Equipment docking method, computer equipment and storage medium

Abstract

The invention discloses an equipment docking method, computer equipment and a storage medium. The method comprises the following steps that: target equipment acquires docking related information of a docking device, and acquires a plurality of point cloud data; fitting the plurality of point cloud data to obtain a plurality of initial linear features; processing the plurality of initial linear features by using the docking related information of the docking device to obtain a target linear feature; wherein the target linear features comprise at least two target linear features in different directions; and based on the target straight line features, determining a target butt joint point so as to perform butt joint with the connection device by using the target butt joint point. According to the scheme, the accuracy of equipment docking can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of device docking, and in particular to a device docking method, a computer device and a storage medium. Background Art

[0002] As equipment becomes more and more intelligent, it can realize functions such as positioning and navigation, and is widely used in many fields such as transportation and logistics, improving operational efficiency.

[0003] Currently, when performing task operations, the device may need to dock with a docking device in the scene. During the docking process, the device and the docking device are usually docked based on information such as the location of the docking device that is preset. However, this method has the problem of inaccurate docking. Summary of the invention

[0004] The main technical problem solved by the present application is to provide a device docking method, a computer device and a storage medium, which can improve the accuracy of device docking.

[0005] In a first aspect, the present application provides a method for docking a device, the method comprising: a target device obtains docking-related information of a docking device, and obtains a number of point cloud data; fits the number of point cloud data to obtain a number of initial straight line features; uses the docking-related information of the docking device to process the number of initial straight line features to obtain a target straight line feature; wherein the target straight line feature includes at least two target straight line features in different directions; based on the target straight line feature, determines a target docking point, so as to use the target docking point to dock with the docking device.

[0006] A second aspect of the present application provides a computer device, which includes a memory and a processor coupled to each other, wherein program data is stored in the memory, and the processor is used to execute the program data to implement any step of the docking method of the above-mentioned device.

[0007] A third aspect of the present application provides a computer-readable storage medium, which stores program data that can be executed by a processor, and the program data is used to implement any step of the docking method of the above-mentioned device.

[0008] The above scheme obtains docking-related information of the docking device and a number of point cloud data through the target device, fits the number of point cloud data, obtains a number of initial straight line features, and then uses the docking-related information of the docking device to process the number of initial straight line features to obtain target straight line features, wherein the target straight line features include at least two target straight line features in different directions, and the target docking point is determined based on the target straight line features. The target docking point can be identified according to the scene, docking device, etc., and a more accurate target docking point can be obtained. The target docking point is used to dock with the docking device to improve the accuracy of device docking.

[0009] 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

[0010] In order to more clearly illustrate the technical solutions in this application, the following briefly introduces the drawings required in the description of the embodiments. Obviously, the drawings described below are only some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0011] Figure 1 It is a flowchart of the first embodiment of the docking method of the device of the present application;

[0012] Figure 2 It is a structural schematic diagram of an embodiment of the target device of the present application;

[0013] Figure 3 It is an exemplary schematic diagram of an embodiment of a working environment of the target device of the present application;

[0014] Figure 4 It is an exemplary schematic diagram of an embodiment of the docking device of the present application;

[0015] Figure 5 This application Figure 1 A schematic diagram of a flow chart of an embodiment of step S12;

[0016] Figure 6 This application Figure 1 A schematic diagram of a flow chart of an embodiment of step S13;

[0017] Figure 7 This application Figure 1 A schematic diagram of a flow chart of an embodiment of step S14;

[0018] Figure 8 This is an example schematic diagram of an embodiment of the related parameters of the present application;

[0019] Fig. 9It is a flow chart of the second embodiment of the docking method of the device of the present application;

[0020] Fig.10 It is a structural schematic diagram of an embodiment of a docking device of the device of the present application;

[0021] Fig.11 It is a structural schematic diagram of an embodiment of a computer device of the present application;

[0022] Fig.12 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] The terms "first" and "second" in this application are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0025] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0026] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: 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 objects associated before and after 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.

[0027] The present application provides the following embodiments, and each embodiment is described in detail below.

[0028] It is understandable that the device docking method in the present application can be executed by a computer device, and the computer device can be any device with processing capabilities, such as a target device, a computer, a server, a mobile robot, etc., and the present application does not limit this. In some possible implementations, the device docking method can be implemented by a processor calling program data stored in a memory.

[0029] See also Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for docking a device of the present application. The method may include the following steps:

[0030] S11: The target device obtains docking-related information of the docking device, and obtains a number of point cloud data.

[0031] The target device may be any movable device such as a mobile robot or a vehicle, for example, a handling robot, a service robot, a sweeping robot, etc. For example, the target device may include an AGV (Automated Guided Vehicle), an AMR (Autonomous Mobile Robot), or a sorting robot, etc. The following description of the present application takes the example that the target device includes a mobile robot, and the present application does not limit the target device.

[0032] Among them, the target device may be equipped with at least a radar device, which is used to collect point cloud data and can be used for posture estimation to achieve functions such as navigation and positioning. For example, the radar device may be a laser radar, a millimeter wave radar, etc. Exemplarily, this application uses a laser radar as an example for explanation, and the radar device may be a 3D (3 Dimensions, three-dimensional) laser radar sensor, a 2D (2 Dimensions, two-dimensional) laser radar sensor, etc. This application does not limit the radar device. In some application scenarios, the target device may also be equipped with at least one other mileage sensor, such as other mileage sensors including IMU (Inertial Measurement Unit, inertial measurement unit), wheel odometer, visual odometer, etc. This application does not limit this. The point cloud data collected by the radar device and the sensor data collected by at least one other mileage sensor can be combined for posture estimation to achieve functions such as navigation and positioning. This application does not limit the sensors installed on the target device.

[0033] In some implementations, the target device moves to the identification preparation point, and detects the working environment at the identification preparation point to obtain a number of point cloud data. Thus, the upper layer sends a number of point cloud data and docking related information of the docking device to the target device. Among them, the working environment can be the environment where the target device is located, such as a storage environment, an indoor environment, a docking environment, etc., and this application does not limit this.

[0034] For example, see Figure 2 , taking the target device including a mobile robot 101 as an example, the mobile robot 101 is provided with a radar device 102 and a driving wheel 103 with an encoder, etc. For example, the radar device 102 can be a 2D laser radar. In addition, the mobile robot 101 also includes a mobile chassis (such as a motion controller, a motor, a battery, an embedded computer, an odometer, etc.) and a lifting device, etc., which are not limited in this application. The mobile machine 101 can obtain point cloud data of the current frame in the target environment through the radar device 102. The target environment can be the environment where the mobile robot 101 is located, such as a storage environment.

[0035] Exemplarily, taking a warehousing environment as an example, when the target device is performing a task operation, the mobile robot can navigate through a topological route map, in which the mobile robot's moving route and the nodes that the mobile robot needs to pass through and reach are marked. These nodes will mark the location / area of ​​the docking device in the working environment, such as marking the outfeed rack area, pallet area, etc., which can indicate that the mobile robot needs to move to the location on the corresponding map of the rack. The mobile robot navigates through an odometer / lidar, etc., and moves to the identification preparation point corresponding to the docking device. Then, the upper layer sends a number of point cloud data and docking-related information of the docking device to the mobile robot. Among them, the point cloud data may include point cloud data collected at the identification preparation point and / or before.

[0036] For example, see Figure 3 Taking the working environment of a mobile robot as an example, the mobile robot can use a radar device to collect point cloud data based on a warehouse environment to generate a two-dimensional grid map for high-precision positioning. The two-dimensional grid map includes shelves, goods, workbenches, support walls, racks that need to be moved, and other components. The mobile robot can use the odometer to estimate the change in the movement of the mobile robot, and use the radar device to scan the environmental contour point cloud data for positioning and navigation. For this environment scan to obtain point cloud data, multiple point cloud data can belong to the same laser beam, that is, multiple point cloud data can be point cloud data on the same laser beam.

[0037] The docking device may include a rack, a shelf, a docking platform, a pallet, etc. This application does not limit the docking device. Figure 4 The connecting device is a material rack, which may include three wall panels, and there is a connectable area in the material rack.

[0038] In some embodiments, the docking-related information of the docking device includes at least one of the following: The docking-related information of the docking device includes at least one of the following: scale information, preset docking point, current posture of the target device, docking parameters, etc. For example, the scale information includes the length L, width W, height H, etc. of the docking device. This embodiment is explained by taking the scale information including the length L and width W of the docking device as an example. The preset docking point P represents the ideal docking position corresponding to the docking device. For example, the docking parameters include a preset docking coordinate system, the relative posture between the coordinate systems, the conversion relationship, etc., which is not limited in this application. The preset docking coordinate system represents the coordinate system used for docking, and the docking process can refer to the coordinate system to determine the relevant posture required for docking.

[0039] In some embodiments, after acquiring a number of point cloud data, the point cloud data are preprocessed, and the preprocessing includes distance filtering. In the radar device coordinate system (e.g., laser radar coordinate system), all point cloud data are filtered according to distance, and point cloud data whose distance from the preset docking point is greater than the set distance d1 is eliminated. For example, when the distance between the detected point cloud data and the preset docking point P is greater than the set distance d1, the point cloud data is eliminated, that is, it is considered that the point cloud data is not point cloud data on the contour of the docking device (e.g., material rack). The set distance can be a preset multiple of the longest side of the docking device, for example, the set distance can be twice the longest side of the docking device. This application does not limit this.

[0040] S12: Fitting a number of point cloud data to obtain a number of initial straight line features.

[0041] Straight line fitting can be performed on a number of point cloud data to obtain a number of initial straight line features, wherein each initial straight line feature may include a fitted straight line and a corresponding straight line point cloud set, the straight line point cloud set contains a plurality of point cloud data, and the fitted straight line represents a straight line segment obtained by fitting the plurality of point cloud data.

[0042] In some implementations, a straight line fitting may be performed on each point cloud data according to its position, and the fitted straight line is used as a number of initial straight line features. Multiple point cloud data that can fit the initial straight line are used as a straight line point cloud set.

[0043] In some implementations, the point cloud data may be divided into multiple linear point cloud sets according to their positions, and then linear fitting is performed on the point cloud data in each linear point cloud set to obtain a number of initial linear features. This application does not limit the fitting method of the multiple point cloud data.

[0044] In some embodiments, see Figure 5 , step S12 of the above embodiment can be further expanded. Fitting a number of point cloud data to obtain a number of initial straight line features, this embodiment may include the following steps:

[0045] S121: Fitting a plurality of point cloud data using a preset straight line fitting algorithm to obtain a plurality of straight line segments and a corresponding straight line point cloud set.

[0046] A preset straight line fitting algorithm can be used to fit a number of point cloud data, and a number of fitted straight line segments and a straight line point cloud set corresponding to each straight line segment can be obtained, and the straight line point cloud set contains a plurality of point cloud data.

[0047] During the docking process of the target device, the head of the target device is basically facing the docking device. In the straight line extraction process, for example, straight line fitting can be started from the point cloud data of the intermediate sequence collected by the radar device. The intermediate sequence means that a number of point cloud data are sorted according to sequence numbers, and straight lines can be extracted starting from the middle sequence number. For another example, straight lines can be extracted starting from the head sequence and / or the tail sequence. The following is an example of extracting a straight line starting from the intermediate sequence, and this application does not limit this.

[0048] In some implementations, fitting a plurality of point cloud data includes the following steps:

[0049] When extracting a straight line starting from point cloud data pi, point cloud data pi and a preset number of adjacent point cloud data may constitute a current straight line point cloud set {Cpi}. For example, three points may be taken from the left and right sides of the point cloud data pi, which are adjacent in sequence, to form the current straight line point cloud set {Cpi}. A preset straight line fitting algorithm is used to perform straight line fitting on the point cloud data included in the current straight line point cloud set {Cpi} to obtain the current straight line segment Lci.

[0050] Some point cloud data can be traversed in the first order. For example, traverse from the line segment endpoint epi1 of the current straight line point cloud set {Cpi} in the direction of increasing sequence number id, that is, other point cloud data except the current straight line point cloud set {Cpi} can be traversed. If the distance from the point cloud data to the current straight line segment Lci is greater than the preset distance threshold, it is considered that the point cloud data is not a point on the current straight line segment Lci, and the next point is traversed. If the distance is less than or equal to the preset distance threshold, the point cloud data is added to the current straight line point cloud set {Cpi}, and the preset straight line fitting algorithm is used to perform straight line fitting on the point cloud data contained in the current straight line point cloud set {Cpi}, and the current straight line segment Lci is updated.

[0051] If the point cloud data does not belong to the current straight line segment Lci, the forward growth ends and the backward growth begins. That is, the other end point epi2 of the current straight line segment Lci is traversed in the direction of decreasing sequence number id. Similarly, it is determined in turn whether the distance from the next point cloud data to the current straight line segment Lci is greater than the preset distance threshold. If the distance is less than or equal to the preset distance threshold, the point cloud data is added to the current straight line point cloud set {Cpi}, and the preset straight line fitting algorithm is used to perform straight line fitting on the point cloud data contained in the current straight line point cloud set {Cpi}, and the current straight line segment Lci is updated.

[0052] When the current straight line segment grows to both ends, the generation of the straight line segment ends when the end point of the previous straight line segment (such as the endpoint with a larger sequence number) is reached, and a generated straight line segment and a corresponding straight line point cloud set are obtained. This method can avoid the problem of overlapping areas between two straight line segments, which will lead to subsequent deduplication processing.

[0053] Through the above method, several straight line segments and corresponding straight line point cloud sets can be obtained.

[0054] In some embodiments, the preset straight line fitting algorithm may include a least squares method, a gradient descent method, a Gauss-Newton method, a Levenberg-Marquardt algorithm (LM method), etc. It is understandable that the preset straight line fitting algorithm can be determined according to different application scenarios, and the present application does not limit this.

[0055] Exemplarily, the present application takes the preset straight line fitting algorithm including the least square method as an example for explanation. The straight line segment can be represented by a straight line equation: ax+by+c=0, where a, b, c are coefficients in the straight line equation. The least square method can be used to perform straight line fitting on a number of point cloud data included in the current straight line point cloud set {Cpi} to obtain the coefficients (a, b, and c) of the straight line segment.

[0056] In some implementations, the preset straight line fitting algorithm can be expressed by the following formula:

[0057]

[0058] Among them, the intermediate results used by each coefficient can be expressed as:

[0059] m1=∑ i x i .

[0060] m2=∑ i y i .

[0061] w1=N·∑ i x i y i -∑ i x i ·∑ i y i .

[0062]

[0063] w3=∑ i x i ·∑ i y i -N·∑ i x i y i .

[0064] In the above formula, xi and yi are the x- and y-direction coordinates of the i-th point cloud data in the current line point cloud set {Cpi}, respectively. N represents the number of point cloud data contained in the current line point cloud set {Cpi}.

[0065] S122: Projecting the endpoints in the line point cloud set to the corresponding line segments to obtain projected endpoints.

[0066] Since the endpoints of a straight line segment may be intersection points, or affected by the tailing of the line, that is, the endpoints in the line point cloud set may not be on the straight line segment, resulting in the two endpoints being far away from the straight line segment. Therefore, before merging the straight line segments, the endpoints of the straight line segments in the line point cloud set are projected to the corresponding straight line segments to obtain the projected endpoints.

[0067] In some implementations, a preset projection algorithm is used to project each endpoint onto a corresponding straight line segment to obtain a corresponding projection endpoint. The preset projection algorithm can be expressed by the following formula:

[0068]

[0069] In the above formula, x0 and y0 represent the x and y coordinates of one end point (such as the starting point) of the straight line segment, respectively. s ,y s They represent the projection endpoints (x0, y0) of the straight line segment. n ,y n They represent the x and y coordinates of the other end point of the straight line segment (such as the end point), respectively. e ,y e Respectively represent the endpoints (x n ,y n ) is projected to the projection endpoint (projection end point) of the straight line segment.

[0070] S123: using the projection endpoints, merging a plurality of straight line segments to obtain a merged straight line segment as an initial straight line feature, so as to obtain a plurality of initial straight line features.

[0071] According to the serial number on each straight line segment, the projection endpoints of adjacent straight line segments are traversed in turn. Thus, the projection endpoints of adjacent straight line segments are used to determine whether the adjacent straight line segments need to be merged. In this way, a merged straight line segment can be obtained. In this way, several straight line segments can be merged to obtain a merged straight line segment, and the merged straight line segment is used as the initial straight line feature.

[0072] In some embodiments, it is determined whether the projection endpoints corresponding to two adjacent straight line segments meet a preset merging condition, wherein the preset merging condition includes: the distance between the projection endpoints corresponding to the two adjacent straight line segments is less than a first distance threshold d_th, and the distance from the projection endpoint corresponding to a straight line segment to the other straight line segment is less than a second distance threshold l_th. For example, if the distance between the projection endpoint of the previous straight line segment and the projection starting point of the next straight line segment is less than the first distance threshold d_th, and in the two adjacent straight line segments, the distances from the two projection endpoints of one straight line segment to the other straight line segment are both less than the second distance threshold l_th, then it is determined that the preset merging condition is met.

[0073] If the preset merging condition is met, in response to the projection endpoints corresponding to the two adjacent straight line segments meeting the preset merging condition, the straight line point cloud sets corresponding to the two adjacent straight line segments are merged to obtain a merged point cloud set; the point cloud data contained in the merged point cloud set is fitted using a preset straight line fitting algorithm to obtain a merged straight line segment. That is, the two straight line segments are merged into one straight line segment, the straight line point cloud sets corresponding to the two straight line segments are merged, and the point cloud data on the two straight line segments can be refitted to calculate the straight line segment to obtain the merged straight line segment.

[0074] Through the above method, multiple straight line segments can be obtained or merged straight line segments can be used as initial straight line features to obtain a fitting straight line and a corresponding straight line point cloud set.

[0075] Continue reading Figure 1 , after the above step S12, the following steps are also included:

[0076] S13: using docking-related information of the docking device, processing a number of initial straight line features to obtain target straight line features; wherein the target straight line features include at least two target straight line features in different directions.

[0077] The docking related information of the docking device can be used to process a number of initial straight line features to extract the target straight line features. For example, the scale information of the docking device can be used to extract the target straight line features from a number of initial straight line features. The target straight line features include target straight line features in at least two different directions, and each direction can include at least one target straight line feature.

[0078] In some embodiments, the target straight line feature includes a first straight line feature and a second straight line feature in two different directions, the first straight line feature corresponds to a first direction, the first direction is determined based on at least a portion of the point cloud data included in the first straight line feature, and the second straight line feature corresponds to a second direction, the first direction and the second direction are different, and the second direction is determined based on the first direction.

[0079] Exemplarily, the target straight line feature may include two first straight line features and one second straight line feature, for example, extracting two parallel straight lines and one vertical line, that is, fitting the three faces of the docking device through three straight line features. It is understandable that when the docking device includes other faces or other angles, etc., the target straight line feature may also be extracted according to the specific application scenario, and this application does not limit this.

[0080] In some embodiments, see Figure 6 , step S13 of the above embodiment can be further expanded. Using the docking related information of the docking device, a number of initial straight line features are processed to obtain the target straight line feature. This embodiment may include the following steps:

[0081] S131: Determine an initial straight line feature that satisfies a first screening condition from among a plurality of initial straight line features, and obtain at least two first straight line features.

[0082] A straight line set {CLi} of several initial straight line features is obtained, and an initial straight line feature satisfying a first screening condition is searched from the straight line set {CLi} as a first straight line feature, wherein the number of the first straight line features is at least two.

[0083] Among them, the first screening condition and the second screening condition at least include different scale conditions corresponding to the docking related information of the docking device. The first screening condition and the second screening condition can be determined according to the scale information of the docking device. For example, the first screening condition is determined by the first scale included in the scale information, and the second screening condition is determined by the second scale included in the scale information. Exemplarily, the scale information includes length and width, and the first screening condition is determined by length and the second screening condition is determined by width as an example. This application can be set according to specific application scenarios, and this application does not limit this.

[0084] In some embodiments, the first screening condition includes a parallel condition and a first scale condition, the first scale condition is determined based on the first scale (such as length L) of the docking device, the parallel condition is that the difference in parallelism or direction angle between the initial straight line features is less than a preset difference threshold pa_th, and the first scale condition is that the difference between the length of the initial straight line feature and the length L of the docking device is less than a preset length difference. In this way, at least two first straight line features Lk1 and Lk2 can be extracted. For example, the first straight line features Lk1 and Lk2 are two parallel line segments.

[0085] S132: Determine a first direction corresponding to the first straight line feature using at least a portion of the point cloud data included in at least two first straight line features.

[0086] Among them, at least part of the point cloud data contained in the first straight line feature can represent the point cloud data of the intermediate sequence of the first straight line feature or representative point cloud data, etc. The present application does not limit at least part of the point cloud data. At least part of the point cloud data contained in the first straight line feature can be used to determine the first direction corresponding to the first straight line feature, thereby reducing the straight line fitting error introduced by the endpoints of the straight line segment.

[0087] In some embodiments, the center point of each first straight line feature is determined, and the center points of the line segments of the first straight line features Lk1 and Lk2 are recorded as Lkc1 and Lkc2, respectively. With the center points Lkc1 and Lkc2 as the center, respectively, the point cloud data within the preset point cloud range of the center points Lkc1 and Lkc2 are acquired on the corresponding first straight line features to obtain at least part of the point cloud data. The preset point cloud range is related to the first scale (such as length) of the docking device. For example, the preset point cloud range includes a first preset ratio of the first scale (such as length) of the docking device. Exemplarily, from the first straight line features, with the center points Lkc1 and Lkc2 as the center, respectively, the point cloud data within 0.4*L between the center points Lkc1 and Lkc2 are intercepted on both sides of the center points to obtain at least part of the point cloud data.

[0088] Then, a preset straight line fitting algorithm is used to perform straight line fitting on at least part of the point cloud data to obtain a reference fitting straight line, that is, the re-fitted first straight line feature can be obtained, and the reference fitting straight lines are respectively recorded as Lk1 and Lk2.

[0089] Finally, the first direction DRk is determined based on the directions corresponding to the reference fitting lines Lk1 and Lk2. For example, the direction corresponding to one of the reference fitting lines Lk1 and Lk2 can be used as the first direction DRk. For another example, the directions corresponding to the reference fitting lines Lk1 and Lk2 can be combined to determine the first direction DRk, for example, the average value of the directions corresponding to the reference fitting lines Lk1 and Lk2 is obtained as the first direction DRk. This application does not limit this.

[0090] S133: Determine a second direction based on the first direction.

[0091] A second direction VDR that satisfies a preset angle condition with the first direction is determined according to the first direction. The angle between the second direction and the first direction satisfies the preset angle condition. The preset angle condition may indicate that the angle between the second direction and the first direction differs by a preset angle. For example, the second direction and the first direction meet a vertical relationship, and the second direction differs from the first direction by 90 degrees. This is used as an example for explanation below. For another example, the second direction differs from the first direction by 60 degrees. For another example, the second direction differs from the first direction by 45 degrees. For another example, the second direction differs from the first direction by 35 degrees. It is understandable that the present application may set a preset angle condition in an application scenario, and the present application does not limit the preset angle condition.

[0092] S134: Determine an initial straight line feature that satisfies a second screening condition from among the plurality of initial straight line features, and obtain at least one second straight line feature.

[0093] From the line set {CLi} of several initial straight line features, the initial straight line features that meet the second screening condition are screened out to obtain at least one second straight line feature Lw. The second screening condition includes: a second direction condition and a second scale condition, and the second scale condition is determined based on the second scale (such as width W) of the docking device. For example, the second scale condition is that the difference between the length of the initial straight line feature and the width W of the docking device is less than the preset width difference, and the second direction condition is that the difference between the direction of the initial straight line feature and the second direction VDR is less than the preset angle difference. In this way, an initial straight line feature that is close to the second direction VDR and whose length is close to the width W of the docking device can be extracted as the second straight line feature Lw. For example, the second straight line feature Lw is a vertical line segment perpendicular to two parallel line segments.

[0094] In some embodiments, there may be multiple second straight line features Lw that meet the conditions. Therefore, in response to the number of second straight line features being greater than a preset number, for example, the preset number is 1, a second straight line feature that meets the third screening condition can be determined to obtain the final second straight line feature. The third screening condition includes at least one of the following: the distance between the center point of the second straight line feature and the center point of the first straight line feature belongs to a preset distance range, and the center point of the second straight line feature and the center point of the first straight line feature meet a preset position relationship. The preset distance range is related to the first scale (such as length L) of the docking device. For example, the preset distance range is within a preset difference range of a second preset ratio of the first scale (such as length) of the docking device. Exemplarily, the preset distance range includes a preset difference range of L / 2. The preset position relationship is that the center points are all within the preset side of the second straight line feature.

[0095] Exemplarily, if there are multiple second straight line features Lw, for the jth second straight line feature Lwj, where j is an integer, the distance from the center point of the first straight line feature (such as Lkc1) to the second straight line feature Lwj, as well as the positional relationship between the center points of each first straight line feature (such as Lkc1 and Lkc2) and the second straight line feature Lwj are calculated. If the distance from Lkc1 to the second straight line feature Lwj is close to L / 2, and the center points Lkc1 and Lkc2 are both on the preset side of the second straight line feature Lwj (such as above), the second straight line feature Lwj can be determined as the final second straight line feature Lw, that is, a vertical line segment. The preset side can represent the side where the center point is away from the target device.

[0096] The above scheme uses the parallel and perpendicular constraint relationship of the straight line feature and the scale information of the docking device to quickly screen out the initial straight line features that meet the conditions from the set of extracted initial straight line features, and can obtain at least two parallel first straight line features Lk1 and Lk2 and at least one second straight line feature Lw perpendicular thereto. In addition, the first straight line feature is refitted by taking point cloud data of a fixed length from both sides of the center point of the first straight line feature to improve the accuracy of the first straight line feature fitting, thereby determining a more accurate first direction and reducing the error caused by the endpoints of the straight line segment.

[0097] Continue reading Figure 1 , after the above step S13, the following steps are also included:

[0098] S14: Determine a target docking point based on the target straight line feature, so as to dock with the docking device using the target docking point.

[0099] The target docking point can be determined by using the target straight line feature and docking related information of the docking device. The docking related information includes at least one of the following: a preset docking point, the current position of the target device, docking parameters, etc. The target docking point indicates the position where the target device finally stops during the docking process. The target docking point can be used to dock with the docking device.

[0100] The above scheme obtains docking-related information of the docking device and a number of point cloud data through the target device, fits the number of point cloud data, obtains a number of initial straight line features, and then uses the docking-related information of the docking device to process the number of initial straight line features to obtain target straight line features, wherein the target straight line features include at least two target straight line features in different directions, and the target docking point is determined based on the target straight line features. The target docking point can be identified according to the scene, docking device, etc., and a more accurate target docking point can be obtained. The target docking point is used to dock with the docking device to improve the accuracy of device docking.

[0101] In some embodiments, see Figure 7 , step S14 of the above embodiment can be further expanded. Based on the target straight line feature, the target docking point is determined to dock with the docking device using the target docking point. This embodiment may include the following steps:

[0102] S141: Obtain the intersection points between each first straight line feature and the second straight line feature respectively.

[0103] The intersection points between each first straight line feature and the second straight line feature are obtained respectively to obtain a plurality of intersection points. For example, the intersection points between the parallel first straight line features Lk1 and Lk2 and the perpendicular second straight line feature Lw are obtained respectively to obtain two intersection points, which are recorded as G1 and G2.

[0104] S142: Determine a target docking point using the intersection point and docking related information of the docking device.

[0105] The target docking point can be determined by utilizing docking-related information of each intersection point and the docking device, such as a preset docking point, a current position of the target device, docking parameters, etc.

[0106] In some embodiments, the target docking coordinate system is obtained using each intersection. The center point G0 of each intersection is obtained, and the center point is used as the coordinate origin of the target docking coordinate system. For example, the center point G0 of the intersection G1 and the intersection G2 is used as the coordinate origin. Then the direction of the first axis is determined based on the direction corresponding to the first straight line feature. For example, the direction of the first axis is the x-axis direction. Exemplarily, the average direction of the first straight line features Lk1 and Lk2 is obtained, and the direction toward the second straight line feature is the first axis. In this way, the target docking coordinate system {D} is established based on the coordinate origin and the first axis. For example, the target docking coordinate system {D} is established using the right-hand rule.

[0107] The target docking point is determined based on the target docking coordinate system and the docking related information of the docking device. The target docking coordinate system can be used to transform the preset docking point P to the target docking coordinate system {D} to obtain the transformed docking point (Qx, Qy, Qa,), where Qx, Qy, and Qa represent the x-axis, y-axis, and attitude angle, respectively. Then, the target docking point is determined using the docking parameters, the transformed docking point, and the current posture.

[0108] In some embodiments, the target docking point can be expressed by the following formula:

[0109] Tmd=Tmb*TbL*TLd*Td formula (3)

[0110] Among them, Tmd represents the target docking point, that is, the target point where the target device is expected to stop when the docking is successful, and represents the posture in the world coordinate system, which can be constructed by Qx, Qy and Qa.

[0111] For example, see Figure 8 , Tmb represents the current posture of the target device 201, that is, the posture of the identified target device 201 in the world coordinate system. TbL represents the docking parameter, that is, the external parameter of the device center of the radar device 202 relative to the target device 201. TLd represents the posture of the target docking coordinate system {D} relative to the radar coordinate system of the radar device 202. Td represents the preset docking point, that is, the conversion docking point, which represents the preset expected posture of the target device 201 when it stops in the target docking coordinate system {D} when successfully docked with the docking device 203.

[0112] S143: docking with the docking device based on the target docking point.

[0113] The target device can be docked with the docking device based on the target docking point. During the docking process between the target device and the docking device, the target device switches to the odometer mode for docking. Using the above determined target docking point for docking can greatly reduce the calibration requirements for docking.

[0114] In some embodiments, during the docking process between the target device and the docking device, after the docking begins, point cloud data is continuously collected, and at least two first straight line features, such as Lk1 and Lk2, are continuously acquired. This part can refer to the specific implementation process of acquiring the first straight line features in the above embodiment, which will not be repeated here.

[0115] Each point cloud data is converted to the device coordinate system of the target device, and the distance between the target device and the first straight line feature is obtained respectively to obtain the moving distance (such as d1 and d2). The moving distance is fed back to the motion control module of the target device, so that the target device can be controlled to move to the target docking point according to the moving distance, and the target device is kept as close as possible to the perpendicular midline of the docking device for docking.

[0116] The above scheme can determine a more accurate target docking point, and then docking with the target docking point can greatly reduce the calibration requirements for docking. During the docking process, at least two first straight line features are continuously obtained, and the distance between the target device and the first straight line features is obtained respectively to obtain the moving distance. The target device is controlled to move toward the target docking point according to the moving distance. The target device is kept as close as possible to the mid-vertical line of the docking device for docking. Continuous identification can be performed during the movement to further eliminate the accumulated error of the odometer and improve the accuracy of the final docking.

[0117] In some embodiments, after the above step S13, it is also possible to determine whether there is any abnormal docking situation in the area corresponding to the docking device based on the acquired target straight line features, so as to determine whether to dock with the docking device.

[0118] See also Fig. 9 , Fig. 9 1 is a flow chart of the second embodiment of the method for docking the device of the present application. The method may include the following steps:

[0119] S21: Using the target straight line feature, detect whether there is any abnormal connection.

[0120] Among them, the abnormal docking situation includes: there are obstacles in the corresponding area of ​​the docking device. For example, the obstacle can be an object, for example, the obstacle can be other target equipment, the docking device is a material rack, and there may be another mobile robot in the docking material rack that failed to exit in time due to a fault, etc. Therefore, it is possible to continuously detect whether there are obstacles in the corresponding area of ​​the material rack within a distance from the docking device.

[0121] In some embodiments, the target straight line feature referred to in this step may refer to the target straight line feature obtained in the above step S13, and / or, during the docking process between the target device and the docking device, point cloud data is continuously collected and the target straight line feature is continuously obtained based on the point cloud data. The target straight line feature includes at least two first straight line features and at least one second straight line feature. The present application does not limit the target straight line feature of this step.

[0122] The target straight line feature can be used to detect whether there is an abnormal connection, that is, whether there is an obstacle in the corresponding area of ​​the docking device.

[0123] In some embodiments, if the first straight line features Lk1, Lk2 and the second straight line feature Lw in the target straight line feature can be successfully fitted, in response to obtaining the first straight line feature and the second straight line feature, the first docking area R1 is determined using the first straight line feature (Lk1, Lk2), the second straight line feature Lw and the scale information of the docking device. The direction of the first side of the first docking area R1 is the first direction or the average direction corresponding to the first straight line feature Lk1 / Lk2, and the length of the first side is the length L of the docking device. The direction of the second side of the first docking area is the second direction corresponding to the second straight line feature Lw, and the width of the second side is the width W of the docking device.

[0124] Exemplarily, a rectangular area is constructed using the three fitted straight line features Lk1, Lk2 and Lw and the length L and width W of the docking device to obtain a first docking area R1, wherein the long side direction of the first docking area R1 is consistent with the direction of the first straight line feature Lk1, with a length of L, and the width direction is consistent with the direction of the second straight line feature Lw, with a width of W.

[0125] Then, traverse each point cloud data to determine whether each point cloud data is in the first docking area R1, so as to obtain each point cloud data in the first docking area R1, and detect whether the point cloud data in the first docking area R1 meets the abnormal condition. If the abnormal condition is met, in response to meeting the abnormal condition, it is determined that a docking abnormality occurs, there is an obstacle in the first docking area R1, and it is determined that the target device does not enter docking temporarily.

[0126] Among them, the point cloud data in the first docking area R1 can be clustered to obtain several clusters. If the length corresponding to the point cloud data of the cluster is greater than the length threshold, and the number of clusters greater than the length threshold is greater than the number threshold, it is determined that the abnormal condition is met and it is considered that there is an obstacle in the corresponding area of ​​the docking rack.

[0127] In some embodiments, if the first straight line features Lk1 and Lk2 of the target straight line features can be fitted successfully, but the second straight line feature Lw cannot be fitted, that is, the first straight line feature can be obtained but the second straight line feature cannot be obtained, then in response to the first straight line feature being obtained but the second straight line feature not being available, it is determined that an abnormal docking situation has occurred. In this case, it can be directly determined that there is an obstacle in the corresponding area of ​​the docking device, and the target device does not enter docking.

[0128] In some embodiments, if the first straight line features Lk1, Lk2 and the second straight line features Lw in the target straight line features are all unsuccessfully fitted, that is, the first straight line features and the second straight line features cannot be obtained, it can be further determined whether the detection of the point cloud data meets the abnormal condition. For example, if the point cloud ranging is less than the ranging threshold, and there is no abnormality in response to the laser inspection of the radar device, it can be determined that the no abnormal condition is met.

[0129] In response to the acquisition that there is no first straight line feature, no second straight line feature, and the detection of the point cloud data satisfies the absence of abnormal conditions, the second docking area R2 can be determined using the scale information (length L and width W) of the docking device, the preset docking point P (Px, Py) and the pose (such as Mx, My) of the preset docking coordinate system. Among them, the center coordinates of the second docking area R2 can be determined using the scale information (length L and width W), the preset docking point P (Px, Py) and the pose (Mx, My, Ma) of the preset docking coordinate system. For example, a rectangular area can be constructed, and the first difference between half of the length L and the x-axis coordinate of the preset docking coordinate system can be obtained, and then the difference between the x-axis coordinate of the preset docking point P and the first difference can be obtained to obtain the x-axis coordinate of the center coordinate point; the second difference between half of the width W and the y-axis coordinate of the preset docking coordinate system is obtained, and then the difference between the y-axis coordinate of the preset docking point P and the second difference is obtained to obtain the y-axis coordinate of the center coordinate point. The length of the second docking area R2 is L and the width is W. The direction of the constructed matrix area can refer to the direction of the preset docking coordinate system, that is, the direction of the attitude angle Ma.

[0130] The center coordinates of the second docking area R2 can be obtained by the following formula:

[0131]

[0132] Among them, (Pcx, Pcy) respectively represent the x-axis and y-axis coordinates of the center coordinates, (Px, Py) respectively represent the x-axis and y-axis coordinates of the preset docking point P, (Mx, My) respectively represent the x-axis and y-axis coordinates of the preset docking coordinate system, L represents the length of the docking device, and W represents the width of the docking device.

[0133] The point cloud data in the second docking area R2 is obtained, and whether the point cloud data in the second docking area meets the abnormal condition is detected. In response to meeting the abnormal condition, it is determined that the docking abnormality occurs. This part can refer to the specific implementation method of the detection process of the docking abnormality in the first docking area R1, and this application will not repeat it here.

[0134] Optionally, in response to a connection abnormality, the following step S22 is performed.

[0135] Optionally, in response to no abnormal connection situation occurring, the following step S23 is performed.

[0136] S22: Determine not to dock with the docking device.

[0137] In response to the occurrence of a docking abnormality, it is determined not to dock with the docking device. In the case where an abnormal docking situation is detected and there is an obstacle in the corresponding area of ​​the docking device, it can be determined not to dock with the docking device, which can improve the accuracy of docking.

[0138] S23: Determine a target docking point based on the target straight line feature, so as to dock with the docking device using the target docking point.

[0139] When it is detected that there is no abnormal docking and there are no obstacles in the corresponding area of ​​the docking device, in response to the absence of abnormal docking, it is determined that docking with the docking device can be carried out, and then based on the target straight line feature, the target docking point is determined, so that the target device can be docked with the docking device using the target docking point, which can improve the accuracy of the docking.

[0140] It is understandable that in the above method of the specific implementation mode, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0141] In some embodiments, the present application also provides a docking device for a device, used to implement the docking method for the device of any of the above embodiments.

[0142] See also Fig.10 , Fig.10 1 is a schematic diagram of the structure of an embodiment of a docking device of the present application. The docking device 30 of the device includes an acquisition module 31, a fitting module 32, an extraction module 33 and a docking module 34. The modules are interconnected.

[0143] The acquisition module 31 is used for the target device to obtain docking related information of the docking device, and to obtain a number of point cloud data. The fitting module 32 is used to fit a number of point cloud data to obtain a number of initial straight line features. The extraction module 33 is used to process a number of initial straight line features using the docking related information of the docking device to obtain a target straight line feature; wherein the target straight line feature includes at least two target straight line features in different directions. The docking module 34 is used to determine the target docking point based on the target straight line feature, so as to use the target docking point to dock with the docking device.

[0144] It should be noted that the docking device of the device provided in the above embodiment and the docking method of the device provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment and will not be repeated here. In practical applications, the docking device of the device provided in the above embodiment can distribute 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 application does not limit this.

[0145] For the above embodiment, the present application provides a computer device, see Fig.11 , Fig.11 1 is a schematic diagram of the structure of an embodiment of a computer device of the present application. The computer device 40 includes a memory 41 and a processor 42, wherein the memory 41 and the processor 42 are coupled to each other, the memory 41 stores program data, and the processor 42 is used to execute the program data to implement the steps of any embodiment of the above-mentioned device docking method.

[0146] In this embodiment, the processor 42 may also be referred to as a CPU (Central Processing Unit). The processor 42 may be an integrated circuit chip having the ability to process signals. The processor 42 may 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. A general-purpose processor may be a microprocessor or the processor 42 may also be any conventional processor, etc.

[0147] The method of the above embodiment can be implemented in the form of a computer program, so the present application proposes a computer readable storage medium, see Fig.12 , Fig.12 The computer-readable storage medium 50 stores program data 51 that can be run by a processor, and the program data 51 can be executed by the processor to implement the steps of any embodiment of the above-mentioned device docking method.

[0148] The computer-readable storage medium 50 of this embodiment can be a medium that can store program data 51, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or it can also be a server that stores the program data 51. The server can send the stored program data 51 to other devices for execution, or it can also execute the stored program data 51 by itself.

[0149] In some embodiments, the functions or modules included in the device provided in the above embodiments of the present application 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, the present application will not go into details here.

[0150] The above description of the various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other. For the sake of brevity, this application will not go into details here.

[0151] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is 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, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, 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.

[0152] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0153] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0154] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium, which is a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of each implementation method of the present application.

[0155] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a computer-readable storage medium and executed by a computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present application is not limited to any specific combination of hardware and software.

[0156] The above descriptions are merely embodiments of the present application and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for docking a device, characterized in that: include: The target device obtains docking related information of the docking device, and obtains a number of point cloud data; Fitting the plurality of point cloud data to obtain a plurality of initial straight line features; Using the docking related information of the docking device, the plurality of initial straight line features are processed to obtain target straight line features; wherein the target straight line features include at least two target straight line features in different directions; Based on the target straight line feature, a target docking point is determined, so as to dock with the docking device using the target docking point.

2. The method according to claim 1, characterized in that The target straight line feature includes a first straight line feature and a second straight line feature in two different directions, the first straight line feature corresponds to a first direction, the second straight line feature corresponds to a second direction, the first direction and the second direction are different, the second direction is determined based on the first direction, and the first direction is determined based on at least part of the point cloud data contained in the first straight line feature.

3. The method according to claim 2, characterized in that The method of processing the plurality of initial straight line features using the docking related information of the docking device to obtain the target straight line features includes: Determine, from the plurality of initial straight line features, initial straight line features that meet a first screening condition, and obtain at least two first straight line features; Determine a first direction corresponding to the at least two first straight line features using at least a portion of the point cloud data included in the at least two first straight line features; Based on the first direction, determining a second direction; Determine, from the plurality of initial straight line features, an initial straight line feature that satisfies a second screening condition, and obtain at least one second straight line feature; The first screening condition and the second screening condition at least include different scale conditions corresponding to the docking related information of the docking device.

4. The method according to claim 3, characterized in that The first screening condition includes a parallel condition and a first scale condition, and the first scale condition is determined based on a first scale of the docking device; And / or, the second screening condition includes: a second direction condition and a second scale condition, the second scale condition being determined based on a second scale of the docking device; And / or, the angle between the second direction and the first direction satisfies a preset angle condition; And / or, using at least part of the point cloud data included in the at least two first straight line features to determine the first direction corresponding to the first straight line features includes: Determine the center point of each first straight line feature, obtain point cloud data within a preset point cloud range located at the center point, and obtain at least part of the point cloud data; A straight line fitting is performed on at least a portion of the point cloud data to obtain a reference fitting line, and the first direction is determined based on a direction corresponding to the reference fitting line.

5. The method according to claim 3 or 4, characterized in that: After determining the initial straight line features satisfying the second screening condition from the plurality of initial straight line features and obtaining at least one second straight line feature, the method includes: In response to the number of the second straight line features being greater than a preset number, determining the second straight line features that meet a third screening condition to obtain final second straight line features; The third screening condition includes at least one of the following: the distance between the center points of the second straight line feature and the first straight line feature belongs to a preset distance range, and the center points of the second straight line feature and the first straight line feature satisfy a preset position relationship.

6. The method according to claim 2, characterized in that The step of determining a target docking point based on the target straight line feature, so as to dock with the docking device using the target docking point, comprises: Obtaining intersection points between each first straight line feature and the second straight line feature respectively; Determine a target docking point by using the intersection point and docking related information of the docking device; Based on the target docking point, docking is performed with the docking device.

7. The method according to claim 6, characterized in that Determining the target docking point by using the intersection point and the docking related information of the docking device includes: Using the intersection point, obtaining a target docking coordinate system; Determining a target docking point based on the target docking coordinate system and docking related information of the docking device; And / or, docking with the docking device based on the target docking point includes: During the docking process between the target device and the docking device, continuously acquiring at least two first straight line features; The distance between the target device and the first straight line feature is respectively acquired to obtain a moving distance, and the target device is controlled to move toward the target docking point according to the moving distance, so that the target device is docked along the perpendicular midline of the docking device.

8. The method according to claim 1, characterized in that The method further comprises: Using the target straight line feature, detecting whether an abnormal connection occurs; In response to the occurrence of the docking abnormality, it is determined not to dock with the docking device.

9. The method according to claim 8, characterized in that The target straight line feature includes a first straight line feature and a second straight line feature, and the docking-related information of the docking device includes at least one of the following: scale information, a preset docking point, and a preset docking coordinate system; The method of using the target straight line feature to detect whether a connection abnormality occurs comprises at least one of the following steps: In response to obtaining the first straight line feature and the second straight line feature, determining a first docking area using the first straight line feature, the second straight line feature and the scale information of the docking device; detecting whether the point cloud data in the first docking area meets an abnormal condition, and determining that a docking abnormality occurs in response to meeting the abnormal condition; In response to obtaining the first straight line feature and not having the second straight line feature, determining that a connection abnormality occurs; In response to obtaining that there is no first straight line feature and no second straight line feature, and the detection of the point cloud data satisfies the condition that there is no abnormality, determining a second docking area by using the scale information of the docking device, the preset docking point and the preset docking coordinate system; It is detected whether the point cloud data in the second docking area meets an abnormal condition, and in response to meeting the abnormal condition, it is determined that a docking abnormality occurs.

10. The method according to claim 1, characterized in that The fitting of the plurality of point cloud data to obtain a plurality of initial straight line features includes: Using a preset straight line fitting algorithm to fit the plurality of point cloud data to obtain a plurality of straight line segments and corresponding straight line point cloud sets; Projecting the endpoints in the straight line point cloud set to the corresponding straight line segments to obtain projected endpoints; The plurality of straight line segments are merged using the projection endpoints to obtain a merged straight line segment as an initial straight line feature to obtain the plurality of initial straight line features.

11. The method according to claim 10, characterized in that The step of merging the plurality of straight line segments by using the projection endpoints to obtain a merged straight line segment includes: In response to the projection endpoints corresponding to two adjacent straight line segments satisfying a preset merging condition, merging the straight line point cloud sets corresponding to the two adjacent straight line segments to obtain a merged point cloud set; Using a preset straight line fitting algorithm to fit the point cloud data included in the merged point cloud set to obtain the merged straight line segment; The preset merging condition includes: the distance between the adjacent projection endpoints corresponding to the two straight line segments is less than a first distance threshold, and the distance from the projection endpoint corresponding to a straight line segment to another straight line segment is less than a second distance threshold.

12. A computer device, characterized in that: The invention comprises a memory and a processor coupled to each other, wherein the memory stores program data, and the processor is used to execute the program data to implement the steps of the method according to any one of claims 1 to 11.

13. A computer-readable storage medium, characterized in that: Program data that can be executed by a processor are stored, and the program data is used to implement the steps of the method according to any one of claims 1 to 11.

Images