Device navigation method, device and storage medium based on laser radar

Abstract

The present application discloses a laser radar-based device navigation method, device, and storage medium. The laser radar-based device navigation method includes: collecting point cloud data of a target identification area to obtain an environment point cloud; extracting points belonging to at least two positioning guidance components from the environment point cloud to obtain a target component point cloud; performing vertical and horizontal line fitting on the target component point cloud, selecting mutually parallel vertical lines from the vertical line fitting results corresponding to the at least two positioning guidance components to obtain a reference line; obtaining a horizontal line corresponding to each reference line, re-performing line fitting based on the point cloud corresponding to the horizontal line to obtain a comprehensive horizontal line; and calculating the coordinates corresponding to the target working position based on the intersection between the reference line and the comprehensive horizontal line. The method can ensure the accuracy of the coordinates of the target working position, and the calculation process is simple and efficient, thereby improving the navigation and positioning efficiency of the device.

Description

Technical Field

[0001] The present application relates to the field of path navigation technology, and in particular to a laser radar-based device navigation method, device, and storage medium. Background Art

[0002] In recent years, mobile robots have developed rapidly in the industrial field, making great contributions to the release of productivity and improvement of efficiency.

[0003] When mobile robots are performing tasks, such as moving objects in a warehouse, accurate positioning technology is particularly critical. The mobile robot needs to accurately identify its position in a constantly changing environment to ensure the precise execution of the task. At the same time, it needs to determine the position and posture of the shelves to achieve automatic docking of the shelves.

[0004] How to improve the navigation capability of mobile robots is a challenge faced by related fields. Summary of the Invention

[0005] This application at least provides a device navigation method, device and storage medium based on laser radar.

[0006] In a first aspect, the present application provides a device navigation method based on a laser radar, the method comprising: in response to a mobile device entering a target recognition area, collecting point cloud data of the target recognition area to obtain an environmental point cloud; wherein, at least two positioning guidance components are deployed relative to a target working position in the target recognition area, and the two positioning guidance components are deployed along a straight line and parallel to each other; extracting points belonging to the at least two positioning guidance components from the environmental point cloud to obtain target component point clouds corresponding to the at least two positioning guidance components; performing vertical line fitting and horizontal line fitting on the target component point clouds corresponding to the at least two positioning guidance components, and selecting mutually parallel vertical lines from the vertical line fitting results corresponding to the at least two positioning guidance components to obtain a reference line; wherein the vertical line corresponds to at least one mutually perpendicular horizontal line, and the vertical line is perpendicular to the linear deployment direction corresponding to the at least two positioning guidance components; obtaining a horizontal line corresponding to each reference line, and re-performing line fitting based on the point cloud corresponding to the horizontal line to obtain a comprehensive horizontal line; calculating the coordinates corresponding to the target working position based on the intersection between the reference line and the comprehensive horizontal line, and controlling the movement of the mobile device using the coordinates corresponding to the target working position.

[0007] In one embodiment, points belonging to at least two positioning guidance components are respectively extracted from an environment point cloud to obtain target component point clouds corresponding to the at least two positioning guidance components, including: obtaining preset appearance parameters and deployment positions of the at least two positioning guidance components; generating point cloud filter boxes corresponding to the at least two positioning guidance components based on the appearance parameters and deployment positions of the at least two positioning guidance components; and determining point clouds in the environment point cloud that fall within the point cloud filter boxes to obtain target component point clouds corresponding to the at least two positioning guidance components.

[0008] In one embodiment, a point cloud in an environment point cloud that falls within a point cloud filtering box is determined to obtain target component point clouds corresponding to at least two positioning guidance components, including: determining a straight edge corresponding to the point cloud filtering box based on the vertices of the point cloud filtering box; detecting whether a point in the environment point cloud is on the straight edge based on a position coordinate relationship between two vertices corresponding to the straight edge and a point in the environment point cloud; if so, adding the point in the environment point cloud to a candidate point cloud set; if not, detecting whether the point in the environment point cloud is within the point cloud filtering box based on an intersection relationship between a laser beam line segment corresponding to the point in the environment point cloud and the straight edge; if so, adding the point in the environment point cloud to a candidate point cloud set; and obtaining target component point clouds corresponding to at least two positioning guidance components based on the points in the candidate point cloud set.

[0009] In one embodiment, point clouds falling within a point cloud screening box in an environment point cloud are determined to obtain target component point clouds corresponding to at least two positioning guidance components, including: determining point clouds falling within a point cloud screening box in an environment point cloud to obtain candidate point cloud sets corresponding to at least two positioning guidance components; clustering the candidate point cloud sets corresponding to the at least two positioning guidance components based on the spacing between points to obtain point cloud clusters corresponding to the at least two positioning guidance components; and filtering the point cloud clusters corresponding to the at least two positioning guidance components based on the number of points in each point cloud cluster to obtain target component point clouds corresponding to the at least two positioning guidance components.

[0010] In one embodiment, a target component point cloud is composed of one or more point cloud clusters; vertical line fitting and horizontal line fitting are performed on the target component point clouds corresponding to at least two positioning guidance components, respectively, including: for the target component point cloud corresponding to any positioning guidance component, obtaining any point cloud cluster in the target component point cloud to obtain a point cloud cluster to be fitted; filtering a first preset number of points before and after the point cloud cluster to be fitted to obtain a filtered point cloud cluster; selecting a second preset number of points before and after the filtered point cloud cluster, and performing line fitting on them, respectively, to obtain a first straight line and a second straight line; detecting whether the first straight line and the second straight line are perpendicular to each other, and if the first straight line and the second straight line are perpendicular to each other, taking the first straight line and the second straight line as a vertical straight line and a horizontal straight line, respectively.

[0011] In one embodiment, the method further includes: if the first straight line and the second straight line are not perpendicular to each other, calculating the intersection point between the first straight line and the second straight line; screening the points in the filtered point cloud cluster whose distance from the intersection point is greater than a first distance threshold, and selecting points from the screened points whose distance from the first straight line and the second straight line is less than a second distance threshold, to obtain a first point set and a second point set; re-performing straight line fitting on the first point set and the second point set, respectively, to obtain a new first straight line and a new second straight line; detecting whether the new first straight line and the new second straight line are perpendicular to each other, and if the new first straight line and the new second straight line are perpendicular to each other, using the new first straight line and the new second straight line as a vertical straight line and a horizontal straight line, respectively.

[0012] In one embodiment, mutually parallel vertical lines are respectively selected from the vertical line fitting results corresponding to at least two positioning guidance components to obtain a reference line, including: calculating the spacing between the at least two positioning guidance components based on the deployment positions of the at least two positioning guidance components to obtain an actual spacing; detecting whether the vertical lines respectively fitted by the at least two positioning guidance components are parallel to each other, and if so, calculating the straight-line distance between the vertical lines fitted by the at least two positioning guidance components; detecting whether the difference between the straight-line distance and the actual spacing is less than a preset difference threshold, and if so, using the vertical lines respectively fitted by the at least two positioning guidance components as the reference line.

[0013] In one embodiment, the coordinates corresponding to the target working position are calculated based on the intersection between the reference straight line and the integrated horizontal line, including: obtaining the relative position relationship between at least two positioning guidance components and the target working position; and calculating the coordinates of the at least two positioning guidance components based on the intersection between each reference straight line and the integrated horizontal line, and calculating the orientation of the at least two positioning guidance components based on the angle between each reference straight line and the integrated horizontal line; and calculating the coordinates corresponding to the target working position based on the coordinates and orientation of the at least two positioning guidance components and the relative position relationship between the at least two positioning guidance components and the target working position.

[0014] In one embodiment, the orientations of at least two positioning guidance components are obtained based on the angle calculation between each reference line and the integrated horizontal line, including: obtaining the perpendicular line of each reference line and obtaining the direction vector of the integrated horizontal line; and obtaining a weighted parameter between the perpendicular line of each reference line and the direction vector of the integrated horizontal line based on the ratio between the number of point clouds corresponding to each reference line and the number of point clouds corresponding to the integrated horizontal line; and performing a weighted sum calculation on the perpendicular line of each reference line and the direction vector of the integrated horizontal line using the weighted parameter to obtain the orientations of at least two positioning guidance components.

[0015] The second aspect of the present application provides a device navigation device based on laser radar, which includes: a point cloud acquisition module for collecting point cloud data of the target recognition area in response to the mobile device entering the target recognition area to obtain an environmental point cloud; wherein at least two positioning guidance components are deployed relative to the target working position in the target recognition area, and the two positioning guidance components are deployed along a straight line and parallel to each other; a point cloud extraction module for extracting points belonging to the at least two positioning guidance components from the environmental point cloud to obtain target component point clouds corresponding to the at least two positioning guidance components; a line selection module for performing vertical line fitting on the target component point clouds corresponding to the at least two positioning guidance components. The vertical straight lines are combined and fitted with horizontal straight lines, and vertical straight lines parallel to each other are selected from the vertical straight line fitting results corresponding to at least two positioning guidance components to obtain a reference straight line; wherein, the vertical straight line corresponds to at least one mutually perpendicular horizontal straight line, and the vertical straight line is perpendicular to the straight line deployment direction corresponding to at least two positioning guidance components; a straight line fitting module is used to obtain the horizontal straight line corresponding to each reference straight line, and re-perform straight line fitting based on the point cloud corresponding to the horizontal straight line to obtain a comprehensive horizontal straight line; a coordinate calculation module is used to calculate the coordinates corresponding to the target working position based on the intersection between the reference straight line and the comprehensive horizontal straight line, and use the coordinates corresponding to the target working position to control the movement of the mobile device.

[0016] A third aspect of the present application provides an electronic device comprising a memory and a processor, wherein the processor is configured to execute program instructions stored in the memory to implement the above-mentioned laser radar-based device navigation method.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium having program instructions stored thereon, which implement the above-mentioned laser radar-based device navigation method when executed by a processor.

[0018] The above scheme obtains an environmental point cloud by collecting point cloud data of the target recognition area; extracts points belonging to at least two positioning guidance components from the environmental point cloud respectively, and obtains target component point clouds corresponding to the at least two positioning guidance components respectively; performs vertical line fitting and horizontal line fitting on the target component point clouds corresponding to the at least two positioning guidance components respectively, and selects mutually parallel vertical lines from the vertical line fitting results corresponding to the at least two positioning guidance components to obtain a reference line; obtains the horizontal line corresponding to each reference line, and re-performs line fitting based on the point cloud corresponding to the horizontal line to obtain a comprehensive horizontal line; calculates the coordinates corresponding to the target working position based on the intersection between the reference line and the comprehensive horizontal line, so as to calculate the coordinates of the target working position through the vertical line and horizontal line of each positioning guidance component, thereby ensuring the accuracy of the coordinates of the target working position, and the calculation process is simple and efficient, thereby improving the navigation and positioning efficiency of the equipment.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and, together with the specification, are used to illustrate the technical solutions of the present application.

[0021] Figure 1 is a schematic diagram of a solution implementation environment shown in an exemplary embodiment of the present application;

[0022] Figure 2 is a flowchart of a laser radar-based device navigation method shown in an exemplary embodiment of the present application;

[0023] Figure 3 is a schematic diagram of a positioning guidance component shown in an exemplary embodiment of the present application;

[0024] Figure 4 is a schematic diagram of a straight line fitting result shown in an exemplary embodiment of the present application;

[0025] Figure 5 is a block diagram of a device navigation apparatus based on a laser radar, shown as an exemplary embodiment of the present application;

[0026] Figure 6 is a schematic structural diagram of an electronic device shown in an exemplary embodiment of the present application;

[0027] Figure 7 It is a schematic diagram of the structure of a computer-readable storage medium shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0028] The following describes the embodiments of the present application in detail with reference to the accompanying drawings.

[0029] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0030] The term "and / or" in this article is merely information describing the association of associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0031] The following describes the laser radar-based device navigation method provided in the embodiments of the present application.

[0032] Please refer to Figure 1 , Figure 1 FIG. 1 is a schematic diagram of an exemplary embodiment of the present application showing a solution implementation environment, wherein the solution implementation environment may include a mobile device 110 and a server 120 , wherein the mobile device 110 and the server 120 are in communication connection with each other.

[0033] The mobile device 110 may be an industrial robot, an automated guided vehicle (AGV), a sweeping robot, etc., which is not limited in this application.

[0034] The mobile device 110 is loaded with a laser radar to scan the environment information through the laser radar. For example, Figure 1 The mobile device 110 is equipped with laser radars on the top of the device and at the tips of the two forks, and the laser radars are used to scan environmental information.

[0035] Of course, the mobile device 110 may also include a mobile chassis, which includes a motion controller, a motor, a battery, an embedded computer, an odometer, etc., which is not limited in this application.

[0036] Server 120 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0037] In one example, the server 120 can perform positioning and identification on the environmental point cloud obtained from the mobile device 110 to obtain the coordinates corresponding to the target work position. The server 120 can transmit the coordinates corresponding to the target work position back to the mobile device 110 to enable the mobile device 110 to perform navigation movement.

[0038] In one example, mobile device 110 is installed with a client running a target application, such as an application providing positioning and navigation functions. This target application is used to perform positioning and recognition on the acquired environmental point cloud to obtain coordinates corresponding to the target work location for navigation and movement. Server 120 may be the backend server of the target application, configured to provide backend services for the client of the target application.

[0039] In the laser radar-based device navigation method provided in the embodiment of the present application, the execution entity of each step can be the mobile device 110, such as the client of the target application installed and running in the mobile device 110, or the server 120, or the mobile device 110 and the server 120 can interact and cooperate to execute, that is, part of the steps of the method are handed over to the mobile device 110 for execution and the other part of the steps are handed over to the server 120 for execution.

[0040] It should be noted that the laser radar-based device navigation method of the present application can be applied to any navigation scenario, such as the shelf docking scenario of an industrial robot, the floor cleaning scenario of a cleaning robot, etc., and the present application does not limit this.

[0041] Taking the shelf docking scenario as an example, the target work position is the lifting center corresponding to the shelf where the goods to be moved are located. The mobile device 110 uses the installed LiDAR to scan the environmental contours of walls, work machines, shelves, building supports, etc. in the workshop, warehouse, etc., to build an environmental map used for navigation for motion navigation. Specifically, the mobile device 110 uses the odometer to estimate the amount of change during the movement, and uses one or more LiDARs installed on the mobile device 110 to scan the environmental contours and match them with the grid map for accurate positioning and navigation. After detecting that the mobile device 110 has entered the target recognition area, the relevant parameters of the positioning guidance component are extracted to calculate the position of the positioning guidance component. After calculating the lifting center using the position of the positioning guidance component, the mobile device 110 adjusts its own navigation trajectory and navigates to the lifting center through the odometer to lift the goods in the shelf.

[0042] See also Figure 2 , Figure 2 This is a flowchart of a device navigation method based on a laser radar, which is an exemplary embodiment of the present application. The device navigation method based on a laser radar can be applied to Figure 1It should be understood that the method can also be applied to other exemplary implementation environments and be specifically executed by devices in other implementation environments, and this embodiment does not limit the implementation environment to which the method is applicable.

[0043] like Figure 2 As shown, the device navigation method based on laser radar includes at least steps S210 to S250, which are described in detail as follows:

[0044] Step S210: In response to the mobile device entering the target recognition area, point cloud data is collected for the target recognition area to obtain an environment point cloud.

[0045] Wherein, at least two positioning guidance components are deployed relative to the target working position in the target recognition area, and the two positioning guidance components are deployed along a straight line and parallel to each other.

[0046] The positioning guidance component is used to help the mobile device to perform positioning, and the positioning guidance component can be a component with a preset shape.

[0047] For example, see Figure 3 , Figure 3 is a schematic diagram of a positioning guidance component shown in an exemplary embodiment of the present application, such as Figure 3 As shown, the positioning guidance component is a limiting structure for limiting the mobile device, specifically a left limiting structure and a right limiting structure, which are deployed relative to the target working position, and the left limiting structure and the right limiting structure are deployed along a straight line and parallel to each other.

[0048] Of course, except Figure 3 In addition to the positioning guidance components shown, other types of components may also be used as positioning guidance components, as long as the two positioning guidance components are arranged along a straight line and are parallel to each other.

[0049] The target identification area contains a target working position and at least two positioning guidance components arranged relative to the target working position.

[0050] Among them, the target recognition area can be pre-divided based on experience, such as taking the target working position as the center of the circle and dividing the area with a radius of r as the target recognition area corresponding to the target working position; the target recognition area can also be flexibly divided according to the current actual scene.

[0051] For example, based on the environmental perception capability of the mobile device, and / or the degree of occlusion corresponding to the target work position (e.g., the smaller the distance between the shelf where the target work position is located and other shelves, the higher the degree of occlusion), etc., the size of the target recognition area is flexibly calculated, so as to divide the target recognition area. For example, the weaker the environmental perception capability of the mobile device, and / or the higher the degree of occlusion corresponding to the target work position, the larger the target recognition area that needs to be divided, and vice versa, the smaller the target recognition area that needs to be divided.

[0052] After the mobile device obtains the target working location, if it detects that the mobile device is not currently within the target identification area corresponding to the target working location, it can first navigate to the target identification area, such as by using an odometer and a lidar. After detecting that the mobile device has entered the target identification area, point cloud data is collected for the target identification area to obtain an environmental point cloud corresponding to the target identification area.

[0053] Optionally, after detecting that the mobile device has entered the target identification area, the component parameters of the positioning guidance component are also obtained. These component parameters include, but are not limited to, appearance parameters and deployment location. For example, component parameters include the length, width, and depth of the positioning guidance component, the distance between it and other positioning guidance components, and the positional relationship between it and the target working position. These component parameters can be pre-stored in a database based on the actual deployment situation to facilitate subsequent positioning calculations. It should be noted that the target working position, deployment position, and positional relationship obtained above are relative to the map coordinate system.

[0054] Optionally, in a docking scenario, in addition to obtaining the target working position of the docking point (such as a shelf), the mobile device also needs to obtain the orientation angle of the docking point, such as the orientation angle of the shelf, to improve docking accuracy.

[0055] Step S220 : extracting points belonging to at least two positioning guidance components from the environment point cloud, respectively, to obtain target component point clouds corresponding to the at least two positioning guidance components.

[0056] After obtaining the environment point cloud, the points in the environment point cloud that belong to the positioning guidance components are screened, and the target component point clouds corresponding to each positioning guidance component are obtained respectively.

[0057] For example, the points in the environment point cloud may be clustered, and the cluster result with the shape closest to the shape of the positioning guidance component may be selected from each cluster result, and used as the target component point cloud corresponding to the positioning guidance component.

[0058] Exemplarily, a point cloud filtering box corresponding to each positioning guidance component can be set according to the appearance parameters, deployment position, etc. of each positioning guidance component, and the point cloud belonging to each positioning guidance component can be filtered according to the point cloud filtering box to obtain the target component point cloud corresponding to each positioning guidance component.

[0059] Of course, the above two embodiments may also be combined to screen the target component point cloud corresponding to the positioning guidance component, and this application does not limit this.

[0060] Step S230: performing vertical line fitting and horizontal line fitting on the target component point clouds corresponding to at least two positioning guidance components respectively, and selecting mutually parallel vertical lines from the vertical line fitting results corresponding to the at least two positioning guidance components respectively to obtain reference lines.

[0061] The vertical straight line corresponds to at least one mutually perpendicular horizontal straight line, and the vertical straight line is perpendicular to the linear deployment directions corresponding to the at least two positioning guidance components.

[0062] Vertical line fitting and horizontal line fitting are performed on the target component point clouds corresponding to at least two positioning guidance components respectively to obtain vertical lines and horizontal lines corresponding to the positioning guidance components. It should be noted that a vertical line is associated with at least one horizontal line, and the associated vertical lines and horizontal lines are perpendicular to each other, that is, through vertical line fitting and horizontal line fitting, multiple pairs of vertical lines and horizontal lines that are perpendicular to each other can be obtained.

[0063] For the vertical lines obtained by fitting each positioning guidance component, vertical lines parallel to each other between each positioning guidance component are used as reference lines.

[0064] For example, see Figure 4 , Figure 4 is a schematic diagram of a straight line fitting result shown in an exemplary embodiment of the present application, such as Figure 4 As shown, the positioning guidance components include a left limit structure and a right limit structure, and vertical line fitting and horizontal line fitting are performed on the target component point clouds corresponding to the left limit structure and the right limit structure respectively. Vertical lines parallel to each other are selected from the vertical line fitting results corresponding to the left limit structure and the right limit structure respectively, and the reference lines include line ml and line mr.

[0065] Step S240: Obtain the horizontal lines corresponding to each reference line, and re-perform line fitting based on the point cloud corresponding to the horizontal line to obtain a comprehensive horizontal line.

[0066] After obtaining the reference lines, obtain the horizontal lines associated with each reference line and the point cloud corresponding to each associated horizontal line. Re-fit the lines based on these point clouds, and use the fitted lines as the comprehensive horizontal lines corresponding to each reference line.

[0067] For example, Figure 4 In the figure, according to the point cloud of the horizontal line corresponding to each reference line, the comprehensive horizontal line mh is finally fitted.

[0068] Step S250: Calculate the coordinates corresponding to the target working position based on the intersection between the reference straight line and the integrated horizontal straight line, and use the coordinates corresponding to the target working position to control the movement of the mobile device.

[0069] After obtaining the reference straight line and the integrated horizontal line, the position of each positioning guidance component in the environmental point cloud can be accurately known based on the intersection between the reference straight line and the integrated horizontal line. Then, combined with the relative position relationship between the positioning guidance component and the target work position, the coordinates of the target work position can be calculated to control the movement of the mobile device according to the coordinates corresponding to the target work position.

[0070] It should be noted that the coordinates corresponding to the target working position calculated in step S250 are generally coordinates relative to the vehicle body coordinate system, so that the mobile device can navigate and move in the vehicle body coordinate system.

[0071] This application pre-deploys multiple positioning guidance components, and uses the vertical and horizontal lines of each positioning guidance component to calculate the coordinates of the target working position during the subsequent recognition process, thereby ensuring the accuracy of the coordinates of the target working position. The calculation process is simple and efficient, and the navigation and positioning efficiency of the equipment is improved.

[0072] Next, some embodiments of the present application are described in detail.

[0073] In some embodiments, extracting points belonging to at least two positioning guidance components from the environment point cloud in step S220 to obtain target component point clouds corresponding to the at least two positioning guidance components includes:

[0074] Step S221: Obtaining preset appearance parameters and deployment positions of at least two positioning guidance components.

[0075] The appearance parameters include but are not limited to the preset length, width, and height of the positioning guidance component, and the deployment position may be the deployment coordinates stored in the database after the positioning guidance component is deployed.

[0076] Step S222: generating point cloud filter boxes corresponding to the at least two positioning guidance components based on the appearance parameters and deployment positions of the at least two positioning guidance components.

[0077] For example, a point cloud filter box is generated at the deployment coordinates, and the size of the point cloud filter box is determined based on the length, width, and height preset by the positioning guidance component.

[0078] Step S223: determining the point clouds in the environment point cloud that fall within the point cloud screening box, and obtaining target component point clouds corresponding to at least two positioning guidance components.

[0079] The point clouds in the point cloud screening box in the environment point cloud are judged to obtain the target component point clouds corresponding to each positioning guidance component.

[0080] Taking the shelf docking scenario as an example, the left and right limit structures are deployed at the lifting center of the shelf (the target working position). The point cloud filter box is calculated based on the length, width, docking depth, and lifting center of the left and right limit structures.

[0081] Specifically, if the ideal position coordinates of the lifting center obtained by the mobile device in the map coordinate system are , then Convert to the vehicle coordinate system. For the specific conversion formula, see the following formula 1:

[0082] (Formula 1)

[0083] in, Indicates the position of the mobile device relative to the map coordinate system. Indicates the position of the lifting center in the vehicle coordinate system.

[0084] And, the environmental point cloud is converted to the vehicle coordinate system. If the environmental point cloud is collected by multiple laser radars, the environmental point cloud collected by each laser radar is converted to the vehicle coordinate system according to the corresponding laser external parameters, and the laser point cloud is reordered according to the angle of each cluster of point clouds in the vehicle coordinate system to obtain the point cloud to be screened. The angle of the i-th cluster of point clouds is The calculation method of is shown in the following formula 2:

[0085] (Formula 2)

[0086] in, Represents the vertical coordinate of point cloud i in the vehicle coordinate system, Represents the horizontal coordinate of point cloud i in the vehicle coordinate system.

[0087] In addition, the center positions of the left and right limit structures are calculated respectively. For specific calculation methods, see the following formulas 3 and 4:

[0088] (Formula 3)

[0089] (Formula 4)

[0090] in, Indicates the center position of the left limit structure; Indicates the center position of the right limit structure; It represents the position of the lifting center in the vehicle coordinate system; Lw represents the distance between the deployment positions of the left limit structure and the right limit structure; W represents the width of the left limit structure and the right limit structure respectively; L represents the length of the left limit structure and the right limit structure respectively; Ld represents the docking depth of the left limit structure and the right limit structure respectively.

[0091] Taking the two-dimensional laser radar as an example, after obtaining the center positions of the left limit structure and the right limit structure, 、 As the center, and is the point cloud filter box, where is the proportional coefficient.

[0092] Optionally, the proportional coefficient can be pre-set based on experience, such as the value of the proportional coefficient is greater than 1.2 and less than 2.5; the proportional coefficient can also be flexibly calculated according to the actual scenario, such as calculating the distance between the mobile device and the positioning guidance component, and setting the size of the proportional coefficient based on the calculated distance between the mobile device and the positioning guidance component. For example, the calculated distance between the mobile device and the positioning guidance component is proportional to the size of the proportional coefficient, so as to generate point cloud filtering boxes corresponding to the positioning guidance components based on the proportional coefficient, the preset appearance parameters and deployment position of the positioning guidance component, thereby improving the accuracy of point cloud filtering.

[0093] It is determined whether the point cloud to be filtered falls within the point cloud filtering box to obtain the target component point clouds corresponding to each positioning guidance component.

[0094] Exemplarily, in step S223, determining the point clouds in the environment point cloud that fall within the point cloud screening box, and obtaining the target component point clouds corresponding to at least two positioning guidance components, respectively, includes:

[0095] Step S2231: Determine the straight line edges corresponding to the point cloud filter box based on the vertices of the point cloud filter box.

[0096] The four vertices of the point cloud filter box are converted to the vehicle coordinate system. The four vertices of the point cloud filter box are recorded as p1, p2, p3, and p4 respectively. The straight line edge is constructed using the four vertices in the order of p1-p2, p2-p3, p3-p4, and p4-p1.

[0097] Step S2232: Based on the position coordinate relationship between the two vertices corresponding to the straight line edge and the point in the environment point cloud, detect whether the point in the environment point cloud is on the straight line edge. If it is on the straight line edge, add the point in the environment point cloud to the candidate point cloud set.

[0098] For example, taking the straight line edge p1-p2 as an example, to determine whether point Qi is on the straight line edge, the specific judgment conditions are shown in the following formulas 5 and 6:

[0099] (Formula 5)

[0100] (Formula 6)

[0101] Formula 5 represents the cross product of two coordinate vectors, and Formula 6 represents the dot product of two coordinate vectors. If both Formula 5 and Formula 6 are satisfied, it is determined that point Qi is on the edge of the straight line and the point is added to the candidate point cloud set.

[0102] Step S2233: If it is not on the straight edge, based on the intersection relationship between the laser beam segment corresponding to the point in the environmental point cloud and the straight edge, detect whether the point in the environmental point cloud is within the point cloud filtering box. If it is within the point cloud filtering box, add the point in the environmental point cloud to the candidate point cloud set.

[0103] If it is not on the straight edge, whether the laser beam segment corresponding to the point intersects with the straight edge segment and whether the intersection point is on the straight edge segment is used to determine whether the point is within the point cloud filter box.

[0104] Specifically, taking the straight line edge p1-p2 as an example, let the coordinates of the laser origin in the vehicle coordinate system be LO, and the i-th laser point cloud Qi, then:

[0105] (Formula 7)

[0106] (Formula 8)

[0107] (Formula 9)

[0108] (Formula 10)

[0109] (Formula 11)

[0110] like and If the value of is between [0,1], the point Qi is considered to be a point cloud within the point cloud filter box, that is, it is judged to be a point cloud on the positioning guidance component, and the point is added to the candidate point cloud set.

[0111] Step S2234: Based on the points in the candidate point cloud set, obtain target component point clouds corresponding to at least two positioning guidance components.

[0112] Through the above embodiments, the target component point cloud corresponding to each positioning guidance component is obtained, so as to efficiently filter the point cloud on the limit by using the method that the laser point cloud is on the straight line edge and the laser beam line segment intersects the straight line edge and the intersection point is on the straight line edge, thereby improving the accuracy of point cloud screening.

[0113] Of course, in addition to the point cloud screening steps shown in the above steps S2231 to S2234, other methods can also be used to screen the point cloud, such as detecting whether the point is within the point cloud screening box based on the coordinates of each point in the point cloud. This application does not limit this.

[0114] After obtaining the candidate point cloud set in the above embodiment, the points of the candidate point cloud set can be directly used as the target component point clouds corresponding to the positioning guidance components; the points of the candidate point cloud set can also be screened again to ensure the accuracy of the target component point cloud finally obtained.

[0115] For example, point clouds in the environment point cloud that fall into the point cloud filtering box are determined to obtain candidate point cloud sets corresponding to at least two positioning guidance components respectively; the candidate point cloud sets corresponding to at least two positioning guidance components are clustered based on the spacing between points to obtain point cloud clusters corresponding to at least two positioning guidance components respectively; based on the number of points in each point cloud cluster, the point cloud clusters corresponding to at least two positioning guidance components are filtered to obtain target component point clouds corresponding to at least two positioning guidance components respectively.

[0116] For example, consider two positioning guidance components. The resulting candidate point cloud sets are labeled LV and LR, respectively. The point clouds in LV and LR are clustered based on the distance between points. For example, points with a distance less than a preset threshold are grouped together, and LV and LR are divided into multiple point cloud clusters. The number of points in each point cloud cluster is then counted, and clusters with fewer than the preset threshold are filtered out. Based on these filtered point cloud clusters, the target component point clouds corresponding to the two positioning guidance components are obtained.

[0117] In some embodiments, the target component point cloud is composed of one or more point cloud clusters; step S230 performs vertical straight line fitting and horizontal straight line fitting on the target component point clouds corresponding to at least two positioning guidance components, including:

[0118] Step S231: for a target component point cloud corresponding to any positioning guidance component, obtain any point cloud cluster in the target component point cloud to obtain a point cloud cluster to be fitted.

[0119] Optionally, when selecting a point cloud cluster to be fitted, it is detected whether the number of points in the point cloud cluster is less than a minimum number threshold. If it is less than the minimum number threshold, the point cloud cluster is ignored; if it is not less than the minimum number threshold, the point cloud cluster is used as the point cloud cluster to be fitted.

[0120] Step S232: filtering a first preset number of points before and after the point cloud cluster to be fitted respectively to obtain a filtered point cloud cluster.

[0121] Since the point clouds at both ends of the point cloud cluster may have tails or even distortion, the first preset number of points before and after the point cloud cluster to be fitted are skipped during the straight line fitting, such as skipping j points before and after the point cloud cluster to be fitted.

[0122] The ordering method of the point cloud can be found in the above formula 2 and will not be described here in detail.

[0123] Step S233: Selecting a second preset number of points before and after the filtered point cloud cluster, and performing straight line fitting on each of them to obtain a first straight line and a second straight line.

[0124] For example, the first k points of the filtered point cloud cluster are selected, and a straight line fitting is performed on the selected points to obtain a first straight line m1, and the linear equation coefficients of m1 include m1a, m1b and m1c; the last k points of the filtered point cloud cluster are selected, and a straight line fitting is performed on the selected points to obtain a second straight line m2, and the linear equation coefficients of m2 include m2a, m2b and m2c.

[0125] Step S234: Detect whether the first straight line and the second straight line are perpendicular to each other. If the first straight line and the second straight line are perpendicular to each other, the first straight line and the second straight line are respectively regarded as a vertical straight line and a horizontal straight line.

[0126] Specifically, calculate the angle between the first straight line and the second straight line , the specific calculation formula is shown in the following formula 12:

[0127] (Formula 12)

[0128] like If the difference between the first straight line and 90° is smaller than a preset angle threshold, it is determined that the first straight line and the second straight line are perpendicular to each other.

[0129] If the first straight line and the second straight line are perpendicular to each other, the first straight line and the second straight line are respectively regarded as a vertical straight line and a horizontal straight line.

[0130] In some embodiments, further comprising:

[0131] Step S235: If the first straight line and the second straight line are not perpendicular to each other, calculate the intersection point between the first straight line and the second straight line.

[0132] Specifically, the intersection point can be calculated using the following formula 13:

[0133] (Formula 13)

[0134] Based on formula 13, the intersection point is calculated .

[0135] Step S236: Filter the points in the filtered point cloud cluster whose distances to the intersection point are greater than the first distance threshold, and select from the filtered points the points whose distances to the first straight line and the second straight line, respectively, are less than the second distance threshold to obtain a first point set and a second point set.

[0136] The first distance threshold and the second distance threshold may be preset based on experience.

[0137] Screening and Intersection Then, from the screened points, the distances between the points and the lines m1 and m2 are counted respectively, and the points whose distance to the first line is less than the second distance threshold are selected to obtain the first point set, and the points whose distance to the second line is less than the second distance threshold are selected to obtain the second point set.

[0138] Step S237: re-perform straight line fitting on the first point set and the second point set respectively to obtain a new first straight line and a new second straight line.

[0139] The first point set and the second point set are re-selected and straight line fitting is performed to obtain a new first straight line m1 and a new second straight line m2.

[0140] Step S238: Detect whether the new first straight line and the new second straight line are perpendicular to each other. If the new first straight line and the new second straight line are perpendicular to each other, use the new first straight line and the new second straight line as a vertical straight line and a horizontal straight line, respectively.

[0141] Of course, if the new first straight line and the new second straight line are still not perpendicular to each other, continue the above steps until the first straight line and the second straight line that are perpendicular to each other are obtained.

[0142] Based on the above embodiment, a first straight line and a second straight line perpendicular to each other corresponding to each positioning guidance component are obtained respectively, the one perpendicular to the straight line deployment direction is used as the vertical line, and the other straight line is used as the horizontal line associated with the vertical line.

[0143] After the vertical lines are obtained, vertical lines parallel to each other are selected from the vertical line fitting results corresponding to at least two positioning guidance components to obtain a reference line.

[0144] In some embodiments, in addition to determining whether the vertical lines corresponding to the respective positioning guidance components are parallel, it is also possible to detect whether the spacing between the vertical lines corresponding to the respective positioning guidance components conforms to the actual deployment conditions of the respective positioning guidance components, specifically including: calculating the spacing between the at least two positioning guidance components based on the deployment positions of the at least two positioning guidance components to obtain the actual spacing; detecting whether the vertical lines respectively fitted by the at least two positioning guidance components are parallel to each other; if so, calculating the straight-line distance between the vertical lines fitted by the at least two positioning guidance components; detecting whether the difference between the straight-line distance and the actual spacing is less than a preset difference threshold; if so, using the vertical lines respectively fitted by the at least two positioning guidance components as reference lines.

[0145] Specifically, calculate whether the vertical straight lines fitted by the positioning guidance components are parallel to each other. If the vertical straight lines fitted by the positioning guidance components are parallel to each other, calculate whether the distance between each vertical straight line is close to the actual distance Lw between the issued positioning guidance components, that is, judge whether the difference between the straight line distance and the actual spacing is less than the preset difference threshold. If it is less than the preset difference threshold, then each vertical straight line is a straight line on each positioning guidance component, which is used as the reference straight line.

[0146] Then, the horizontal line corresponding to each reference line is obtained, and the line fitting is re-performed based on the point cloud corresponding to the horizontal line to obtain a comprehensive horizontal line.

[0147] For example, if the number of positioning guidance components is 2, the vertical and horizontal lines corresponding to the left positioning guidance component are fitted to include m1 and m2, and the vertical and horizontal lines corresponding to the right positioning guidance component are fitted to include m3 and m4. If the vertical line m1 and the vertical line m3 are parallel, and the difference between the straight line spacing and the actual spacing between the left positioning guidance component and the right positioning guidance component is less than the preset difference threshold, then the vertical line m1 and the vertical line m3 are used as the reference lines ml and mr, respectively.

[0148] Then, the horizontal lines corresponding to the reference lines ml and mr are obtained respectively, and the horizontal lines m2 and m4 are obtained. The point clouds on the horizontal lines m2 and m4 are re-fitted, and the fitted lines are recorded as the comprehensive horizontal line mh.

[0149] Then, based on the intersection between the reference straight line and the integrated horizontal straight line, the coordinates corresponding to the target working position are calculated.

[0150] In some embodiments, calculating the coordinates corresponding to the target working position based on the intersection of the reference line and the integrated horizontal line in step S250 includes:

[0151] Step S251: Obtain the relative positional relationship between at least two positioning guidance components and the target working position; and calculate the coordinates of the at least two positioning guidance components based on the intersection points between each reference line and the integrated horizontal line, and calculate the orientations of the at least two positioning guidance components based on the angles between each reference line and the integrated horizontal line.

[0152] The coordinates of each positioning guidance component in the vehicle coordinate system can be obtained based on the intersection points between each reference line and the integrated horizontal line, and the orientation of the positioning guidance component can be obtained based on the angle between each reference line and the integrated horizontal line.

[0153] In some embodiments, the calculation of the orientations of at least two positioning guidance components based on each reference line and the integrated horizontal line in step S251 includes:

[0154] Step S2511: Obtain the perpendicular line of each reference straight line and obtain the direction vector of the comprehensive horizontal straight line; and, based on the ratio between the number of point clouds corresponding to each reference straight line and the number of point clouds corresponding to the comprehensive horizontal straight line, obtain the weighted parameter between the perpendicular line of each reference straight line and the direction vector of the comprehensive horizontal straight line.

[0155] Step S2512: performing weighted sum calculation on the direction vectors of the perpendicular line of each reference straight line and the integrated horizontal straight line using weighted parameters to obtain the orientations of at least two positioning guidance components.

[0156] According to the ratio between the number of point clouds corresponding to each reference line and the number of point clouds corresponding to the comprehensive horizontal line, a weighted parameter between the perpendicular line of each reference line and the direction vector of the comprehensive horizontal line is obtained.

[0157] For example, the total number of point clouds corresponding to each reference line is n1, and the total number of point clouds corresponding to the comprehensive horizontal line is n2. Then the weighted parameter corresponding to the perpendicular line of each reference line is calculated. is n1 / (n1+n2), the weighted parameter corresponding to the direction vector of the comprehensive horizontal line is n2 / (n1+n2).

[0158] Step S252: Calculating coordinates corresponding to the target working position based on the coordinates and orientations of the at least two positioning guidance components and the relative positional relationship between the at least two positioning guidance components and the target working position.

[0159] The above embodiments are merely illustrative, and other methods may be used to calculate the coordinates corresponding to the target working position. For example, for low-precision navigation scenarios, the orientation of the positioning guidance component may not be considered, and this application does not limit this.

[0160] Then, the mobile device is controlled to move based on the coordinates corresponding to the target working position, so as to move to the target working position to perform the corresponding work task.

[0161] The laser radar-based device navigation method provided in the present application obtains an environmental point cloud by collecting point cloud data of a target recognition area; extracts points belonging to at least two positioning guidance components from the environmental point cloud to obtain target component point clouds corresponding to the at least two positioning guidance components; performs vertical line fitting and horizontal line fitting on the target component point clouds corresponding to the at least two positioning guidance components, selects mutually parallel vertical lines from the vertical line fitting results corresponding to the at least two positioning guidance components, and obtains a reference line; obtains a horizontal line corresponding to each reference line, and re-performs line fitting based on the point cloud corresponding to the horizontal line to obtain a comprehensive horizontal line; calculates the coordinates corresponding to the target working position based on the intersection between the reference line and the comprehensive horizontal line, so as to calculate the coordinates of the target working position through the vertical line and horizontal line of each positioning guidance component, thereby ensuring the accuracy of the coordinates of the target working position, and the calculation process is simple and efficient, thereby improving the navigation and positioning efficiency of the device.

[0162] Figure 5 FIG. 1 is a block diagram of a device navigation apparatus based on laser radar, as shown in an exemplary embodiment of the present application. Figure 5 As shown, the exemplary laser radar-based device navigation apparatus 500 includes:

[0163] The point cloud acquisition module 510 is configured to acquire point cloud data of the target recognition area in response to the mobile device entering the target recognition area to obtain an environmental point cloud. At least two positioning guidance components are deployed within the target recognition area relative to the target working position, with the two positioning guidance components being arranged along a straight line and parallel to each other.

[0164] A point cloud extraction module 520 is configured to extract points belonging to at least two positioning guidance components from the environment point cloud, thereby obtaining target component point clouds corresponding to the at least two positioning guidance components.

[0165] Line selection module 530 is configured to perform vertical and horizontal line fitting on the target component point clouds corresponding to at least two positioning guidance components, and select mutually parallel vertical lines from the vertical line fitting results corresponding to the at least two positioning guidance components to obtain reference lines. Each vertical line corresponds to at least one mutually perpendicular horizontal line, and is perpendicular to the deployment direction of the lines corresponding to the at least two positioning guidance components.

[0166] A straight line fitting module 540 is used to obtain a horizontal line corresponding to each reference line, and re-perform straight line fitting based on the point cloud corresponding to the horizontal line to obtain a comprehensive horizontal line;

[0167] The coordinate calculation module 550 is used to calculate the coordinates corresponding to the target working position based on the intersection between the reference straight line and the integrated horizontal straight line, and use the coordinates corresponding to the target working position to control the movement of the mobile device.

[0168] It should be noted that the laser radar-based device navigation apparatus provided in the above embodiment and the laser radar-based device navigation method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the laser radar-based device navigation apparatus provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0169] See also Figure 6 , Figure 6 6 is a schematic diagram of the structure of an embodiment of an electronic device of the present application. Electronic device 600 includes memory 601 and processor 602. Processor 602 is configured to execute program instructions stored in memory 601 to implement the steps of any of the aforementioned embodiments of the device navigation method based on lidar. In a specific implementation scenario, electronic device 600 may include, but is not limited to, a microcomputer and a server. In addition, electronic device 600 may also include mobile devices such as laptops and tablet computers, which are not limited here.

[0170] Specifically, the processor 602 is used to control itself and the memory 601 to implement the steps of any of the above-mentioned embodiments of the device navigation method based on laser radar. The processor 602 can also be called a central processing unit (CPU). The processor 602 may be an integrated circuit chip with signal processing capabilities. The processor 602 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor. In addition, the processor 602 can be implemented by an integrated circuit chip.

[0171] See also Figure 7 , Figure 7The computer-readable storage medium 700 stores program instructions 710 that can be executed by a processor, and the program instructions 710 are used to implement the steps of any of the above-mentioned embodiments of the device navigation method based on laser radar.

[0172] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0173] The above description of the various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced with each other and will not be repeated herein for the sake of brevity.

[0174] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation methods described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0175] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in either hardware or software functional units. If the integrated units are implemented as software functional units and sold or used as standalone products, they may be stored on a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the portion that contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product. This computer software product, stored on a storage medium, includes instructions for causing a computer device (such as a personal computer, server, or network device) or a processor to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

Claims

1. A device navigation method based on laser radar, characterized in that: The method comprises: In response to the mobile device entering the target recognition area, point cloud data is collected for the target recognition area to obtain an environmental point cloud; wherein at least two positioning guidance components are deployed in the target recognition area relative to the target working position, and the two positioning guidance components are deployed along a straight line and parallel to each other; Extracting points belonging to the at least two positioning guidance components from the environment point cloud to obtain target component point clouds corresponding to the at least two positioning guidance components; Performing vertical line fitting and horizontal line fitting on the target component point clouds corresponding to the at least two positioning guidance components, respectively, and selecting mutually parallel vertical lines from the vertical line fitting results corresponding to the at least two positioning guidance components to obtain reference lines; wherein the vertical lines correspond to at least one mutually perpendicular horizontal line, and the vertical lines are perpendicular to the linear deployment directions corresponding to the at least two positioning guidance components; Obtaining the horizontal lines corresponding to each reference line, and re-performing line fitting based on the point cloud corresponding to the horizontal line to obtain a comprehensive horizontal line; Obtaining a relative positional relationship between the at least two positioning guidance components and the target working position; and calculating coordinates of the at least two positioning guidance components based on the intersection points between each reference line and the integrated horizontal line, and calculating orientations of the at least two positioning guidance components based on the angles between each reference line and the integrated horizontal line; The calculating of the orientations of the at least two positioning guidance components based on the angle between each reference line and the integrated horizontal line includes: obtaining a perpendicular line to each reference line and obtaining a direction vector of the integrated horizontal line; and obtaining a weighted parameter between the perpendicular line to each reference line and the direction vector of the integrated horizontal line based on a ratio between the number of point clouds corresponding to each reference line and the number of point clouds corresponding to the integrated horizontal line; and performing a weighted sum calculation on the perpendicular line to each reference line and the direction vector of the integrated horizontal line using the weighted parameter to obtain the orientations of the at least two positioning guidance components. Calculating coordinates corresponding to the target working position based on the coordinates and orientations of the at least two positioning guidance components and the relative positional relationship between the at least two positioning guidance components and the target working position; The mobile device is controlled to move using the coordinates corresponding to the target working position.

2. The method according to claim 1, characterized in that The extracting points belonging to the at least two positioning guidance components from the environment point cloud to obtain target component point clouds corresponding to the at least two positioning guidance components respectively includes: Obtaining preset appearance parameters and deployment positions of the at least two positioning guidance components; Based on the appearance parameters and deployment positions of the at least two positioning coaching components, generating point cloud screening boxes corresponding to the at least two positioning coaching components respectively; Point clouds in the environment point cloud that fall within the point cloud screening box are determined to obtain target component point clouds corresponding to the at least two positioning guidance components.

3. The method according to claim 2, characterized in that The step of determining the point clouds in the environment point cloud that fall within the point cloud screening box to obtain the target component point clouds corresponding to the at least two positioning guidance components respectively includes: Determining a straight line edge corresponding to the point cloud filtering box based on the vertices of the point cloud filtering box; Based on the position coordinate relationship between the two vertices corresponding to the straight edge and the point in the environment point cloud, detecting whether the point in the environment point cloud is on the straight edge, and if so, adding the point in the environment point cloud to the candidate point cloud set; If the point is not on the straight edge, then based on the intersection relationship between the laser beam line segment corresponding to the point in the environment point cloud and the straight edge, detect whether the point in the environment point cloud is within the point cloud filtering box; if it is within the point cloud filtering box, add the point in the environment point cloud to the candidate point cloud set; Based on the points in the candidate point cloud set, target component point clouds corresponding to the at least two positioning guidance components are obtained.

4. The method according to claim 2, characterized in that The step of determining the point clouds in the environment point cloud that fall within the point cloud screening box to obtain the target component point clouds corresponding to the at least two positioning guidance components respectively includes: Determine the point clouds in the environment point cloud that fall within the point cloud screening box, and obtain candidate point cloud sets corresponding to the at least two positioning guidance components respectively; Clustering the candidate point cloud sets corresponding to the at least two positioning guidance components respectively based on the distance between the points to obtain point cloud clusters corresponding to the at least two positioning guidance components respectively; Based on the number of points in each point cloud cluster, the point cloud clusters corresponding to the at least two positioning guidance components are screened to obtain target component point clouds corresponding to the at least two positioning guidance components.

5. The method according to claim 1, wherein The target component point cloud is composed of one or more point cloud clusters; and performing vertical straight line fitting and horizontal straight line fitting on the target component point clouds corresponding to the at least two positioning guidance components respectively includes: For a target component point cloud corresponding to any positioning guidance component, obtain any point cloud cluster in the target component point cloud to obtain a point cloud cluster to be fitted; Filtering a first preset number of points before and after the point cloud cluster to be fitted respectively to obtain a filtered point cloud cluster; Selecting a second preset number of points before and after the filtered point cloud cluster respectively, and performing straight line fitting on each of them to obtain a first straight line and a second straight line; It is detected whether the first straight line and the second straight line are perpendicular to each other. If the first straight line and the second straight line are perpendicular to each other, the first straight line and the second straight line are respectively regarded as a vertical straight line and a horizontal straight line.

6. The method according to claim 5, characterized in that The method further comprises: If the first straight line and the second straight line are not perpendicular to each other, calculating the intersection point between the first straight line and the second straight line; Filtering the points in the filtered point cloud cluster whose distances from the intersection point are greater than a first distance threshold, and selecting from the filtered points points whose distances from the first straight line and the second straight line are less than a second distance threshold, to obtain a first point set and a second point set; Re-performing straight line fitting on the first point set and the second point set respectively to obtain a new first straight line and a new second straight line; It is detected whether the new first straight line and the new second straight line are perpendicular to each other. If the new first straight line and the new second straight line are perpendicular to each other, the new first straight line and the new second straight line are respectively used as a vertical straight line and a horizontal straight line.

7. The method according to claim 1, characterized in that The step of selecting mutually parallel vertical lines from the vertical line fitting results corresponding to the at least two positioning guidance components to obtain a reference line includes: Calculating a distance between the at least two positioning guidance components based on the deployment positions of the at least two positioning guidance components to obtain an actual distance; detecting whether the vertical lines fitted by the at least two positioning guidance components are parallel to each other, and if so, calculating a linear distance between the vertical lines fitted by the at least two positioning guidance components; It is detected whether the difference between the straight-line distance and the actual spacing is less than a preset difference threshold. If it is less than the preset difference threshold, the vertical lines respectively fitted by the at least two positioning guidance components are used as reference lines.

8. A mobile device, characterized in that: The mobile device includes a memory and a processor, and the processor is configured to execute program instructions stored in the memory to implement the steps in the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program instructions, and the program instructions can be executed by a processor to implement the steps in the method according to any one of claims 1 to 7.

Images