognition result is determined according to the comparison result.

6. The control method of the wall recognition system according to claim 5, characterized in that: The step of determining the wall recognition result according to the comparison result includes: If the comparison result shows that the target distance is less than the distance threshold, issuing a wall recognition result including a wall detection success notification and the target point cloud data to indicate that the wall detection complies with the preset protection rule; If the comparison result shows that the target distance is greater than the distance threshold, the wall recognition result including a wall detection failure notification is issued to indicate that the wall does not meet the preset protection rules.

7. The control method of the wall recognition system according to claim 1, characterized in that: Before the step of determining target point cloud data corresponding to the wall according to the wall boundary line in the point cloud data, the method further includes: Based on the laser irradiation of the line laser radar perpendicular to the ground and the horizontal laser irradiation of the top laser radar, generating a projection result corresponding to the line laser radar and a horizontal projection result corresponding to the top laser radar; The projection result and the horizontal projection result are identified and judged. If both the projection result and the horizontal projection result appear as straight lines, then a wall exists at the sampling position in the projection result.

8. The control method of the wall recognition system according to claim 1, characterized in that: Before the step of determining the boundary point set of the target point cloud data on the horizontal projection plane, the method further includes: Based on the line laser straight line projected by the line laser radar and the horizontal projection result of the top laser radar, a projection surface is formed; Based on the projection plane, controlling the robot to move in a direction parallel to the wall to obtain multiple time-series projection planes; Projection is performed on a horizontal plane according to the multi-time-sequential projection plane to generate the horizontal projection plane.

9. A wall recognition device, characterized in that: The wall recognition device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the control method of the wall recognition system according to any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the control method of the wall recognition system according to any one of claims 1 to 8 are implemented.

Images