Relocation result verification method

Abstract

The invention relates to a relocation result verification method, and the method comprises the steps: obtaining an environment map and relocation information of a self-moving device, and the relocation information comprises laser point cloud data obtained by the self-moving device through transmitting a laser beam to carry out the laser scanning of a surrounding environment at a relocation moment; matching the laser point cloud data with the environment map to obtain an abnormal light beam penetrating through an obstacle in the environment map; acquiring an abnormal grid on the different side of an obstacle opposite to the self-moving equipment based on the abnormal light beam; determining an abnormal grid proportion and an abnormal light beam proportion corresponding to the laser point cloud data; and according to the abnormal grid proportion and the abnormal light beam proportion, verifying data of relocation information to determine a relocation result. According to the method and the device, the verification parameters in multiple aspects are comprehensively considered in relocation result verification to eliminate abnormal relocation results, so that the accuracy of relocation verification is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of robotics technology, and in particular to a relocation result verification method. Background Art

[0002] With the continuous innovation and development of science and technology, autonomous mobile robot technology has gradually become mature and stable. They usually have the ability to autonomously locate, move, perceive, make decisions, etc. After the autonomous mobile robot completes exploration in an unknown environment and builds a map, when it starts working at any location, or when an abnormal situation occurs during the work process and it cannot confirm its own position, it needs to go through the relocation process.

[0003] However, in actual work, the environment in which the autonomous mobile robot is located may be very complex, and the sensor data may also be biased. Therefore, it is necessary to comprehensively consider the multiple sensors carried by the autonomous mobile robot to verify the repositioning results and ensure the accuracy of the repositioning results.

[0004] In the prior art, the accuracy of the relocation result is usually determined based on the degree of match between the laser point cloud data obtained by the autonomous mobile robot at the time of relocation and the pre-built map data. However, since laser measurement itself has errors, the accuracy of verifying the relocation result based on the laser point cloud data is low. Summary of the invention

[0005] In order to solve the above technical problems, the present disclosure provides a relocation result verification method to improve the accuracy of relocation result verification.

[0006] In a first aspect, an embodiment of the present disclosure provides a relocation result verification method, which is applied to a mobile device, and includes:

[0007] Obtaining an environment map and relocation information from a mobile device, wherein the relocation information includes laser point cloud data obtained by the mobile device at the time of relocation by laser scanning the surrounding environment by emitting a laser beam;

[0008] Matching the laser point cloud data with the environment map to obtain an abnormal light beam passing through an obstacle in the environment map; obtaining an abnormal grid on the opposite side of the obstacle relative to the self-moving device based on the abnormal light beam;

[0009] Determine the abnormal grid ratio and abnormal beam ratio corresponding to the laser point cloud data;

[0010] According to the abnormal grid proportion and the abnormal light beam proportion, the data of the relocation information is verified to determine the relocation result.

[0011] In some embodiments, it also includes:

[0012] Obtaining laser sensor parameters of the self-mobile device;

[0013] According to the laser point cloud data and the laser sensor parameters of the self-moving device, the laser scanning range corresponding to the laser point cloud data is calculated, and the laser scanning range is the range between the nearest scanning point and the farthest scanning point corresponding to each laser point in the laser point cloud data.

[0014] In some embodiments, the laser sensor parameters include a minimum measurement distance and a maximum measurement distance of the laser sensor, and the step of calculating the laser scanning range corresponding to the laser point cloud data according to the laser point cloud data and the laser sensor parameters of the self-moving device includes:

[0015] Determine the scanning distance of each laser point in the laser point cloud data;

[0016] Determining the relative error of each laser point according to the scanning distance of each laser point and the laser sensor parameters of the self-moving device;

[0017] The laser scanning range corresponding to the laser point cloud data is determined according to the scanning distance of each laser point, the relative error of each laser point, the minimum measuring distance of the laser sensor and the maximum measuring distance of the laser sensor.

[0018] In some embodiments, matching the laser point cloud data with the environment map to determine the abnormal grid proportion corresponding to the laser point cloud data includes:

[0019] Matching the laser point cloud data with the environment map, and if a laser beam corresponding to a laser point passes through an obstacle in the environment map, determining that the laser beam is an abnormal beam;

[0020] The number of normal grids, the number of nearest abnormal grids, and the number of farthest abnormal grids passed by the abnormal light beam are counted according to the laser point cloud data, wherein the normal grid is a grid located between the self-moving device and the obstacle among the grids passed by the abnormal light beam, the nearest abnormal grid is a grid located between the obstacle and the nearest scanning point among the grids passed by the abnormal light beam, and the farthest abnormal grid is a grid located between the obstacle and the farthest scanning point among the grids passed by the abnormal light beam;

[0021] According to the number of normal grids, the number of nearest abnormal grids and the number of farthest abnormal grids contained in the laser point cloud data, the proportion of abnormal grids corresponding to the laser point cloud data is determined.

[0022] In some embodiments, determining the proportion of abnormal grids corresponding to the laser point cloud data according to the number of normal grids, the number of nearest abnormal grids, and the number of farthest abnormal grids contained in the laser point cloud data includes:

[0023] Determine the nearest grid number based on the normal grid number and the nearest abnormal grid number;

[0024] Determine the farthest grid number according to the normal grid number and the farthest abnormal grid number;

[0025] Calculating the ratio of the number of nearest abnormal grids in the laser point cloud data to the number of nearest grids to obtain the nearest abnormal grid ratio;

[0026] Calculating the ratio of the farthest abnormal grid number in the laser point cloud data to the farthest grid number to obtain the farthest abnormal grid ratio;

[0027] The smaller value between the nearest abnormal grid ratio and the farthest abnormal grid ratio is taken as the abnormal grid ratio.

[0028] In some embodiments, matching the laser point cloud data with the environment map to determine the abnormal light beam proportion includes:

[0029] Matching the laser point cloud data with the environment map, and if a laser beam corresponding to a laser point passes through an obstacle in the environment map, determining that the laser beam is an abnormal beam;

[0030] Calculate the ratio of the number of nearest abnormal beams to the number of laser beams to obtain the nearest abnormal beam ratio, wherein the nearest abnormal beam is an abnormal beam passing through a normal grid, a nearest abnormal grid, and a farthest abnormal grid;

[0031] Calculate the ratio of the number of the farthest abnormal beams to the number of laser beams to obtain the farthest abnormal beam ratio, wherein the farthest abnormal beam is an abnormal beam that passes through a normal grid and a farthest abnormal grid;

[0032] The smaller one of the nearest abnormal beam ratio and the farthest abnormal beam ratio is taken as the abnormal beam ratio.

[0033] In some embodiments, before verifying the relocation result according to the abnormal grid proportion and the abnormal beam proportion, the method further includes:

[0034] Matching the laser point cloud data with the environment map to determine a matching score between each laser point in the laser point cloud data and an obstacle in the environment map;

[0035] Determine a minimum matching ratio and a maximum matching ratio between the laser point cloud data and the environment map according to the matching score of each laser point;

[0036] Whether the relocation result is successful is determined according to the minimum matching ratio and the maximum matching ratio.

[0037] In some embodiments, the verifying the relocation result according to the abnormal grid proportion and the abnormal beam proportion includes:

[0038] If the abnormal grid ratio is greater than the maximum abnormal point ratio threshold, or the abnormal light beam ratio is greater than the maximum abnormal light beam ratio threshold, it is determined that the relocation fails; or,

[0039] If the minimum matching ratio is greater than or equal to the first matching threshold and the maximum matching ratio is less than or equal to the third matching ratio, and at the same time the abnormal grid proportion is greater than the minimum abnormal point proportion threshold or the abnormal light beam proportion is greater than the minimum abnormal light beam proportion threshold, then it is determined that the repositioning has failed, and the third matching threshold is greater than the first matching threshold and less than the second matching threshold.

[0040] In a second aspect, an embodiment of the present disclosure provides a relocation result verification method, which is applied to a mobile device, and includes:

[0041] Obtaining an environment map and relocation information from a mobile device, wherein the relocation information includes laser point cloud data obtained by the mobile device at the time of relocation by laser scanning the surrounding environment by emitting a laser beam;

[0042] Matching the laser point cloud data with the environment map to obtain an abnormal light beam passing through an obstacle in the environment map; obtaining an abnormal grid on the opposite side of the obstacle relative to the self-moving device based on the abnormal light beam;

[0043] Determine the abnormal grid proportion corresponding to the laser point cloud data;

[0044] According to the abnormal grid ratio, the data of the relocation information is verified to determine the relocation result.

[0045] In a third aspect, an embodiment of the present disclosure provides a relocation result verification method, which is applied to a mobile device, and includes:

[0046] Obtaining an environment map and relocation information from a mobile device, wherein the relocation information includes laser point cloud data obtained by the mobile device at the time of relocation by laser scanning the surrounding environment by emitting a laser beam;

[0047] Matching the laser point cloud data with the environment map to obtain an abnormal light beam passing through an obstacle in the environment map;

[0048] Determine the proportion of abnormal light beams corresponding to the laser point cloud data;

[0049] According to the abnormal light beam proportion, the data of the relocation information is verified to determine the relocation result.

[0050] The relocation result verification method provided by the embodiment of the present disclosure eliminates abnormal relocation results by comprehensively considering various verification parameters in the relocation result verification, thereby improving the accuracy of the relocation verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0053] Figure 1 A flow chart of a relocation result verification method provided by an embodiment of the present disclosure;

[0054] Figure 2 A schematic diagram of a laser scanning range provided in an embodiment of the present disclosure;

[0055] Figure 3 A schematic diagram of a matching score rule provided in an embodiment of the present disclosure;

[0056] Figure 4 A schematic diagram of an abnormal grid provided in an embodiment of the present disclosure;

[0057] Figure 5 A flow chart of a relocation result verification method provided by another embodiment of the present disclosure;

[0058] Figure 6 A flow chart of a relocation result verification method provided by another embodiment of the present disclosure;

[0059] Fig. 7A A schematic diagram of an application scenario provided by another embodiment of the present disclosure;

[0060] Figure 7B A schematic diagram of another application scenario provided for another embodiment of the present disclosure;

[0061] Figure 8 A schematic diagram of the structure of a relocation result verification device provided by an embodiment of the present disclosure;

[0062] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0063] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0065] The disclosed embodiment provides a relocation result verification method, which is described below in conjunction with a specific embodiment.

[0066] Figure 1 The flowchart of the relocation result verification method provided by the embodiment of the present disclosure. The method can be applied to a self-moving device, such as a sweeping and mopping robot. It is understandable that the relocation result verification method provided by the embodiment of the present disclosure can also be applied in other scenarios.

[0067] Below Figure 1 The relocation result verification method shown in the figure is introduced, and the specific steps of the method are as follows:

[0068] S101, obtaining an environment map and repositioning information from a mobile device, wherein the repositioning information includes laser point cloud data obtained by the mobile device at the time of repositioning by laser scanning the surrounding environment by emitting a laser beam.

[0069] First, the self-moving device needs to perform initialization operations related to positioning, such as loading the size parameters of the self-moving device, etc. During the operation of the self-moving device, it is determined whether the self-moving device meets the repositioning conditions according to the state of the self-moving device, such as detecting that the self-moving cleaning device is lifted, moved, or trapped. When the self-moving device meets the repositioning conditions, the repositioning operation is performed.

[0070] The relocation operation is the process by which a mobile device collects surrounding environment information based on sensors at the current moment and determines its current location after matching it with a preset map.

[0071] The mobile device performs a repositioning operation to obtain repositioning information, which at least includes laser scanning data obtained after the mobile device performs a laser scan of the surrounding environment at the moment of repositioning; optionally, the repositioning information also includes the posture information of the mobile device itself at the moment of repositioning, etc., which is not limited to the embodiments of the present disclosure.

[0072] S102, matching the laser point cloud data with the environment map to obtain an abnormal light beam passing through an obstacle in the environment map; obtaining an abnormal grid on the opposite side of the obstacle relative to the self-moving device based on the abnormal light beam; and determining the abnormal grid ratio and abnormal light beam ratio corresponding to the laser point cloud data.

[0073] The abnormal grid is a grid corresponding to a beam segment in the abnormal light beam that is on the opposite side of the obstacle in the environment map from the self-moving device, and the abnormal light beam is a laser light beam that passes through the obstacle in the environment map.

[0074] The environment map is the environment map data pre-stored in the mobile device or the server of the mobile device. When the laser point cloud data matches the environment map well, it can be considered that the relocation is successful, otherwise it is considered that the relocation fails.

[0075] Specifically, the environment map includes obstacle information. When the laser point cloud data is matched with the environment map, under normal circumstances, the laser light beam corresponding to the laser point in the laser point cloud data should be emitted from the position of the mobile device and end at the position of the obstacle; when the laser light beam corresponding to the laser point in the laser point cloud data passes through the obstacle in the environment map, such laser light beam is considered to be an abnormal light beam; or, in some embodiments, when the laser light beam corresponding to the laser point in the laser point cloud data passes through an unknown area in the environment map, such laser light beam is also considered to be an abnormal light beam.

[0076] Environmental maps are usually divided into several grids, and the corresponding laser point cloud data is also divided into several grids in the same way, and the two are matched and corresponded. Under normal circumstances, the grids corresponding to the laser beam should all be located between the self-moving device and the obstacle; when an abnormal beam appears, some grids on the other side of the self-moving device relative to the obstacle will also be passed through by the abnormal beam. Such grids are called abnormal grids, and the laser beam passing through the abnormal grid is identified as an abnormal beam.

[0077] The abnormal grid is the grid corresponding to the beam segment in the abnormal light beam that is on the opposite side of the obstacle in the environmental map from the mobile device, and the corresponding abnormal grid ratio refers to the ratio of the abnormal grid to the total number of grids corresponding to the abnormal light beam; the abnormal light beam is a laser light beam that passes through the obstacle in the environmental map, and the corresponding abnormal light beam ratio refers to the ratio of the abnormal light beam to the total number of laser light beams emitted by the mobile device, that is, the ratio of the total number of laser light beams corresponding to the laser point cloud data.

[0078] S103. Verify the repositioning result according to the abnormal grid proportion and the abnormal light beam proportion.

[0079] Taking into account the above-mentioned abnormal grid proportion and abnormal light beam proportion, the consistency between the laser point cloud data and the environmental map is examined to verify the relocation result.

[0080] The disclosed embodiment obtains an environmental map and a repositioning result from a mobile device, wherein the repositioning information includes laser point cloud data obtained by the mobile device performing laser scanning of the surrounding environment by emitting a laser beam at the time of repositioning; the laser point cloud data is matched with the environmental map to obtain an abnormal light beam passing through an obstacle in the environmental map; an abnormal grid on the opposite side of the obstacle relative to the mobile device is obtained based on the abnormal light beam; the proportion of abnormal grids and the proportion of abnormal light beams corresponding to the laser point cloud data are determined; the repositioning result is verified according to the proportion of abnormal grids and the proportion of abnormal light beams, and various verification parameters are comprehensively considered in the verification of the repositioning result to exclude abnormal repositioning results, thereby improving the accuracy of the repositioning verification.

[0081] Based on the above embodiment, the method also includes: obtaining the laser sensor parameters of the self-moving device; calculating the laser scanning range corresponding to the laser point cloud data according to the laser point cloud data and the laser sensor parameters of the self-moving device, wherein the laser scanning range is the range between the nearest scanning point and the farthest scanning point corresponding to each laser point in the laser point cloud data.

[0082] Due to the theoretical characteristics of laser ranging itself, different errors will occur depending on the distance between the target object and the laser sensor. Therefore, it is necessary to determine the laser scanning range based on the parameters of the laser sensor itself and the actual measurement distance value. The laser scanning range represents the possible error range relative to the measurement result.

[0083] Specifically, the laser sensor parameters include a minimum measurement distance and a maximum measurement distance of the laser sensor, and the laser scanning range corresponding to the laser point cloud data is calculated based on the laser point cloud data and the laser sensor parameters of the self-moving device, including: determining the scanning distance of each laser point in the laser point cloud data; determining the relative error of each laser point based on the scanning distance of each laser point and the laser sensor parameters of the self-moving device; determining the laser scanning range corresponding to the laser point cloud data based on the scanning distance of each laser point, the relative error of each laser point, the minimum measurement distance of the laser sensor, and the maximum measurement distance of the laser sensor.

[0084] Among them, the minimum measurement distance and maximum measurement distance of the laser sensor are inherent properties of the laser sensor. When the distance between the object to be measured and the laser sensor is less than the minimum measurement distance, or the distance between the object to be measured and the laser sensor is greater than the maximum measurement distance, the error of the distance measurement result for the object to be measured is large.

[0085] After obtaining the initial laser point cloud data, first perform data processing such as distortion removal, and then convert the laser point cloud data in the laser sensor coordinate system to the world coordinate system according to the posture information of the mobile device, and perform coordinate system alignment with the environment map. The specific process is expressed as follows:

[0086]

[0087] Where P world is the world coordinate system, is the matrix parameter in the process of transforming from the mobile device coordinate system to the robot coordinate system, P base The coordinate system of the self-moving device.

[0088] For each laser point in the laser point cloud data, the actual position of the laser point can be obtained relative to the scanning distance of the mobile device. The scanning distance is the measurement result of the laser distance measurement. The laser sensor has different relative errors at different scanning distances l:

[0089] abs_error=l·relative_error(l)

[0090] Where relative_error is an error function, and its function value represents the error rate, which is related to the scanning distance l. Based on the error function, there is a linear relationship between the relative error abs_error and the scanning distance l as shown in the above formula.

[0091] The laser scanning range of the laser point is further determined based on the scanning distance, the relative error, the minimum measuring distance of the laser sensor, and the maximum measuring distance of the laser sensor, which is expressed as:

[0092] l∈[max(min_length,l-abs_error),min(max_length,l

[0093] +abs_error)]

[0094] Where min_length is the minimum measurement distance of the laser sensor, max_length is the maximum measurement distance of the laser sensor, and the two boundary values ​​in the value range of l are the distances between the nearest scanning point and the farthest scanning point and the self-moving device.

[0095] The nearest scanning point and the farthest scanning point are calculated for each laser point in the laser point cloud data, and finally the laser scanning range in the world coordinate system corresponding to the laser point cloud data is obtained.

[0096] Figure 2 A schematic diagram of a laser scanning range provided in an embodiment of the present disclosure. Figure 2 As shown, the solid line is composed of multiple laser points in the laser point cloud data, and the dotted line is composed of the nearest scanning point and the farthest scanning point of each laser point. The range between the two dotted lines is the laser scanning range in the world coordinate system.

[0097] The disclosed embodiment makes the repositioning verification more accurate by referring to the laser measurement error during the repositioning result verification process.

[0098] The following describes in detail the calculation methods of the matching degree, the abnormal grid proportion, and the abnormal light beam proportion in conjunction with specific embodiments.

[0099] In some embodiments, before verifying the repositioning result according to the abnormal grid proportion and / or the abnormal light beam proportion, the method further includes: matching the laser point cloud data with the environmental map to determine a matching score between each laser point in the laser point cloud data and an obstacle in the environmental map; determining a degree of matching between the laser point cloud data and the environmental map according to the matching score of each laser point; and determining whether the repositioning result is successful according to the matching degree.

[0100] In some embodiments, matching the laser point cloud data with the environmental map to determine the degree of matching between the laser point cloud data and the environmental map includes: matching the laser point cloud data with the environmental map to determine a matching score between each laser point in the laser point cloud data and an obstacle in the environmental map; and determining the degree of matching between the laser point cloud data and the environmental map based on the matching score of each laser point.

[0101] In the disclosed embodiment, a global matching score method is adopted to calculate the matching score of each laser point in the laser point cloud data. Each laser point in the laser point cloud data should correspond to an obstacle in the actual environment of the self-mobile device, and the corresponding laser point will be generated only when the laser beam hits the surface of the obstacle. Therefore, according to the environmental map, if there is an obstacle at the actual position corresponding to the laser point in the environmental map, the laser point is considered to match the environmental map; accordingly, the closer the actual position corresponding to the laser point is to the obstacle position recorded in the environmental map, the higher the matching degree between the laser point and the obstacle in the environmental map, and the higher the matching score. The matching score of each laser point in the laser point cloud data is calculated to obtain the total matching score of the laser point cloud data. The higher the total matching score of the laser point cloud data, the higher the matching degree of the laser point cloud data and the environmental map.

[0102] Specifically, when the laser point coincides with an obstacle in the environment map, the matching score of the laser point is determined to be a first score; when the laser point is within a first neighborhood of an obstacle in the environment map and does not coincide with the obstacle, the matching score of the laser point is determined to be a second score; when the laser point is outside the first neighborhood of an obstacle in the environment map and within a second neighborhood of the obstacle, the matching score of the laser point is determined to be a third score; wherein the first score is greater than the second score and greater than the third score, and the distance between the first neighborhood and the obstacle is less than the distance between the second neighborhood and the obstacle.

[0103] When the laser point coincides with an obstacle in the environment map, the laser point is completely matched with the environment map, and the matching score of the laser point is determined to be the highest score, i.e., the first score; the distance between the first neighborhood and the obstacle is less than the distance between the second neighborhood and the obstacle, so the matching score of the laser point in the first neighborhood is higher than that of the laser point in the second neighborhood. It is understandable that the embodiment of the present disclosure is described by taking only two neighborhoods as an example, and multiple neighborhoods and their respective corresponding matching scores can be set according to actual conditions to determine the matching score of each laser point in the laser point cloud data.

[0104] The calculation process of the total matching score of laser point cloud data is as follows:

[0105]

[0106] The matching ratio mr (match_ratio) calculation process between the laser point cloud data and the environment map is as follows:

[0107]

[0108] Where n is the number of laser points in the laser point cloud data, is the i-th laser point in the laser point cloud data, is the matching score of the i-th laser point.

[0109] Figure 3 A schematic diagram of a matching score rule provided in an embodiment of the present disclosure. In an embodiment of the present disclosure, a calculation method of an 8-connected domain is used to calculate the matching score of each laser point in the laser point cloud data. Figure 3 As shown in the figure, 8 connected regions are constructed based on the middle grid to form a nine-square grid, where the middle grid is the grid where the laser point is located, recorded as the current grid. If the current grid is an obstacle grid, the matching score of the laser point is recorded as 1 point; if one or more of the upper, lower, left, and right grids of the current grid is an obstacle grid, the matching score of the laser point is recorded as 0.5 points; if one or more of the upper left, lower left, upper right, and lower right grids of the current grid is an obstacle grid, the matching score of the laser point is recorded as 0.293 points; in other cases, the matching score of the laser point is recorded as 0 points.

[0110] In some embodiments, the maximum matching score of the laser point cloud data is calculated with reference to the laser scanning range. max , minimum matching score score min , maximum matching ratio mr max , minimum matching ratio mr min Specifically, the matching score is calculated based on the closest scanning point and the farthest scanning point of each laser point in the above manner, and the larger value is selected as the maximum matching score score. max , the smaller value is used as the minimum matching score score min , further calculate the maximum matching ratio mr based on the maximum matching score and the minimum matching score max And the minimum matching ratio mr min Or, calculate the matching score for each point in the laser scanning range according to the above method, and select the maximum value as the maximum matching score score max , the minimum value is used as the minimum matching score score min , further calculate the maximum matching ratio mr based on the maximum matching score and the minimum matching score max And the minimum matching ratio mr min .

[0111] The disclosed embodiment assigns a matching score to each laser point through the relative position of the laser point in the laser point cloud data and the obstacle in the environment map, so as to quantify the degree of matching between the laser point cloud data and the environment map, thereby providing accurate data for repositioning result verification.

[0112] In some embodiments, the laser point cloud data is matched with the environmental map to determine the proportion of abnormal grids corresponding to the laser point cloud data, including: matching the laser point cloud data with the environmental map, if there is a laser beam corresponding to the laser point passing through an obstacle in the environmental map, then determining that the laser beam is an abnormal beam; counting the number of normal grids, the number of nearest abnormal grids, and the number of farthest abnormal grids passed by the abnormal beam according to the laser point cloud data, the normal grid is a grid located between the self-moving device and the obstacle among the grids passed by the abnormal beam, the nearest abnormal grid is a grid located between the obstacle and the nearest scanning point among the grids passed by the abnormal beam, and the farthest abnormal grid is a grid located between the obstacle and the farthest scanning point among the grids passed by the abnormal beam; determining the proportion of abnormal grids corresponding to the laser point cloud data according to the number of normal grids, the number of nearest abnormal grids, and the number of farthest abnormal grids contained in the laser point cloud data.

[0113] Figure 4 A schematic diagram of an abnormal grid provided by an embodiment of the present disclosure. Figure 4 As shown, taking two abnormal light beams L1 and L2 emitted from a mobile device as an example, the solid line part represents an obstacle (such as a wall, etc.) in the environment map, and the dotted line part represents the nearest scanning point and the farthest scanning point. It can be seen that the abnormal light beams L1 and L2 pass through the obstacles in the environment map, and the grid corresponding to the beam segment after passing through the obstacle is the abnormal grid. Specifically, the abnormal grid includes the nearest abnormal grid and the farthest abnormal grid, wherein the nearest abnormal grid is the grid between the obstacle and the nearest scanning point in the grid passed by the abnormal light beam, as shown in FIG. Figure 4 The grids 41 and 42 corresponding to the abnormal beam L1, and the grids 44 and 45 corresponding to the abnormal beam L2; the farthest abnormal grid is the grid located between the obstacle and the farthest scanning point among the grids passed by the abnormal beam, that is, the sum of the nearest abnormal grid and the extra farthest grid, wherein the extra farthest grid is the grid located between the nearest scanning point and the farthest scanning point among the grids passed by the abnormal beam, as shown in FIG. Figure 4 The additional farthest grid 43 and the farthest abnormal grids 41-43 corresponding to the abnormal beam L1, and the additional farthest grid 46 and the farthest abnormal grids 44-46 corresponding to the abnormal beam L2. The normal grid is the grid between the self-moving device and the obstacle among the grids passed by the abnormal beam, such as Figure 4 The remaining grids except the abnormal grids 41-46 passed by the abnormal light beams L1 and L2.

[0114] In some embodiments, determining the abnormal grid ratio corresponding to the laser point cloud data according to the number of normal grids, the nearest abnormal grid number and the farthest abnormal grid number contained in the laser point cloud data includes: determining the nearest grid number according to the number of normal grids and the nearest abnormal grid number; determining the farthest grid number according to the number of normal grids and the farthest abnormal grid number; calculating the ratio of the nearest abnormal grid number in the laser point cloud data to the nearest grid number to obtain the nearest abnormal grid ratio; calculating the ratio of the farthest abnormal grid number in the laser point cloud data to the farthest grid number to obtain the farthest abnormal grid ratio; and taking the smaller value between the nearest abnormal grid ratio and the farthest abnormal grid ratio as the abnormal grid ratio.

[0115] Specifically, the number of nearest grids is the sum of the number of normal grids and the number of nearest abnormal grids, and the number of farthest grids is the sum of the number of normal grids and the number of farthest abnormal grids.

[0116] In summary, for each beam, the number of normal grids it passes through (normal_grid), the number of nearest abnormal grids (nearest_abnormal_grid), the number of farthest abnormal grids (farrest_abnormal_grid), the number of nearest grids (total_nearest_grid), the number of farthest grids (total_farrest_grid), and the number of extra farthest grids (pure_far_grid) are counted, and the following relationship is satisfied between them:

[0117] total_nearest_grid=normal_grid+nearest_abnormal_grid

[0118] total_farrest_grid=normal_grid+farrest_abnormal_grid farrest_abnormal_grid=nearest_abnormal_grid+pure_far_grid

[0119] Traverse the n laser beams in the laser point cloud data, calculate the ratio of the nearest abnormal grid number to the nearest grid number, and obtain the nearest abnormal grid ratio of the laser point cloud data (denoted as pr 1 ); Calculate the ratio of the farthest abnormal grid number to the farthest grid number to obtain the farest abnormal grid ratio of the laser point cloud data (referred to as pr 2 ), the calculation process is as follows:

[0120]

[0121]

[0122] Further determine the relationship between the nearest abnormal grid ratio and the farthest abnormal grid ratio, and select the smaller value of the two as the abnormal grid ratio pr min The calculation process is shown as follows:

[0123] pr min =min{pr 1 ,pr 2}

[0124] The proportion of abnormal grids represents the degree of abnormality of the abnormal light beam. For example, the higher the proportion of abnormal grids, the more serious the abnormality in the matching between the laser point cloud data and the environmental map. This reflects the degree of matching between the laser point cloud data and the environmental map from another perspective.

[0125] In some embodiments, the nearest scanning point of the abnormal light beam and the self-moving device are located on the same side of the obstacle, while the farthest scanning point and the self-moving device are located on both sides of the obstacle respectively. At this time, the nearest abnormal grid of the abnormal light beam is 0, the number of nearest grids is equal to the number of normal grids, the farthest grid number is equal to the sum of the number of normal grids and the farthest abnormal grid number, and the farthest abnormal grid number is equal to the additional farthest grid number.

[0126] The disclosed embodiment takes into account the error of the laser sensor itself, calculates the ratio of the abnormal grid based on the nearest scanning point and the farthest scanning point, quantifies the degree of abnormality of the abnormal light beam, and provides data support from another angle for the verification of the repositioning results.

[0127] In some embodiments, the laser point cloud data is matched with the environmental map to determine the abnormal beam ratio, including: matching the laser point cloud data with the environmental map, if there is a laser beam corresponding to a laser point passing through an obstacle in the environmental map, determining that the laser beam is an abnormal beam; calculating the ratio of the number of nearest abnormal beams to the number of laser beams to obtain the nearest abnormal beam ratio, wherein the nearest abnormal beam is an abnormal beam passing through a normal grid, a nearest abnormal grid, and a farthest abnormal grid; calculating the ratio of the number of farthest abnormal beams to the number of laser beams to obtain the farthest abnormal beam ratio, wherein the farthest abnormal beam is an abnormal beam passing through a normal grid and a farthest abnormal grid; taking the smaller of the nearest abnormal beam ratio and the farthest abnormal beam ratio as the abnormal beam ratio.

[0128] Referring to the above embodiment, under normal circumstances, all grids corresponding to the laser beam should be located between the self-moving device and the obstacle; when an abnormal beam appears, part of the grids on the other side of the self-moving device relative to the obstacle will also be passed through by the abnormal beam. Such grids are called abnormal grids, and the laser beam that passes through the normal grids and the abnormal grids is identified as an abnormal beam.

[0129] Specifically, the abnormal beam includes the nearest abnormal beam and the farthest abnormal beam, wherein the nearest abnormal beam is the abnormal beam that passes through the normal grid, the nearest abnormal grid, and the farthest abnormal grid. Figure 4 As shown, abnormal beams L1 and L2 are the nearest abnormal beams, and there are also several laser beams between the angles of L1 and L2, which are the nearest abnormal beams. In some embodiments, the nearest scanning point of the abnormal beam and the self-moving device are located on the same side of the obstacle, while the farthest scanning point and the self-moving device are located on both sides of the obstacle. At this time, the nearest abnormal grid of the abnormal beam is 0, and the corresponding abnormal beam only passes through the normal grid and the farthest abnormal grid. Such an abnormal beam becomes the farthest abnormal beam.

[0130] After determining the nearest anomalous beam and the farthest anomalous beam, calculate the number of nearest anomalous beams i respectively The ratio of the nearest abnormal ray ratio (denoted as rr) to the number of laser beams n is 1 ), calculate the number of the farthest anomalous beams The ratio of the farthest abnormal ray ratio (denoted as rr) to the number of laser beams n is obtained. 2 ), the specific calculation process is as follows:

[0131]

[0132]

[0133] The smaller of the nearest abnormal beam ratio and the farthest abnormal beam ratio is further taken as the abnormal beam ratio rr min , expressed as:

[0134] rr min =min{rr 1 ,rr 2}

[0135] The abnormal beam ratio actually represents the angle range covered by the abnormal beam. The embodiment of the present disclosure evaluates the coverage of the abnormal beam by calculating the abnormal beam ratio, thereby further ensuring the accuracy of the relocation verification result.

[0136] The following is a detailed introduction to the rules for verifying the relocation results based on one or more of the matching degree, the abnormal grid proportion, and the abnormal beam proportion.

[0137] In some embodiments, the matching degree includes a maximum matching ratio and a minimum matching ratio. If the minimum matching ratio is less than a first matching threshold, it is determined that the relocation fails.

[0138] Minimum matching ratio mr min When it is less than the first matching threshold, it means that the laser point cloud data and the environment map have a poor matching degree, and the relocation is directly considered to have failed. Optionally, the first matching threshold is 50%.

[0139] In some embodiments, if the minimum matching ratio is greater than or equal to a second matching threshold, it is determined that the relocation is successful, and the second matching threshold is greater than the first matching threshold.

[0140] When the minimum matching ratio mr min When it is greater than or equal to the second matching threshold, it means that the laser point cloud data matches the environment map very well, and the relocation is directly determined to be successful, wherein the second matching threshold is greater than the first matching threshold, and the second matching threshold should take a higher ratio value, such as 95%.

[0141] In some embodiments, if the abnormal grid ratio is greater than a maximum abnormal point ratio threshold, or the abnormal light beam ratio is greater than a maximum abnormal light beam ratio threshold, it is determined that the repositioning fails.

[0142] When the abnormal grid proportion pr min Greater than the maximum abnormal point ratio threshold, or the abnormal beam ratio rr min When it is greater than the abnormal light ratio threshold, it means that there are more abnormal grids or abnormal beams, and relocation is directly considered to have failed. Optionally, the maximum abnormal point ratio threshold is 50%, and the abnormal light ratio threshold is 60%.

[0143] In some embodiments, if the minimum matching ratio is greater than or equal to the first matching threshold and the maximum matching ratio is less than or equal to the third matching ratio, and at the same time the abnormal grid proportion is greater than the minimum abnormal point proportion threshold or the abnormal light beam proportion is greater than the minimum abnormal light beam proportion threshold, then it is determined that the repositioning has failed, and the third matching threshold is greater than the first matching threshold and less than the second matching threshold.

[0144] When the minimum matching ratio mr min is greater than or equal to the first matching threshold, and the maximum matching ratio mr max Less than or equal to the third matching ratio, and the abnormal grid ratio pr min Greater than the minimum abnormal point ratio threshold or abnormal beam ratio rr minIf it is greater than the minimum abnormal light ratio threshold, it means that the matching degree between the laser point cloud data and the environment map is average, but the abnormal grid ratio or abnormal light beam ratio is high, which is considered as relocation failure. Optionally, the minimum abnormal point ratio threshold is 40% and the minimum abnormal light ratio threshold is 50%.

[0145] It is understandable that the rules for verifying the repositioning results based on one or more of the degree of matching, the proportion of abnormal grids, and the proportion of abnormal beams are not limited to the above items, and the various matching thresholds or ratio thresholds are not limited to the examples given above. In actual situations, the verification rules and parameters can be reasonably adjusted according to verification needs, and the embodiments of the present disclosure do not limit this.

[0146] The disclosed embodiment comprehensively evaluates and verifies the repositioning result through the degree of matching, the proportion of abnormal grids, and the proportion of abnormal light beams, and provides a variety of verification methods to improve the accuracy of the repositioning verification.

[0147] Figure 5 A flow chart of a relocation result verification method provided by another embodiment of the present disclosure. The method can be applied to a self-moving device, such as a sweeping and mopping robot. It is understandable that the relocation result verification method provided by the embodiment of the present disclosure can also be applied in other scenarios.

[0148] Below Figure 5 The relocation result verification method shown in the figure is introduced, and the specific steps of the method are as follows:

[0149] Step S501: Acquire an environment map and repositioning information from a mobile device, wherein the repositioning information includes laser point cloud data obtained by the mobile device at the time of repositioning by laser scanning the surrounding environment by emitting a laser beam.

[0150] Step S502: Match the laser point cloud data with the environment map to obtain an abnormal light beam that passes through an obstacle in the environment map; obtain an abnormal grid on the opposite side of the obstacle relative to the self-moving device based on the abnormal light beam; and determine the proportion of the abnormal grid corresponding to the laser point cloud data.

[0151] Step S503: verify the data of the relocation information according to the abnormal grid proportion to determine the relocation result.

[0152] Among them, the content of determining the proportion of abnormal grids can refer to the above Figure 1The relevant steps in the illustrated embodiment are not repeated here. The disclosed embodiment only considers the proportion of abnormal grids. If the proportion of abnormal grids is greater than the maximum abnormal point ratio threshold, the relocation failure is determined; when the minimum matching ratio is greater than or equal to the first matching threshold and the maximum matching ratio is less than or equal to the third matching ratio, the proportion of abnormal grids is greater than the minimum abnormal point ratio threshold, and the relocation failure is determined. By examining the consistency between the laser point cloud data and the environmental map, the relocation result can be verified.

[0153] Figure 6 A flow chart of a relocation result verification method provided by another embodiment of the present disclosure. The method can be applied to a self-moving device, such as a sweeping and mopping robot. It is understandable that the relocation result verification method provided by the embodiment of the present disclosure can also be applied in other scenarios.

[0154] Step S601: Acquire an environment map and repositioning information from a mobile device, wherein the repositioning information includes laser point cloud data obtained by the mobile device at the time of repositioning by laser scanning the surrounding environment by emitting a laser beam.

[0155] Step S602: Match the laser point cloud data with the environment map to obtain abnormal light beams that pass through obstacles in the environment map; and determine the proportion of abnormal light beams corresponding to the laser point cloud data.

[0156] Step S603: According to the abnormal light beam proportion, the data of the relocation information is verified to determine the relocation result.

[0157] Among them, the content of determining the proportion of abnormal beams can refer to the above Figure 1 The relevant steps in the illustrated embodiment are not repeated here. The disclosed embodiment only considers the abnormal light beam ratio. If the abnormal light beam ratio is greater than the maximum abnormal light beam ratio threshold, the relocation is determined to have failed; when the minimum matching ratio is greater than or equal to the first matching threshold and the maximum matching ratio is less than or equal to the third matching ratio, the abnormal light beam ratio is greater than the minimum abnormal light beam ratio threshold, and the relocation is determined to have failed. The consistency of the laser point cloud data and the environmental map is examined to verify the relocation result.

[0158] Fig. 7A This is a schematic diagram of an application scenario provided by another embodiment of the present disclosure, which is used to verify whether the mobile device adopts the relocation verification result method described in any of the above embodiments. Fig. 7A As shown, a test site scene is provided in which an opening on the inner contour of the test site can be opened or closed, and the outer contour of the test site can be moved forward and backward along the y direction to open or close the opening on the inner contour of the test site.

[0159] The self-moving device has pre-established a scene map of the experimental field with the opening of the internal contour closed. By picking up the self-moving device, the relocation of the self-moving device can be triggered. Move the external contour of the experimental field to open the opening, and place the self-moving robot at a fixed position in the field (i.e., the distance d between the self-moving device and the contour of the experimental field) 1 and d 2 Fixed), so that the laser beam emitted by the self-moving robot during repositioning can pass through the opening and reach the outer contour of the experimental site, so as to obtain the abnormal beam and abnormal grid when the opening is opened. 3 is the distance between the inner contour of the experimental site and the outer contour of the experimental site at the opening. In this scenario, the outer contour of the experimental site is moved so that the distance between the outer contour and the inner contour of the experimental site is d 3 , change d 3 Multiple experiments were performed (due to d 1 d 2 Fixed, by adjusting d 3 The abnormal grid ratio r can be changed A3 ), we can find that there is a certain distance threshold D 1 , when d 3 When the distance is less than the threshold, the probability of successful relocation is high. 3 When the distance is greater than this threshold, the probability of relocation failure is high.

[0160] Figure 7B This is a schematic diagram of an application scenario provided by another embodiment of the present disclosure, which is used to further verify whether the mobile device adopts the relocation verification result method described in any of the above embodiments. Figure 7B As shown, there are two openings on the inner contour of the experimental site that can be opened or closed. Figure 7B The mobile device is at a fixed position (d 1 d 2 The sum of the coverage angles of the two openings of the abnormal beam when the and Fig. 7A Abnormal beam coverage angle of mobile devices same.

[0161] The self-moving device has pre-established a scene map of the case where the opening of the internal contour of the experimental site is closed. By picking up the self-moving device, the relocation of the self-moving device can be triggered. Move the two external contours of the experimental site to open two openings, and place the self-moving robot in a fixed position in the site, so that the laser beam emitted by the self-moving robot during relocation can pass through the two openings to reach the external contour of the experimental site, so as to obtain the abnormal beam and abnormal grid when the opening is opened. In this scenario, move the two external contours of the experimental site at the same time so that the two external contours are at a distance d from the internal contour of the experimental site. 3Change (due to d 1 d 2 Fixed, by adjusting d 3 The abnormal grid ratio r can be changed A3 ), change d 3 After multiple experiments, we can find that there is a certain distance threshold D 2 , the distance threshold D 2 The distance threshold D 1 Closer, when d 3 Less than the distance threshold D 2 The probability of successful relocation is higher when d 3 Greater than the distance threshold D 2 The probability of relocation failure is high.

[0162] If after picking up the self-moving robot, only one outer contour in the experimental field is moved to open an opening. The self-moving robot is placed at a fixed position in the field, so that the laser beam emitted by the self-moving robot during repositioning can pass through the opening here to reach the outer contour of the experimental field, so as to obtain the abnormal beam and abnormal grid when the opening is opened. In this scenario, the distance d between the outer contour moved and the inner contour of the experimental field is changed. 3 After multiple experiments, we can find that there is a certain distance threshold D 3 , the distance threshold D 3 The distance threshold D 2 The difference is large, when d 3 Less than the distance threshold D 3 The probability of successful relocation is higher when d 3 Greater than the distance threshold D 3 The probability of relocation failure is high.

[0163] Figure 8 The structure diagram of the relocation result verification device provided in the embodiment of the present disclosure. The relocation result verification device may be the self-moving device as described in the above embodiment, or the relocation result verification device may be a component or assembly in the self-moving device. The relocation result verification device provided in the embodiment of the present disclosure may execute the processing flow provided in the embodiment of the relocation result verification method, such as Figure 8As shown, the repositioning result verification device 80 includes: a first acquisition module 81, a matching module 82, and a verification module 83; wherein the first acquisition module 81 is used to obtain the environmental map and repositioning information of the self-mobile device, and the repositioning information includes the laser point cloud data obtained by the self-mobile device at the time of repositioning by laser scanning the surrounding environment by emitting a laser beam; the matching module 82 is used to match the laser point cloud data with the environmental map to obtain an abnormal light beam passing through an obstacle in the environmental map; based on the abnormal light beam, an abnormal grid on the opposite side of the obstacle relative to the self-mobile device is obtained; and the abnormal grid ratio and abnormal light beam ratio corresponding to the laser point cloud data are determined; the verification module 83 is used to verify the data of the repositioning information according to the abnormal grid ratio and the abnormal light beam ratio to determine the repositioning result.

[0164] Optionally, the repositioning result verification device 80 also includes a second acquisition module 84 and a calculation module 85; wherein the second acquisition module 84 is used to obtain the laser sensor parameters of the self-moving device; the calculation module 85 is used to calculate the laser scanning range corresponding to the laser point cloud data based on the laser point cloud data and the laser sensor parameters of the self-moving device, and the laser scanning range is the range between the nearest scanning point and the farthest scanning point corresponding to each laser point in the laser point cloud data.

[0165] Optionally, the laser sensor parameters include the minimum measurement distance and the maximum measurement distance of the laser sensor; the calculation module 85 includes a first determination unit 851, a second determination unit 852, and a third determination unit 853; wherein the first determination unit 851 is used to determine the scanning distance of each laser point in the laser point cloud data; the second determination unit 852 is used to determine the relative error of each laser point according to the scanning distance of each laser point and the laser sensor parameters of the self-mobile device; the third determination unit 853 is used to determine the laser scanning range corresponding to the laser point cloud data according to the scanning distance of each laser point, the relative error of each laser point, the minimum measurement distance of the laser sensor, and the maximum measurement distance of the laser sensor.

[0166] Optionally, the matching module 82 includes a first matching unit 821, which is used to match the laser point cloud data with the environment map to determine the degree of matching between the laser point cloud data and the environment map. Specifically, the first matching unit 821 is used to match the laser point cloud data with the environment map to determine the matching score between each laser point in the laser point cloud data and the obstacle in the environment map; and determine the degree of matching between the laser point cloud data and the environment map according to the matching score of each laser point.

[0167] Optionally, the first matching unit 821 is further used to determine that the matching score of the laser point is a first score when the laser point coincides with an obstacle in the environment map; when the laser point is within a first neighborhood of an obstacle in the environment map and does not coincide with the obstacle, determine that the matching score of the laser point is a second score; when the laser point is outside the first neighborhood of an obstacle in the environment map and within a second neighborhood of the obstacle, determine that the matching score of the laser point is a third score; wherein the first score is greater than the second score and greater than the third score, and the distance between the first neighborhood and the obstacle is less than the distance between the second neighborhood and the obstacle.

[0168] Optionally, the matching module 82 further includes a second matching unit 822, which is used to match the laser point cloud data with the environmental map to determine the proportion of abnormal grids corresponding to the laser point cloud data. Specifically, the second matching unit 822 is used to match the laser point cloud data with the environmental map, and if there is a laser beam corresponding to the laser point passing through an obstacle in the environmental map, the laser beam is determined to be an abnormal beam; the number of normal grids, the number of nearest abnormal grids, and the number of farthest abnormal grids passed by the abnormal beam are counted according to the laser point cloud data, the normal grid is a grid located between the self-moving device and the obstacle in the grid passed by the abnormal beam, the nearest abnormal grid is a grid located between the obstacle and the nearest scanning point in the grid passed by the abnormal beam, and the farthest abnormal grid is a grid located between the obstacle and the farthest scanning point in the grid passed by the abnormal beam; the proportion of abnormal grids corresponding to the laser point cloud data is determined according to the number of normal grids, the number of nearest abnormal grids, and the number of farthest abnormal grids contained in the laser point cloud data.

[0169] Optionally, the second matching unit 822 is specifically used to determine the nearest grid number based on the normal grid number and the nearest abnormal grid number; determine the farthest grid number based on the normal grid number and the farthest abnormal grid number; calculate the ratio of the nearest abnormal grid number in the laser point cloud data to the nearest grid number to obtain the nearest abnormal grid ratio; calculate the ratio of the farthest abnormal grid number in the laser point cloud data to the farthest grid number to obtain the farthest abnormal grid ratio; and take the smaller value between the nearest abnormal grid ratio and the farthest abnormal grid ratio as the abnormal grid ratio.

[0170] Optionally, the matching module 82 further includes a third matching unit 823, which is used to match the laser point cloud data with the environmental map to determine the abnormal beam ratio. Specifically, the third matching unit 823 is used to match the laser point cloud data with the environmental map, and if there is a laser beam corresponding to the laser point passing through an obstacle in the environmental map, the laser beam is determined to be an abnormal beam; the ratio of the number of the nearest abnormal beams to the number of laser beams is calculated to obtain the nearest abnormal beam ratio, and the nearest abnormal beam is an abnormal beam passing through a normal grid, a nearest abnormal grid, and a farthest abnormal grid; the ratio of the number of the farthest abnormal beams to the number of laser beams is calculated to obtain the farthest abnormal beam ratio, and the farthest abnormal beam is an abnormal beam passing through a normal grid and a farthest abnormal grid; the smaller of the nearest abnormal beam ratio and the farthest abnormal beam ratio is used as the abnormal beam ratio.

[0171] Optionally, the matching degree includes a maximum matching ratio and a minimum matching ratio, and the verification module 83 is used to determine that the relocation has failed if the minimum matching ratio is less than a first matching threshold; or, if the minimum matching ratio is greater than or equal to a second matching threshold, determine that the relocation has been successful, and the second matching threshold is greater than the first matching threshold.

[0172] Optionally, the verification module 83 is also used to determine that the repositioning has failed if the proportion of the abnormal grid is greater than the maximum abnormal point proportion threshold, or the proportion of the abnormal light beam is greater than the maximum abnormal light proportion threshold; or, if the minimum matching ratio is greater than or equal to the first matching threshold and the maximum matching ratio is less than or equal to the third matching ratio, and at the same time the proportion of the abnormal grid is greater than the minimum abnormal point proportion threshold or the proportion of the abnormal light beam is greater than the minimum abnormal light proportion threshold, then the repositioning has failed, and the third matching threshold is greater than the first matching threshold and less than the second matching threshold.

[0173] Figure 8 The relocation result verification device of the illustrated embodiment can be used to execute the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effect are similar and will not be described in detail here.

[0174] Fig. 9 Schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. The electronic device may be a self-moving device as described in the above embodiment. The electronic device provided in an embodiment of the present disclosure may execute the processing flow provided in the embodiment of the relocation result verification method, such as Fig. 9 As shown, the electronic device 90 includes: a memory 91, a processor 92, a computer program and a communication interface 93; wherein the computer program is stored in the memory 91 and is configured so that the processor 92 executes the relocation result verification method as described above.

[0175] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement the relocation result verification method described in the above embodiment.

[0176] In addition, an embodiment of the present disclosure further provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the relocation result verification method as described above is implemented.

[0177] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0178] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A relocation result verification method, applied to a self-moving device, the method include: Obtaining an environment map and relocation information from a mobile device, wherein the relocation information includes laser point cloud data obtained by the mobile device at the time of relocation by laser scanning the surrounding environment by emitting a laser beam; Characterized in that the method further comprises: Matching the laser point cloud data with the environment map to obtain an abnormal light beam passing through an obstacle in the environment map; obtaining an abnormal grid on the opposite side of the obstacle relative to the self-moving device based on the abnormal light beam; Determine the abnormal grid ratio and abnormal beam ratio corresponding to the laser point cloud data; According to the abnormal grid proportion and the abnormal light beam proportion, the data of the relocation information is verified to determine the relocation result.

2. The method according to claim 1, It is characterized in that The method further comprises: Obtaining laser sensor parameters of the self-mobile device; According to the laser point cloud data and the laser sensor parameters of the self-moving device, the laser scanning range corresponding to the laser point cloud data is calculated, and the laser scanning range is the range between the nearest scanning point and the farthest scanning point corresponding to each laser point in the laser point cloud data.

3. The method according to claim 2, It is characterized in that The laser sensor parameters include a minimum measurement distance and a maximum measurement distance of the laser sensor, and the step of calculating a laser scanning range corresponding to the laser point cloud data according to the laser point cloud data and the laser sensor parameters of the self-mobile device includes: Determine the scanning distance of each laser point in the laser point cloud data; Determining the relative error of each laser point according to the scanning distance of each laser point and the laser sensor parameters of the self-moving device; The laser scanning range corresponding to the laser point cloud data is determined according to the scanning distance of each laser point, the relative error of each laser point, the minimum measuring distance of the laser sensor and the maximum measuring distance of the laser sensor.

4. The method according to claim 2, It is characterized in that Matching the laser point cloud data with the environment map to determine the abnormal grid proportion corresponding to the laser point cloud data includes: Matching the laser point cloud data with the environment map, and if a laser beam corresponding to a laser point passes through an obstacle in the environment map, determining that the laser beam is an abnormal beam; The number of normal grids, the number of nearest abnormal grids, and the number of farthest abnormal grids passed by the abnormal light beam are counted according to the laser point cloud data, wherein the normal grid is a grid located between the self-moving device and the obstacle among the grids passed by the abnormal light beam, the nearest abnormal grid is a grid located between the obstacle and the nearest scanning point among the grids passed by the abnormal light beam, and the farthest abnormal grid is a grid located between the obstacle and the farthest scanning point among the grids passed by the abnormal light beam; According to the number of normal grids, the number of nearest abnormal grids and the number of farthest abnormal grids contained in the laser point cloud data, the proportion of abnormal grids corresponding to the laser point cloud data is determined.

5. The method according to claim 4, It is characterized in that Determining the proportion of abnormal grids corresponding to the laser point cloud data according to the number of normal grids, the number of nearest abnormal grids, and the number of farthest abnormal grids contained in the laser point cloud data includes: Determine the nearest grid number based on the normal grid number and the nearest abnormal grid number; Determine the farthest grid number according to the normal grid number and the farthest abnormal grid number; Calculating the ratio of the number of nearest abnormal grids in the laser point cloud data to the number of nearest grids to obtain the nearest abnormal grid ratio; Calculating the ratio of the farthest abnormal grid number in the laser point cloud data to the farthest grid number to obtain the farthest abnormal grid ratio; The smaller value between the nearest abnormal grid ratio and the farthest abnormal grid ratio is taken as the abnormal grid ratio.

6. The method according to claim 1, It is characterized in that Matching the laser point cloud data with the environment map to determine the abnormal light beam proportion includes: Matching the laser point cloud data with the environment map, and if a laser beam corresponding to a laser point passes through an obstacle in the environment map, determining that the laser beam is an abnormal beam; Calculate the ratio of the number of nearest abnormal beams to the number of laser beams to obtain the nearest abnormal beam ratio, wherein the nearest abnormal beam is an abnormal beam passing through a normal grid, a nearest abnormal grid, and a farthest abnormal grid; Calculate the ratio of the number of the farthest abnormal beams to the number of laser beams to obtain the farthest abnormal beam ratio, wherein the farthest abnormal beam is an abnormal beam that passes through a normal grid and a farthest abnormal grid; The smaller one of the nearest abnormal beam ratio and the farthest abnormal beam ratio is taken as the abnormal beam ratio.

7. The method according to claim 1, It is characterized in that Before verifying the relocation result according to the abnormal grid proportion and the abnormal beam proportion, the method further includes: Matching the laser point cloud data with the environment map to determine a matching score between each laser point in the laser point cloud data and an obstacle in the environment map; Determine a minimum matching ratio and a maximum matching ratio between the laser point cloud data and the environment map according to the matching score of each laser point; Whether the relocation result is successful is determined according to the minimum matching ratio and the maximum matching ratio.

8. The method according to claim 7, It is characterized in that The verifying the relocation result according to the abnormal grid proportion and the abnormal beam proportion comprises: If the abnormal grid ratio is greater than the maximum abnormal point ratio threshold, or the abnormal light beam ratio is greater than the maximum abnormal light beam ratio threshold, it is determined that the relocation fails; or, If the minimum matching ratio is greater than or equal to the first matching threshold and the maximum matching ratio is less than or equal to the third matching ratio, and at the same time the abnormal grid proportion is greater than the minimum abnormal point proportion threshold or the abnormal light beam proportion is greater than the minimum abnormal light beam proportion threshold, then it is determined that the repositioning has failed, and the third matching threshold is greater than the first matching threshold and less than the second matching threshold.

9. A relocation result verification method, applied to a self-moving device, the method include: Obtaining an environment map and relocation information from a mobile device, wherein the relocation information includes laser point cloud data obtained by the mobile device at the time of relocation by laser scanning the surrounding environment by emitting a laser beam; Characterized in that the method further comprises: Matching the laser point cloud data with the environment map to obtain an abnormal light beam passing through an obstacle in the environment map; obtaining an abnormal grid on the opposite side of the obstacle relative to the self-moving device based on the abnormal light beam; Determine the abnormal grid proportion corresponding to the laser point cloud data; According to the abnormal grid ratio, the data of the relocation information is verified to determine the relocation result.

10. A relocation result verification method, applied to a mobile device, the method include: Obtaining an environment map and relocation information from a mobile device, wherein the relocation information includes laser point cloud data obtained by the mobile device at the time of relocation by laser scanning the surrounding environment by emitting a laser beam; Characterized in that the method further comprises: Matching the laser point cloud data with the environment map to obtain an abnormal light beam passing through an obstacle in the environment map; Determine the proportion of abnormal light beams corresponding to the laser point cloud data; According to the abnormal light beam proportion, the data of the relocation information is verified to determine the relocation result.

Images