Mobile robot and its threshold recognition method, device and storage medium

Abstract

The present invention discloses a mobile robot, as well as a threshold recognition method, device and storage medium thereof. The method includes the following steps: obtaining first point cloud data of a first target object at a first preset height, and obtaining second point cloud data of a second target object at a second preset height, wherein the first preset height is set corresponding to the threshold height, and the second preset height is greater than the first preset height; performing endpoint extraction processing on the first point cloud data and the second point cloud data to respectively obtain a first endpoint and a second endpoint; recognizing the threshold according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint. Thus, endpoint extraction processing is performed on point cloud data at different heights, and the threshold is recognized according to the endpoint coordinate information. Therefore, the mobile robot can recognize the threshold at a long distance without crossing or approaching the threshold, increasing the buffer response time of the mobile robot.

Description

Technical Field

[0001] The present invention relates to the technical field of mobile robots, and in particular, to a method for identifying thresholds of a mobile robot, a computer-readable storage medium, a mobile robot, and a threshold identification device for a mobile robot. Background Art

[0002] Currently, robot threshold recognition technology can already accurately recognize threshold features, but there is still a problem, that is, the efficiency problem.

[0003] Taking a floor sweeper in the prior art as an example, the threshold recognition technology usually adopts the following two methods: one is physical detection, that is, by setting a height limit for the floor sweeper to cross, and if it crosses, it is a threshold. However, this method has poor perception of the surrounding environment and cannot detect the threshold in advance. The other is to combine limited sensing technology and physical methods to analyze the characteristics of obstacles in order to distinguish thresholds from general obstacles. However, due to the small recognition range of this method, it has a slow response to road changes and has a certain trial-and-error cost. Summary of the Invention

[0004] The present invention aims to at least solve one of the technical problems in the related art to some extent. For this purpose, the first object of the present invention is to propose a method for a mobile robot that can perform endpoint extraction processing on point cloud data at different heights and identify thresholds based on endpoint coordinate information. Thus, the mobile robot can identify thresholds at a long distance without crossing or approaching the threshold, increasing the buffer response time of the mobile robot.

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

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

[0007] The fourth object of the present invention is to propose a threshold identification device for a mobile robot.

[0008] To achieve the above object, the threshold recognition method for a mobile robot proposed in the first aspect embodiment of the present invention includes: obtaining first point cloud data of a first target object at a first preset height, and obtaining second point cloud data of a second target object at a second preset height, where the first preset height is set corresponding to the threshold height, and the second preset height is greater than the first preset height; performing endpoint extraction processing on the first point cloud data and the second point cloud data to respectively obtain a first endpoint and a second endpoint; and identifying the threshold according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint.

[0009] The threshold recognition method of a mobile robot according to an embodiment of the present invention includes obtaining first point cloud data of a first target object at a first preset height and obtaining second point cloud data of a second target object at a second preset height, where the first preset height is set corresponding to the threshold height, the second preset height is greater than the first preset height, and endpoint extraction processing is performed on the first point cloud data and the second point cloud data to respectively obtain a first endpoint and a second endpoint. Further, the threshold is recognized according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint. Thus, endpoint extraction processing is performed on point cloud data at different heights, and the threshold is recognized according to the endpoint coordinate information. Therefore, the mobile robot can recognize the threshold at a long distance without crossing or approaching the threshold, increasing the buffer response time of the mobile robot.

[0010] In addition, the threshold recognition method of the mobile robot according to an embodiment of the present invention may further have the following additional technical features:

[0011] According to an embodiment of the present invention, the first point cloud data is scanned and obtained by a first detection unit at the first preset height; and the second point cloud data is scanned and obtained by a second detection unit at the second preset height.

[0012] According to an embodiment of the present invention, the first detection unit scans the first target object at the first preset height by a laser detection method, and the second detection unit scans the second target object at the second preset height by the laser detection method.

[0013] According to an embodiment of the present invention, the first detection unit is a line laser ranging device and is set corresponding to the first preset height, and the second detection unit is at least one of the line laser ranging device, the point laser ranging device, and the surface laser ranging device and is set corresponding to the second preset height.

[0014] According to an embodiment of the present invention, the first detection unit is the line laser ranging device, and the second detection unit is the point laser ranging device. Wherein, performing endpoint extraction processing on the first point cloud data and the second point cloud data includes: generating a laser line segment according to the first point cloud data, and performing endpoint extraction processing on both ends of the laser line segment to obtain the first endpoint; and performing clustering operation on the second point cloud data to generate a clustering line segment corresponding to the second point cloud data, and performing endpoint extraction processing on both ends of the clustering line segment corresponding to the second point cloud data to obtain the second endpoint.

[0015] According to an embodiment of the present invention, identifying a threshold based on the first coordinate information of the first endpoint and the second coordinate information of the second endpoint includes: performing coordinate transformation on the first endpoint and the second endpoint so that the first coordinate information and the second coordinate information are in the same coordinate system; identifying a threshold based on the first coordinate information and the second coordinate information in the same coordinate system.

[0016] According to an embodiment of the present invention, identifying a threshold based on the first coordinate information and the second coordinate information in the same coordinate system includes: determining, based on the first coordinate information of the first endpoint and the second coordinate information of the second endpoint, whether at least one of the second endpoints is on the line segment formed by the first endpoints; if at least one of the second endpoints is on the line segment formed by the first endpoints, then identifying the first target object as the threshold.

[0017] According to an embodiment of the present invention, identifying a threshold based on the first coordinate information and the second coordinate information in the same coordinate system further includes: if none of the second endpoints is on the line segment formed by the first endpoints, then further determining whether all of the first endpoints are on the line segment formed by the second endpoints, or determining whether the first endpoints are between multiple line segments formed by the second endpoints; if all of the first endpoints are on the line segment formed by the second endpoints, then identifying the first target object as a wall, and if the first endpoints are between multiple line segments formed by the second endpoints, then identifying the first target object as a threshold.

[0018] According to an embodiment of the present invention, after identifying the first target object as a threshold, the method for the mobile robot to identify a threshold further includes: obtaining the third point cloud data of the third target object at a third preset height, where the third preset height is greater than the second preset height; performing endpoint extraction processing on the third point cloud data to obtain third endpoints; determining whether to control the mobile robot to continue moving forward based on the first coordinate information of the first endpoints and the third coordinate information of the third endpoints.

[0019] According to an embodiment of the present invention, performing endpoint extraction processing on the third point cloud data includes: performing clustering operation on the third point cloud data to generate clustering line segments corresponding to the third point cloud data, and performing endpoint extraction processing on both ends of the clustering line segments corresponding to the third point cloud data to obtain the third endpoints.

[0020] According to an embodiment of the present invention, determining whether to control the mobile robot to continue moving according to the first coordinate information of the first endpoint and the third coordinate information of the third endpoint includes: performing coordinate transformation on the first endpoint and the third endpoint so that the first coordinate information and the third coordinate information are in the same coordinate system; determining whether the first endpoint is located on the line segment formed by the third endpoint according to the first coordinate information of the first endpoint and the third coordinate information of the third endpoint in the same coordinate system; if the first endpoint is located on the line segment formed by the third endpoint, identifying the third target object as a door beam, controlling the mobile robot to stop moving forward, and performing turning.

[0021] According to an embodiment of the present invention, the third detection unit point is at least one of a line laser ranging device, a point laser ranging device, and a surface laser ranging device, and is set corresponding to the third preset height.

[0022] To achieve the above object, a computer-readable storage medium proposed by the second aspect embodiment of the present invention stores a threshold recognition program for a mobile robot. When the threshold recognition program for the mobile robot is executed by a processor, the threshold recognition method for the mobile robot is as described above.

[0023] The computer-readable storage medium proposed by the embodiment of the present invention can perform endpoint extraction processing on point cloud data of different heights and perform threshold recognition according to endpoint coordinate information. Thus, the mobile robot can remotely recognize the threshold without crossing or approaching the threshold, increasing the buffer response time of the mobile robot.

[0024] To achieve the above object, a mobile robot proposed by the third aspect embodiment of the present invention includes a memory, a processor, and a threshold recognition program for the mobile robot stored in the memory and executable on the processor. When the processor executes the threshold recognition program for the mobile robot, the threshold recognition method for the mobile robot as described above is implemented.

[0025] The mobile robot proposed by the embodiment of the present invention can perform endpoint extraction processing on point cloud data of different heights and perform threshold recognition according to endpoint coordinate information. Thus, the mobile robot can remotely recognize the threshold without crossing or approaching the threshold, increasing the buffer response time of the mobile robot.

[0026] To achieve the above object, the present invention provides a threshold recognition device for a mobile robot according to a fourth aspect. The device includes: an acquisition module configured to acquire first point cloud data of a first target object at a first preset height and second point cloud data of a second target object at a second preset height, where the first preset height is set corresponding to the threshold height and the second preset height is greater than the first preset height; an endpoint extraction module configured to perform endpoint extraction processing on the first point cloud data and the second point cloud data to obtain a first endpoint and a second endpoint respectively; and a recognition module configured to recognize the threshold according to first coordinate information of the first endpoint and second coordinate information of the second endpoint.

[0027] According to the threshold recognition device of the mobile robot in an embodiment of the present invention, the acquisition module acquires first point cloud data of a first target object at a first preset height and second point cloud data of a second target object at a second preset height, where the first preset height is set corresponding to the threshold height, the second preset height is greater than the first preset height, and the endpoint extraction module performs endpoint extraction processing on the first point cloud data and the second point cloud data to obtain a first endpoint and a second endpoint respectively. Further, the recognition module recognizes the threshold according to first coordinate information of the first endpoint and second coordinate information of the second endpoint. Thus, endpoint extraction processing is performed on point cloud data at different heights, and the threshold is recognized according to the endpoint coordinate information. Therefore, the mobile robot can recognize the threshold from a distance without crossing or approaching the threshold, can recognize the threshold in advance while the mobile robot is moving at a high speed, increases the buffer response time of the mobile robot, and is beneficial to the path planning and reasonable crossing of the threshold by the mobile robot. In addition, the method of recognizing the threshold using the coordinate information of the first endpoint and the second endpoint does not require complex calculations, is simple and convenient to calculate, has a high accuracy rate, can greatly reduce the amount of computation, and reduce the load and power consumption of the chip.

[0028] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flowchart of a threshold recognition method for a mobile robot according to an embodiment of the present invention;

[0030] Figure 2 is a schematic diagram of the setting manner of a detection unit of a mobile robot according to a specific embodiment of the present invention;

[0031] Figure 3 is a flowchart of a threshold recognition method for a mobile robot according to an embodiment of the present invention;

[0032] Figure 4 It is a schematic flowchart of a threshold recognition method for a mobile robot according to an embodiment of the present invention;

[0033] Figure 5 It is a schematic diagram of the position distribution of laser line segments and clustered point line segments according to a specific embodiment of the present invention;

[0034] Figure 6 It is a schematic flowchart of a threshold recognition method for a mobile robot according to an embodiment of the present invention;

[0035] Figure 7 It is a schematic diagram of the position distribution of laser line segments and clustered point line segments according to a specific embodiment of the present invention;

[0036] Figure 8 It is a schematic diagram of the position distribution of laser line segments and clustered point line segments according to a specific embodiment of the present invention;

[0037] Figure 9 It is a schematic flowchart of a threshold recognition method for a mobile robot according to an embodiment of the present invention;

[0038] Figure 10 It is a schematic flowchart of a threshold recognition method for a mobile robot according to an embodiment of the present invention;

[0039] Figure 11 It is a schematic diagram of the position distribution of laser line segments and clustered point line segments according to a specific embodiment of the present invention;

[0040] Figure 12 It is a schematic block diagram of a threshold recognition device for a mobile robot according to an embodiment of the present invention. Detailed Embodiments

[0041] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present invention, but should not be construed as limiting the present invention.

[0042] The threshold recognition method, computer-readable storage medium, mobile robot, and threshold recognition device for a mobile robot according to an embodiment of the present invention will be described below with reference to the accompanying drawings.

[0043] Figure 1 It is a schematic flowchart of a threshold recognition method for a mobile robot according to an embodiment of the present invention.

[0044] As Figure 1 shown, the threshold recognition method for a mobile robot includes the following steps:

[0045] S101, obtain the first point cloud data of the first target object at a first preset height, and obtain the second point cloud data of the second target object at a second preset height, where the first preset height corresponds to the threshold height setting, and the second preset height is greater than the first preset height.

[0046] It can be understood that the first target object can be an obstacle or an object to be scanned corresponding to the first preset height, such as a threshold, and the second target object can be an obstacle or an object to be scanned corresponding to the second preset height, such as a wall.

[0047] Specifically, in an embodiment of the present invention, the first point cloud data can be obtained by scanning at the first preset height by a first detection unit, and the second point cloud data can be obtained by scanning at the second preset height by a second detection unit.

[0048] More specifically, in the embodiment of the present invention, the first detection unit can be a line laser ranging device and can be set corresponding to the first preset height. For example, if the first preset height of the threshold is 2 cm, the installation height of the first detection unit can be set to a height of 2 cm or less from the ground, or can be higher than the threshold height, such as a height of 3 cm or 10 cm from the ground, or other heights greater than 2 cm. There is no limitation here as long as the threshold can be detected. The second detection unit can be at least one of a line laser ranging device, a point laser ranging device, and a surface laser ranging device, and can be set corresponding to the second preset height. For example, if the installation height of the first detection unit is 2 cm from the ground, the installation height of the second detection unit can be set to a height of 3 cm or 10 cm from the ground, or other heights greater than 2 cm. There is no limitation here as long as the installation height of the second detection unit can detect the wall or other obstacles at the second preset height, so that the first detection unit can scan the first target object at the first preset height by laser detection, and the second detection unit can scan the second target object at the second preset height by laser detection. In other words, the first detection unit set corresponding to the first preset height is used to obtain the first point cloud data at the low scanning height, and the second detection unit set corresponding to the second preset height is used to obtain the second point cloud data at the medium scanning height.

[0049] It should be understood that the first detection unit is set as a line laser ranging device. The laser of this line laser ranging device is emitted obliquely downward, and its light on the threshold and other first target objects is displayed as a horizontal line segment. This horizontal line segment has direct start and end points, which is beneficial to reducing subsequent endpoint extraction steps, reducing the amount of calculation, and improving the calculation speed. Moreover, the laser angle and visible distance of the line laser emission can control the detected distance, and can be flexibly adjusted according to the threshold height to detect the threshold. Correspondingly, the installation height of this line laser ranging device can be the same as the installation height of the second detection unit, which is not limited here.

[0050] Meanwhile, in order to improve the accuracy of the second detection unit in scanning the second target object, in the embodiment of the present invention, as Figure 2 shown, the second detection unit can preferably be a point laser ranging device. Among them, the height scanning range of the point laser ranging device is greater than the height scanning range of the line laser ranging device to detect a larger height range.

[0051] In addition, in an embodiment not shown in the present invention, the first detection unit and the second detection unit can also scan the first target object at the first preset height and the second target object at the second preset height through other detection methods such as ultrasonic detection or camera detection.

[0052] S102, perform endpoint extraction processing on the first point cloud data and the second point cloud data to respectively obtain a first endpoint and a second endpoint.

[0053] Specifically, the first detection unit is a line laser ranging device, and the second detection unit is a point laser ranging device. Among them, as shown in the figure, performing endpoint extraction processing on the first point cloud data and the second point cloud data includes:

[0054] Generate a laser line segment according to the first point cloud data, and perform endpoint extraction processing on both ends of the laser line segment to obtain the first endpoint.

[0055] It should be understood that since the first detection unit is a line laser ranging device, therefore, the first point cloud data has the characteristic of linearity, and a corresponding laser line segment can be directly generated. Furthermore, the first endpoint can be obtained by performing endpoint extraction processing on both ends of the laser line segment. Among them, the first endpoint includes the start and end points of the laser line segment.

[0056] And perform clustering operation on the second point cloud data to generate a clustering line segment corresponding to the second point cloud data, and perform endpoint extraction processing on both ends of the clustering line segment corresponding to the second point cloud data to obtain the second endpoint.

[0057] It should be understood that when the second detection unit is a non-linear laser ranging device, since the second point cloud data does not have the characteristic of linearity and cannot directly generate the corresponding laser line segment, it is necessary to first perform a clustering operation on the second point cloud data to generate a clustering line segment corresponding to the second point cloud data, and then perform endpoint extraction processing on both ends of the clustering line segment corresponding to the second point cloud data to obtain the second endpoints. Among them, the second endpoints include the head and tail endpoints of the clustering line segment. For example, the distance between each clustering point in the clustering line segment corresponding to the second point cloud data can be calculated to determine the two clustering points with the largest distance as the second endpoints.

[0058] Optionally, in the embodiments of the present invention, the clustering operation on the second point cloud data can be performed based on the Euclidean distance, or the clustering operation on the second point cloud data can be performed based on the density.

[0059] S103, identify the threshold according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint.

[0060] Thus, in the embodiments of the present invention, the first target object can be scanned by the line laser ranging device set at the first preset height, and the second target object can be scanned by the point laser ranging device set at the second preset height to obtain the point cloud data at different preset heights, and the endpoint extraction processing is performed on the point cloud data to identify the threshold according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint. Therefore, the mobile robot can remotely identify the threshold without crossing or approaching the threshold, and can identify the threshold in advance while the mobile robot is moving at a high speed, increasing the buffer response time of the mobile robot, which is beneficial to the path planning and reasonable crossing of the threshold by the mobile robot. In addition, the method of identifying the threshold using the coordinate information of the first endpoint and the second endpoint does not require complex calculations, is simple and convenient to calculate, and has a high accuracy rate, which can greatly reduce the amount of calculation, reduce the load and power consumption of the chip.

[0061] Furthermore, as Figure 3 shown, identifying the threshold according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint includes:

[0062] S201, perform coordinate transformation on the first endpoint and the second endpoint to make the first coordinate information and the second coordinate information in the same coordinate system.

[0063] It should be understood that since the point cloud data collected by the line laser ranging device, the point laser ranging device, and the surface laser ranging device are polar coordinate data, therefore, in the embodiments of the present invention, in order to further simplify the data calculation amount of the mobile robot, coordinate conversion can also be performed on the first endpoint and the second endpoint so that the first coordinate information and the second coordinate information are in the same coordinate system. For example, both the first point cloud data and the second point cloud data are converted into Cartesian coordinate data.

[0064] S202, identify the threshold according to the first coordinate information and the second coordinate information in the same coordinate system.

[0065] The following combines the attached Figures 4 - 11 and the specific embodiments of the present invention to make corresponding descriptions of the specific implementation manners of the identified threshold.

[0066] As Figure 4 shown, identifying the threshold according to the first coordinate information and the second coordinate information in the same coordinate system includes:

[0067] S301, according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint, determine whether at least one second endpoint is located on the line segment formed by the first endpoints.

[0068] For example, taking the head endpoint of the laser line segment in the first endpoints as the coordinate origin and the laser line segment as the coordinate x-axis, a Cartesian coordinate system is constructed, and the second coordinate information of the second endpoint is vertically projected onto the coordinate x-axis corresponding to the first coordinate information of the first endpoint to determine whether the second endpoint is located on the line segment formed by the first endpoints. At this time, if the x-axis coordinate corresponding to the projected second endpoint is between the x-axis coordinate of the head endpoint of the laser line segment and the x-axis coordinate of the tail endpoint of the laser line segment, it can be determined that at least one second endpoint is located on the line segment formed by the first endpoints; otherwise, it can be determined that the second endpoint is not located on the line segment formed by the first endpoints.

[0069] Taking either endpoint of the second endpoint as an example, assume that the first coordinate information of the first endpoint corresponds to the head endpoint (0, 0) and the tail endpoint (X1, 0) respectively, and the second coordinate information of the second endpoint corresponds to (X21, Y21). At this time, the second coordinate information of the second endpoint can be vertically projected onto the x-axis of the coordinate to determine whether the second endpoint is located on the line segment formed by the first endpoints. For example, assume that the x-axis coordinate X21 corresponding to the second coordinate information of the second endpoint after vertical projection is on the left side of the first coordinate information (such as the x-axis coordinate 0, that is, the coordinate origin) of the first endpoint, or the x-axis coordinate X21 corresponding to the second coordinate information of the second endpoint after vertical projection is on the right side of the first coordinate information (such as the x-axis coordinate X1) of the first endpoint. Then, it can be determined that the second endpoint is not located on the line segment formed by the first endpoints. Another example, assume that the x-axis coordinate X21 corresponding to the second coordinate information of the second endpoint after vertical projection is between the x-axis coordinates 0 and X1 of the first coordinate information of the first endpoint. Then, it can be determined that at least one second endpoint is located on the line segment formed by the first endpoints.

[0070] S302, if at least one second endpoint is located on the line segment formed by the first endpoints, then identify the first target object as a threshold.

[0071] It should be understood that if at least one second endpoint is located on the line segment formed by the first endpoints, as Figure 5 shown, at this time, it can be determined that the first point cloud data obtained by scanning by the first detection unit is the first point cloud data corresponding to the junction of the wall and the threshold, and the second point cloud data obtained by scanning by the second detection unit is the second point cloud data corresponding to the wall. Therefore, the mobile robot can identify the first target object as a threshold.

[0072] Furthermore, as Figure 6 shown, identifying the threshold according to the first coordinate information and the second coordinate information in the same coordinate system further includes:

[0073] S401, if none of the second endpoints are located on the line segment formed by the first endpoints, then further determine whether all of the first endpoints are located on the line segment formed by the second endpoints, or determine whether the first endpoints are located between multiple line segments formed by the second endpoints.

[0074] Similarly, taking the starting point of the laser line segment in the first endpoint as the coordinate origin and the laser line segment as the x-axis of the coordinate system, a Cartesian coordinate system is constructed, and the first coordinate information of the first endpoint is vertically projected onto the x-axis corresponding to the second coordinate information of the second endpoint to further determine whether all the first endpoints are located on the line segment formed by the second endpoints, or to determine whether the first endpoints are located between multiple line segments formed by the second endpoints. At this time, if the x-axis coordinates corresponding to the projected first endpoints are all between the x-axis coordinate of the starting point of the clustered line segment and the x-axis coordinate of the ending point of the clustered line segment, it can be determined that all the first endpoints are located on the line segment formed by the second endpoints, and if the x-axis coordinates corresponding to the projected first endpoints are between the x-axis coordinate of the ending point of one clustered line segment and the x-axis coordinate of the starting point of another clustered line segment, it can be determined that the first endpoints are located between multiple line segments formed by the second endpoints.

[0075] Taking the starting and ending points of the first endpoint as an example for illustration, assume that the first coordinate information of the first endpoint corresponds to (0, 0) and (X1, 0), and the second coordinate information of the second endpoints corresponds to (X21, Y), (X22, Y), (X23, Y), (X24, Y) respectively. Taking (X21, Y) and (X22, Y) as the starting and ending points to form the first clustered line segment, and taking (X23, Y) and (X24, Y) as the starting and ending points to form the second clustered line segment. At this time, the first coordinate information of the first endpoint can be vertically projected onto the first clustered line segment or the second clustered line segment to determine whether all the first endpoints are located on the line segment formed by the second endpoints. For example, assume that the x-axis coordinates 0 and X1 of the vertically projected first coordinate information are both between X21 and X22, or the x-axis coordinates 0 and X1 of the first coordinate information are both between X23 and X24, then it can be determined that all the first endpoints are located on the line segment formed by the second endpoints. Another example, assume that the x-axis coordinate 0 or X1 of the vertically projected first coordinate information is between X23 and X24, then it can be determined that the first endpoints are located between multiple line segments formed by the second endpoints.

[0076] S402, if all the first endpoints are located on the line segment formed by the second endpoints, then identify the first target object as a wall, and if the first endpoints are located between multiple line segments formed by the second endpoints, then identify the first target object as a threshold.

[0077] It should be understood that if all the first endpoints are located on the line segment formed by the second endpoints, as Figure 7 shown, at this time, it can be determined that the first point cloud data obtained by scanning by the first detection unit is the first point cloud data corresponding to the wall, and the second point cloud data obtained by scanning by the second detection unit is the second point cloud data corresponding to the wall. Therefore, the mobile robot can identify the first target object as a wall.

[0078] And if the first endpoints are located between multiple line segments formed by the second endpoints, asFigure 8 As shown, at this time, it can be determined that the first point cloud data obtained by the first detection unit scanning is the first point cloud data corresponding to the threshold, and the second point cloud data obtained by the second detection unit scanning is the second point cloud data corresponding to the wall. Therefore, the mobile robot can identify the first target object as the threshold.

[0079] Further, as Figure 9 shown, after identifying the first target object as the threshold, the threshold recognition method of the mobile robot further includes:

[0080] S501, obtaining the third point cloud data of the third target object at the third preset height, where the third preset height is greater than the second preset height.

[0081] It can be understood that the third target object can be an obstacle or an object to be scanned corresponding to the third preset height. At this time, when the overall height of the mobile robot is relatively high, for example, if the overall height of the mobile robot is set to 70 cm, during the movement of the mobile robot, it may hit an obstacle less than or equal to 70 cm, such as a door beam.

[0082] Specifically, in an embodiment of the present invention, the third point cloud data can be obtained by the third detection unit scanning at the third preset height.

[0083] More specifically, in the embodiment of the present invention, the third detection unit can be at least one of a line laser ranging device, a point laser ranging device, and a surface laser ranging device, and is set corresponding to the third preset height. For example, the installation height of the second detection unit is 30 cm from the ground. In this embodiment, the installation height of the second detection unit can be set to 40 cm or 50 cm from the ground, or other heights greater than 30 cm, which is not limited here. As long as the installation height of the third detection unit can detect the wall or other obstacles at the third preset height, and the installation height of the third detection unit is higher than the installation height of the second detection unit, it is okay, so that the third detection unit can scan the third target object at the third preset height by laser detection and implement the corresponding obstacle avoidance strategy. In other words, the third detection unit set corresponding to the third preset height is used to obtain the third point cloud data of the high scanning height.

[0084] It should be understood that, in order to improve the accuracy of the third detection unit scanning the third target object, in the embodiment of the present invention, as Figure 2 shown, the third detection unit can preferably be a surface laser ranging device, where the height scanning range of the surface laser ranging device is greater than the height scanning range of the point laser ranging device to detect a larger height range, so that during the movement, it can ensure that the obstacles corresponding to the overall height range of the mobile robot can be detected and recognized, and prevent the mobile robot from colliding with the obstacles.

[0085] In addition, in embodiments not shown in the present invention, the third detection unit may also scan the third target object at the third preset height through other detection methods such as ultrasonic detection or camera detection.

[0086] S502. Perform endpoint extraction processing on the third point cloud data to obtain third endpoints.

[0087] Specifically, performing endpoint extraction processing on the third point cloud data includes: performing clustering operation on the third point cloud data to generate clustering line segments corresponding to the third point cloud data, and performing endpoint extraction processing on both ends of the clustering line segments corresponding to the third point cloud data to obtain third endpoints.

[0088] It can be understood that the specific implementation manner of extracting the third endpoints in the embodiments of the present invention corresponds to the specific implementation manner of extracting the second endpoints described above. To reduce redundancy, it will not be elaborated here.

[0089] S503. Determine whether to control the mobile robot to continue moving forward according to the first coordinate information of the first endpoint and the third coordinate information of the third endpoint.

[0090] Specifically, as Figure 10 shown, determining whether to control the mobile robot to continue moving forward according to the first coordinate information of the first endpoint and the third coordinate information of the third endpoint includes:

[0091] S601. Perform coordinate transformation on the first endpoint and the third endpoint so that the first coordinate information and the third coordinate information are in the same coordinate system.

[0092] It should be understood that since the point cloud data collected by the line laser ranging device, the point laser ranging device, and the surface laser ranging device is polar coordinate system data, therefore, in the embodiments of the present invention, to further simplify the data calculation amount of the mobile robot, coordinate transformation can also be performed on the first endpoint and the third endpoint so that the first coordinate information and the third coordinate information are in the same coordinate system. For example, both the first point cloud data and the third point cloud data are converted into Cartesian coordinate system data.

[0093] S602. Determine whether the first endpoint is located on the line segment formed by the third endpoints according to the first coordinate information of the first endpoint and the third coordinate information of the third endpoint in the same coordinate system.

[0094] It should be noted that the specific implementation manner of making the first coordinate information and the third coordinate information in the same coordinate system in the embodiments of the present invention corresponds to the specific implementation manner of making the first coordinate information and the second coordinate information in the same coordinate system described above, and the specific implementation manner of determining whether the first endpoints are all located on the line segment formed by the third endpoints in the embodiments of the present invention corresponds to the specific implementation manner of determining whether the first endpoints are all located on the line segment formed by the second endpoints described above. To reduce redundancy, they will not be elaborated here.

[0095] S603. If the first endpoints are all located on the line segment formed by the third endpoints, then identify the third target object as the door beam, control the mobile robot to stop moving forward, and perform a turn.

[0096] It should be understood that if the first endpoints are all located on the line segment formed by the third endpoints, as Figure 11 shown, at this time, it can be determined that the first point cloud data scanned by the first detection unit is the first point cloud data corresponding to the threshold, and the third point cloud data scanned by the third detection unit is the third point cloud data corresponding to the door beam. Therefore, the mobile robot can identify the third target object as the door beam. At this time, the mobile robot can be controlled to stop moving forward and perform a turn to avoid the mobile robot colliding with the door beam.

[0097] It should be noted that in the embodiments of the present invention, after obtaining the first coordinate information of the first endpoints, the second coordinate information of the second endpoints, and the third coordinate information of the third endpoints, the first coordinate information of the first endpoints can also be pre-stored in the memory space of the first detection unit, the second endpoints can be pre-stored in the memory space of the second detection unit, and the third endpoints can be pre-stored in the memory space of the third detection unit.

[0098] In addition, in the embodiments of the present invention, in combination with the coordinate offset threshold, it can also be determined whether at least one of the second endpoints is located on the line segment formed by the first endpoints, whether the first endpoints are all located on the line segment formed by the second endpoints, or whether the first endpoints are located between multiple line segments formed by the second endpoints, and whether the first endpoints are all located on the line segment formed by the third endpoints, so as to avoid misidentifying some obstacles outside or inside the door as the threshold.

[0099] In summary, according to the threshold recognition method of the mobile robot proposed in the embodiments of the present invention, the first point cloud data of the first target object at the first preset height is obtained, and the second point cloud data of the second target object at the second preset height is obtained, wherein the first preset height is set corresponding to the threshold height, the second preset height is greater than the first preset height, and endpoint extraction processing is performed on the first point cloud data and the second point cloud data to respectively obtain a first endpoint and a second endpoint. Furthermore, the threshold is recognized according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint. Thus, endpoint extraction processing is performed on point cloud data at different heights, and the threshold is recognized according to the endpoint coordinate information. Therefore, the mobile robot can recognize the threshold at a long distance without crossing or approaching the threshold, and can recognize the threshold in advance while the mobile robot is moving at a high speed, increasing the buffer response time of the mobile robot, which is beneficial to the path planning and reasonable threshold crossing of the mobile robot. In addition, the method of recognizing the threshold using the coordinate information of the first endpoint and the second endpoint does not require complex calculations, is simple and convenient to calculate, and has a high accuracy rate, which can greatly reduce the amount of computation, reduce the load and power consumption of the chip.

[0100] Specifically, based on the threshold recognition method of the mobile robot in the foregoing embodiments of the present invention, the present invention also proposes a computer-readable storage medium, on which a threshold recognition program for the mobile robot is stored. When the threshold recognition program for the mobile robot is executed by a processor, the threshold recognition method of the mobile robot as described above is implemented.

[0101] It should be noted that when the computer-readable storage medium according to the embodiments of the present invention executes the threshold recognition program for the mobile robot, it can implement the specific implementation manners of the foregoing corresponding threshold recognition methods of the mobile robot, which will not be elaborated herein.

[0102] In summary, the computer-readable storage medium proposed according to the embodiments of the present invention can perform endpoint extraction processing on point cloud data at different heights and recognize the threshold according to the endpoint coordinate information. Therefore, the mobile robot can recognize the threshold at a long distance without crossing or approaching the threshold, increasing the buffer response time of the mobile robot.

[0103] Specifically, based on the threshold recognition method of the mobile robot in the foregoing embodiments of the present invention, the present invention also proposes a mobile robot, including a memory, a processor, and a threshold recognition program for the mobile robot stored on the memory and executable on the processor. When the processor executes the threshold recognition program for the mobile robot, the threshold recognition method of the mobile robot as described above is implemented.

[0104] It should be noted that when the mobile robot according to the embodiments of the present invention executes the threshold recognition program for the mobile robot, it can implement the specific implementation manners of the foregoing corresponding threshold recognition methods of the mobile robot, which will not be elaborated herein.

[0105] Optionally, the mobile robot may include a floor cleaning robot, a delivery robot, a food delivery robot, etc.

[0106] In addition, the other components and functions of the mobile robot according to the embodiments of the present invention are known to those skilled in the art. To reduce redundancy, they will not be described in detail herein.

[0107] In summary, the mobile robot proposed according to the embodiments of the present invention can perform endpoint extraction processing on point cloud data at different heights, and perform threshold recognition based on the endpoint coordinate information. Thus, the mobile robot can recognize the threshold at a long distance without crossing or approaching the threshold, increasing the buffer response time of the mobile robot.

[0108] Figure 12 It is a block diagram of a threshold recognition device of a mobile robot according to an embodiment of the present invention.

[0109] As Figure 12 shown, the threshold recognition device 100 of the mobile robot includes: an acquisition module 10, an endpoint extraction module 20, and a recognition module 30.

[0110] Specifically, the acquisition module 10 is configured to acquire first point cloud data of a first target object at a first preset height, and acquire second point cloud data of a second target object at a second preset height, where the first preset height is set corresponding to the threshold height, and the second preset height is greater than the first preset height; the endpoint extraction module 20 is configured to perform endpoint extraction processing on the first point cloud data and the second point cloud data to respectively obtain a first endpoint and a second endpoint; the recognition module 30 is configured to recognize the threshold according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint.

[0111] Further, the acquisition module 10 includes a first detection unit and a second detection unit. The first point cloud data is scanned by the first detection unit at the first preset height; and the second point cloud data is scanned by the second detection unit at the second preset height.

[0112] Further, the first detection unit scans the first target object at the first preset height by a laser detection method, and the second detection unit scans the second target object at the second preset height by a laser detection method.

[0113] Further, the first detection unit is a line laser ranging device and is set corresponding to the first preset height, and the second detection unit is at least one of a line laser ranging device, a point laser ranging device, and a surface laser ranging device and is set corresponding to the second preset height.

[0114] Further, the first detection unit is a line laser ranging device, and the second detection unit is a point laser ranging device. The endpoint extraction module 20 is further configured to generate a laser line segment based on the first point cloud data, perform endpoint extraction processing on both ends of the laser line segment to obtain a first endpoint; and perform a clustering operation on the second point cloud data to generate a clustering line segment corresponding to the second point cloud data, and perform endpoint extraction processing on both ends of the clustering line segment corresponding to the second point cloud data to obtain a second endpoint.

[0115] Further, the recognition module 30 is further configured to perform coordinate transformation on the first endpoint and the second endpoint so that the first coordinate information and the second coordinate information are in the same coordinate system; and recognize a threshold based on the first coordinate information and the second coordinate information in the same coordinate system.

[0116] Further, the recognition module 30 is further configured to determine, based on the first coordinate information of the first endpoint and the second coordinate information of the second endpoint, whether at least one second endpoint is located on the line segment formed by the first endpoints; if at least one second endpoint is located on the line segment formed by the first endpoints, then recognize the first target object as a threshold.

[0117] Further, the recognition module 30 is further configured to, if none of the second endpoints is located on the line segment formed by the first endpoints, further determine whether all of the first endpoints are located on the line segment formed by the second endpoints, or determine whether the first endpoints are located between multiple line segments formed by the second endpoints; if all of the first endpoints are located on the line segment formed by the second endpoints, then recognize the first target object as a wall, and if the first endpoints are located between multiple line segments formed by the second endpoints, then recognize the first target object as a threshold.

[0118] Further, the acquisition module 10 includes a third detection unit. The acquisition module 10 is further configured to, after recognizing the first target object as a threshold, acquire third point cloud data of a third target object at a third preset height, where the third preset height is greater than the second preset height; the endpoint extraction module 20 is further configured to perform endpoint extraction processing on the third point cloud data to obtain a third endpoint; the recognition module 30 is further configured to determine whether to control the mobile robot to continue moving forward based on the first coordinate information of the first endpoint and the third coordinate information of the third endpoint.

[0119] Further, the endpoint extraction module 20 is further configured to perform a clustering operation on the third point cloud data to generate a clustering line segment corresponding to the third point cloud data, and perform endpoint extraction processing on both ends of the clustering line segment corresponding to the third point cloud data to obtain a third endpoint.

[0120] Further, the recognition module 30 is further configured to perform coordinate transformation on the first endpoint and the third endpoint, so that the first coordinate information and the third coordinate information are in the same coordinate system; according to the first coordinate information of the first endpoint and the third coordinate information of the third endpoint in the same coordinate system, determine whether the first endpoint is located on the line segment formed by the third endpoints; if the first endpoint is located on the line segment formed by the third endpoints, then recognize the third target object as a door beam, control the mobile robot to stop moving forward, and perform a turn.

[0121] Further, the third detection unit is at least one of a line laser ranging device, a point laser ranging device, and a surface laser ranging device, and is set corresponding to the third preset height.

[0122] It should be noted that the specific implementation manner of the threshold recognition device 100 of the mobile robot in the embodiment of the present invention corresponds one by one to the specific implementation manner of the threshold recognition method of the mobile robot in the foregoing embodiment of the present invention. To reduce redundancy, it will not be repeated here.

[0123] In summary, according to the threshold recognition device of the mobile robot in the embodiment of the present invention, the acquisition module acquires the first point cloud data of the first target object at the first preset height, and acquires the second point cloud data of the second target object at the second preset height, where the first preset height is set corresponding to the threshold height, the second preset height is greater than the first preset height, and the endpoint extraction module performs endpoint extraction processing on the first point cloud data and the second point cloud data to respectively obtain a first endpoint and a second endpoint. Furthermore, the recognition module recognizes the threshold according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint. Thus, endpoint extraction processing is performed on point cloud data of different heights, and the threshold is recognized according to the endpoint coordinate information. Therefore, the mobile robot can recognize the threshold at a long distance without crossing or approaching the threshold, can recognize the threshold in advance while the mobile robot is moving at a high speed, increases the buffer response time of the mobile robot, and is beneficial to the mobile robot for path planning and reasonably crossing the threshold. In addition, the method of recognizing the threshold using the coordinate information of the first endpoint and the second endpoint does not require complex calculations, is simple and convenient to calculate, has a high accuracy rate at the same time, can greatly reduce the amount of calculation, and reduce the load and power consumption of the chip.

[0124] It should be noted that the logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection part with one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0125] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0126] In the description of this specification, the description referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0127] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation on the present invention.

[0128] In addition, the terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of the present invention, the meaning of "a plurality of" is at least two, such as two, three, etc., unless otherwise specifically and clearly defined.

[0129] In the present invention, unless otherwise clearly specified and defined, the terms such as "mounted", "connected", "connected to", "fixed", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements or the interaction relationship between two elements, unless otherwise clearly defined. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0130] In the present invention, unless otherwise clearly specified and defined, the first feature being "on" or "under" the second feature may be that the first and second features are in direct contact, or the first and second features are indirectly in contact through an intermediate medium. Moreover, the first feature being "above", "over" and "on top of" the second feature may be that the first feature is directly above or obliquely above the second feature, or merely indicates that the first feature has a higher horizontal height than the second feature. The first feature being "under", "below" and "beneath" the second feature may be that the first feature is directly below or obliquely below the second feature, or merely indicates that the first feature has a lower horizontal height than the second feature.

[0131] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as a limitation on the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A threshold recognition method for a mobile robot, characterized in that The method includes the following steps: Obtain the first point cloud data of the first target object at a first preset height, and obtain the second point cloud data of the second target object at a second preset height, where the first preset height is set corresponding to the threshold height, and the second preset height is greater than the first preset height; Perform endpoint extraction processing on the first point cloud data and the second point cloud data to obtain a first endpoint and a second endpoint respectively; Identify the threshold according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint; According to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint, determine whether at least one of the second endpoints is located on the line segment formed by the first endpoints; If none of the second endpoints is located on the line segment formed by the first endpoints, further determine whether all of the first endpoints are located on the line segment formed by the second endpoints, or determine whether the first endpoints are located between multiple line segments formed by the second endpoints; If all of the first endpoints are located on the line segment formed by the second endpoints, identify the first target object as a wall, and if the first endpoints are located between multiple line segments formed by the second endpoints, identify the first target object as a threshold; 2. The threshold recognition method for a mobile robot according to claim 1, characterized in that The first point cloud data is obtained by scanning of a first detection unit at the first preset height; and the second point cloud data is obtained by scanning of a second detection unit at the second preset height; 3. The threshold recognition method for a mobile robot according to claim 2, characterized in that, The first detection unit scans the first target object at the first preset height by a laser detection method, and the second detection unit scans the second target object at the second preset height by the laser detection method; 4. The threshold recognition method for a mobile robot according to claim 2, characterized in that, The first detection unit is a line laser ranging device and is set corresponding to the first preset height, and the second detection unit is at least one of a line laser ranging device, a point laser ranging device, and a surface laser ranging device and is set corresponding to the second preset height; 5. The threshold recognition method of the mobile robot according to claim 4, characterized in that, The first detection unit is the line laser ranging device, and the second detection unit is the point laser ranging device, where performing endpoint extraction processing on the first point cloud data and the second point cloud data includes: Generate a laser line segment according to the first point cloud data, and perform endpoint extraction processing on both ends of the laser line segment to obtain the first endpoint; and Perform clustering operation on the second point cloud data to generate a clustering line segment corresponding to the second point cloud data, and perform endpoint extraction processing on both ends of the clustering line segment corresponding to the second point cloud data to obtain the second endpoint; 6. The threshold recognition method for a mobile robot according to claim 5, characterized in that, Identifying the threshold according to the first coordinate information of the first endpoint and the second coordinate information of the second endpoint includes: Perform coordinate transformation on the first endpoint and the second endpoint so that the first coordinate information and the second coordinate information are in the same coordinate system; Identify the threshold according to the first coordinate information and the second coordinate information in the same coordinate system; 7. The threshold recognition method for a mobile robot according to claim 6, characterized in that, Identifying the threshold according to the first coordinate information and the second coordinate information in the same coordinate system includes: If at least one of the second endpoints is located on the line segment formed by the first endpoints, the first target object is identified as the threshold.

8. The threshold recognition method for a mobile robot according to any one of claims 1-7, characterized in that, After identifying the first target object as the threshold, the method further includes: Obtaining the third point cloud data of the third target object at a third preset height, where the third preset height is greater than the second preset height; Performing endpoint extraction processing on the third point cloud data to obtain third endpoints; Judging whether to control the mobile robot to continue moving according to the first coordinate information of the first endpoints and the third coordinate information of the third endpoints.

9. The threshold recognition method for a mobile robot according to claim 8, wherein, Performing endpoint extraction processing on the third point cloud data includes: Performing clustering operation on the third point cloud data to generate a clustering line segment corresponding to the third point cloud data, and performing endpoint extraction processing on both ends of the clustering line segment corresponding to the third point cloud data to obtain the third endpoints.

10. The threshold recognition method for a mobile robot according to claim 9, wherein, Judging whether to control the mobile robot to continue moving according to the first coordinate information of the first endpoints and the third coordinate information of the third endpoints includes: Performing coordinate transformation on the first endpoints and the third endpoints so that the first coordinate information and the third coordinate information are in the same coordinate system; Judging whether the first endpoints are all located on the line segment formed by the third endpoints according to the first coordinate information of the first endpoints and the third coordinate information of the third endpoints in the same coordinate system; If the first endpoints are all located on the line segment formed by the third endpoints, the third target object is identified as the door beam, the mobile robot is controlled to stop continuing to move, and a turn is made.

11. The threshold recognition method for a mobile robot according to claim 8, wherein, The third point cloud data is obtained by the third detection unit scanning at the third preset height. The third detection unit is at least one of a line laser ranging device, a point laser ranging device, and a surface laser ranging device, and is set corresponding to the third preset height.

12. A computer-readable storage medium, characterized in that, Stored thereon is a threshold recognition program for a mobile robot. When the threshold recognition program for the mobile robot is executed by a processor, the threshold recognition method for the mobile robot according to any one of claims 1-11 is implemented.

13. A mobile robot, characterized in that, Including a memory, a processor, and a threshold recognition program for a mobile robot stored on the memory and executable on the processor. When the processor executes the threshold recognition program for the mobile robot, the threshold recognition method for the mobile robot according to any one of claims 1-11 is implemented.

14. A threshold recognition device for a mobile robot, characterized in that, The device includes: An acquisition module, which is used to acquire the first point cloud data of the first target object at a first preset height and acquire the second point cloud data of the second target object at a second preset height, where the first preset height is set corresponding to the threshold height, and the second preset height is greater than the first preset height; An endpoint extraction module, which is used to perform endpoint extraction processing on the first point cloud data and the second point cloud data to obtain first endpoints and second endpoints respectively; An identification module, which is used to identify the threshold according to the first coordinate information of the first endpoints and the second coordinate information of the second endpoints; The recognition module is further configured to determine whether at least one of the second endpoints is located on the line segment formed by the first endpoints according to the first coordinate information of the first endpoints and the second coordinate information of the second endpoints; If none of the second endpoints is located on the line segment formed by the first endpoints, it is further determined whether all of the first endpoints are located on the line segment formed by the second endpoints, or it is determined whether the first endpoints are located between multiple line segments formed by the second endpoints; If all of the first endpoints are located on the line segment formed by the second endpoints, the first target object is recognized as a wall, and if the first endpoints are located between multiple line segments formed by the second endpoints, the first target object is recognized as a threshold.

Images