Forklift positioning method, device and equipment and computer storage medium

Abstract

The invention provides a forklift positioning method, a forklift positioning device, forklift positioning equipment and a computer storage medium. The forklift positioning method comprises the following steps: extracting a cargo compartment edge point coordinate and a first cargo compartment angle of a cargo compartment in a laser radar coordinate system; acquiring a yaw angle of the laser radar in the map coordinate system by using a first cargo compartment angle of the cargo compartment in the laser radar coordinate system and a second cargo compartment angle of the cargo compartment in the map coordinate system; solving laser radar position coordinates of the laser radar in the map coordinate system by using the cargo compartment edge point coordinates, the second cargo compartment angle and the first cargo compartment angle; based on the yaw angle and the laser radar position coordinates, position information of the forklift where the laser radar is located is determined. According to the forklift positioning method, the information of the edge points of the cargo compartment door is extracted to improve the positioning precision in the cargo compartment, the positioning of the unmanned forklift outside and inside the cargo compartment is considered, seamless connection can be achieved, and the obtained position angle information is information in the map coordinate system and is convenient to control and plan.

Description

Technical Field

[0001] The present application relates to the technical field of navigation and positioning of mobile robots, and in particular to a forklift positioning method, a forklift positioning device, a forklift positioning equipment and a computer storage medium. Background Art

[0002] At present, the application of mobile robots has become a hot topic in intelligent manufacturing. Among them, unmanned forklifts are mainly used for cargo handling, material transfer, intelligent operation and other businesses, such as cargo handling within the factory, and cargo handling from the factory to the cargo compartment of the logistics vehicle. Since the size of the cargo compartment of the logistics vehicle is unknown and the position of the cargo compartment in the map is not fixed, the commonly used positioning method based on the prior map is not available. Therefore, the autonomous positioning of the unmanned forklift in the cargo compartment is a problem that needs to be solved. The current inability to accurately handle the autonomous positioning of the unmanned forklift in the cargo compartment will greatly affect work efficiency. Summary of the invention

[0003] In order to solve the above technical problems, the present application proposes a forklift positioning method, a forklift positioning device, a forklift positioning equipment and a computer storage medium.

[0004] In order to solve the above technical problems, the present application proposes a forklift positioning method, which includes:

[0005] Get the current lidar point cloud;

[0006] Based on the current laser radar point cloud, extracting the coordinates of the edge points of the cargo compartment and the first cargo compartment angle of the cargo compartment in the laser radar coordinate system;

[0007] Using a first cargo compartment angle of the cargo compartment in the laser radar coordinate system and a second cargo compartment angle of the cargo compartment in the map coordinate system, obtaining a yaw angle of the laser radar in the map coordinate system;

[0008] Solving the laser radar position coordinates of the laser radar in the map coordinate system using the cargo compartment edge point coordinates, the second cargo compartment angle, and the first cargo compartment angle;

[0009] Based on the yaw angle and the laser radar position coordinates, the position information of the forklift where the laser radar is located is determined.

[0010] The step of extracting the cargo compartment edge point coordinates and the first cargo compartment angle of the cargo compartment in the laser radar coordinate system based on the current laser radar point cloud includes:

[0011] Performing straight line fitting and segmentation on the current laser radar point cloud to obtain a number of straight line point cloud classes in the laser radar coordinate system;

[0012] Clustering the straight line point clouds located on the same side of the laser radar to obtain a first type of point cloud and a second type of point cloud;

[0013] Determine the coordinates of the edge point of the cargo compartment based on the data point with the largest horizontal coordinate obtained in the first type of point cloud and the data point with the largest horizontal coordinate obtained in the second type of point cloud;

[0014] Obtain a first straight line angle of a straight line equation corresponding to the first type of point cloud in the laser radar coordinate system;

[0015] Obtain a second straight line angle of the straight line equation corresponding to the second type of point cloud in the laser radar coordinate system;

[0016] The first cargo box angle is determined based on an average of the first straight line angle and the second straight line angle.

[0017] Wherein, before clustering the straight line point clouds located on the same side of the laser radar to obtain the first type of point cloud and the second type of point cloud, the forklift positioning method further includes:

[0018] Get the predicted angle of the current laser radar in the map coordinate system;

[0019] Converting the line equation corresponding to each line point cloud class to the map coordinate system according to the predicted angle to obtain two predicted line angles of the line equation;

[0020] Eliminate the straight line point cloud class whose deviations between the two predicted straight line angles and the second cargo compartment angle are both greater than a preset angle threshold.

[0021] Wherein, before clustering the straight line point clouds located on the same side of the laser radar to obtain the first type of point cloud and the second type of point cloud, the forklift positioning method further includes:

[0022] Get the line equation corresponding to each line point cloud class;

[0023] Eliminate the straight line point cloud class whose distance between the straight line equation and the laser radar position is greater than a preset distance threshold.

[0024] Wherein, the forklift positioning method further comprises:

[0025] Obtaining a first straight line between one of the cargo compartment edge point coordinates and the origin of the laser radar coordinate system, and a second straight line between another of the cargo compartment edge point coordinates and the origin of the laser radar coordinate system;

[0026] Obtaining a first angle deviation between the first straight line and a straight line equation corresponding to the first type of point cloud, and a second angle deviation between the second straight line and a straight line equation corresponding to the second type of point cloud;

[0027] Based on the cargo compartment edge point coordinates, determining edge point line segments;

[0028] Obtaining the edge point distance from the origin of the laser radar coordinate system to the edge point line segment;

[0029] In response to the first angle deviation and the second angle deviation being both greater than a preset angle deviation threshold, and the edge point distance being less than a preset edge threshold, confirming that the yaw angle and the laser radar position coordinates are credible;

[0030] The determining, based on the yaw angle and the laser radar position coordinates, the position information of the forklift where the laser radar is located includes:

[0031] In response to the yaw angle and the laser radar position coordinates being credible, the yaw angle and the laser radar position coordinates are used as position information of the forklift where the laser radar is located.

[0032] Wherein, determining the position information of the forklift where the laser radar is located based on the yaw angle and the laser radar position coordinates includes:

[0033] In response to the yaw angle and the laser radar position coordinates being unreliable, obtaining the position coordinates at the last moment and a projection of the position change;

[0034] By using the position coordinates at the last moment and the projection of the position change, the laser radar position coordinates are fused to obtain the position information of the forklift where the laser radar is located.

[0035] Wherein, before obtaining the yaw angle of the laser radar in the map coordinate system by using the first cargo compartment angle of the cargo compartment in the laser radar coordinate system and the second cargo compartment angle of the cargo compartment in the map coordinate system, the forklift positioning method further includes:

[0036] Obtain the first vector and the second vector of the cargo compartment edge point coordinates and the origin of the laser radar coordinate system;

[0037] According to the first cargo compartment angle, converting the first vector and the second vector into a cargo compartment coordinate system to obtain a third vector and a fourth vector;

[0038] In response to the angular deviation between the third vector and the horizontal axis of the cargo compartment coordinate system being less than or equal to a first preset deviation threshold, or the angular deviation between the fourth vector and the horizontal axis of the cargo compartment coordinate system being less than or equal to a second preset deviation threshold, it is determined to use the cargo compartment edge point coordinates, the second cargo compartment angle, and the first cargo compartment angle for positioning.

[0039] In order to solve the above technical problems, the present application also proposes a forklift positioning device, which includes: an acquisition module, a calibration module, and a positioning module; wherein,

[0040] The acquisition module is used to acquire the current laser radar point cloud;

[0041] The calibration module is used to extract the coordinates of the edge points of the cargo compartment and the first cargo compartment angle of the cargo compartment in the laser radar coordinate system based on the current laser radar point cloud;

[0042] The calibration module is used to obtain the yaw angle of the laser radar in the map coordinate system by using the first cargo compartment angle of the cargo compartment in the laser radar coordinate system and the second cargo compartment angle of the cargo compartment in the map coordinate system;

[0043] The calibration module is used to solve the laser radar position coordinates of the laser radar in the map coordinate system by using the cargo compartment edge point coordinates, the second cargo compartment angle, and the first cargo compartment angle;

[0044] The positioning module is used to determine the position information of the forklift where the laser radar is located based on the yaw angle and the laser radar position coordinates.

[0045] To solve the above technical problems, the present application also proposes a forklift positioning device, which includes a memory and a processor coupled to the memory; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the forklift positioning method as described above.

[0046] In order to solve the above technical problems, the present application further proposes a computer storage medium, wherein the computer storage medium is used to store program data, and when the program data is executed by a computer, it is used to implement the above forklift positioning method.

[0047] Compared with the prior art, the beneficial effects of the present application are as follows: the forklift positioning device obtains the current laser radar point cloud; based on the current laser radar point cloud, the cargo compartment edge point coordinates and the first cargo compartment angle of the cargo compartment in the laser radar coordinate system are extracted; the first cargo compartment angle of the cargo compartment in the laser radar coordinate system and the second cargo compartment angle of the cargo compartment in the map coordinate system are used to obtain the yaw angle of the laser radar in the map coordinate system; the laser radar position coordinates of the laser radar in the map coordinate system are solved using the cargo compartment edge point coordinates, the second cargo compartment angle, and the first cargo compartment angle; based on the yaw angle and the laser radar position coordinates, the position information of the forklift where the laser radar is located is determined. Through the above-mentioned forklift positioning method, the information of the edge points of the cargo compartment door is extracted to improve the positioning accuracy in the cargo compartment, and the positioning of the unmanned forklift outside and inside the cargo compartment is taken into consideration, so that seamless connection can be achieved, and the obtained position angle information is the information in the map coordinate system, which is convenient for control planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0049] Figure 1 It is a top view schematic diagram of the unmanned forklift provided by the present application backing into the cargo compartment of a logistics vehicle to load and unload goods;

[0050] Figure 2 is a schematic diagram of multiple coordinate systems provided in this application;

[0051] Figure 3 It is a flow chart of an embodiment of a forklift positioning method provided by the present application;

[0052] Figure 4 It is a schematic diagram of the overall process of the forklift positioning method provided by the present application;

[0053] Figure 5 yes Figure 3 The specific flow diagram of step S12 of the forklift positioning method shown;

[0054] Figure 6 It is a structural schematic diagram of an embodiment of a forklift positioning device provided by the present application;

[0055] Figure 7 It is a structural schematic diagram of an embodiment of a forklift positioning device provided by the present application;

[0056] Figure 8It is a structural diagram of an embodiment of a computer storage medium provided by the present application. DETAILED DESCRIPTION

[0057] 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.

[0058] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can, for example, be implemented in an order other than those illustrated or described herein. 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 necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0059] The problems to be solved by the forklift positioning method of this application are as follows:

[0060] 1. A seamless positioning method for unmanned forklifts from outside the cargo compartment to inside the cargo compartment.

[0061] 2. Rely on laser radar to extract the characteristics of the cargo compartment and integrate the wheel odometer to improve the positioning accuracy of the unmanned forklift in the cargo compartment.

[0062] Please refer to the application scenario of the forklift positioning method of this application. Figure 1 and Figure 2 ,in, Figure 1 This is a top view schematic diagram of the unmanned forklift provided by the present application backing into the cargo compartment of a logistics vehicle to load and unload goods. Figure 2 It is a schematic diagram of multiple coordinate systems provided in this application.

[0063] like Figure 1 and Figure 2 As shown, the origin of the map coordinate system is W o , Z axis upward, W x is the X axis, W y is the Y axis. The laser radar coordinate system and the cargo compartment coordinate system change with the position of the unmanned forklift. Specifically, Figure 2 The origin of the laser radar coordinate system at the current moment is shown as L o, Z axis upward, L x is the X axis, L y is the Y axis. Figure 2 The origin of the cargo compartment coordinate system at the current moment is L o , the same as the origin of the current laser radar coordinate system; the Z axis is upward; C x is the X-axis, parallel to the side baffle of the cargo compartment; C y It is the Y-axis, which is perpendicular to the side baffle of the cargo compartment.

[0064] The angle of the cargo compartment in the map coordinate system is as follows: the angle of the ray parallel to the cargo compartment side baffle, pointing from the inner baffle to the outside of the cargo compartment in the map, and the ray The angle in map coordinates.

[0065] The prior information used by the forklift positioning method of this application is: the logistics vehicle is parked in the platform area, the unmanned forklift enters the cargo compartment through the platform, and there are generally facilities such as lifting platforms or fences at the entrance, as shown in the application scenario diagram Figure 1 As shown in , we can get the following two pieces of information roughly in advance:

[0066] Calibrate the rough angle of the cargo compartment in the map coordinate system according to the position of the cargo compartment door edge point The error is less than 10 degrees.

[0067] Approximate width of cargo door L door , the error is less than 0.5m.

[0068] The positioning ideas of the forklift positioning method of the present application at different stages are as follows: when the forklift is outside the cargo compartment, the lidar data and prior map matching are used for positioning; when the forklift is in the cargo compartment and the lidar's field of view is largely blocked by the side baffles of the cargo compartment, the extracted cargo compartment door edge points and cargo compartment side baffle straight line information are used for positioning.

[0069] Please refer to Figure 3 and Figure 4 , Figure 3 is a flow chart of an embodiment of a forklift positioning method provided by the present application, Figure 4 It is a schematic diagram of the overall process of the forklift positioning method provided by the present application.

[0070] The forklift positioning method of the present application is applied to a forklift positioning device, wherein the forklift positioning device of the present application can be a server, a terminal device, or a system in which a server and a terminal device cooperate with each other. Accordingly, the various parts of the forklift positioning device, such as various units, subunits, modules, and submodules, can all be set in the server, can all be set in the terminal device, or can be set in the server and the terminal device respectively.

[0071] Furthermore, the above-mentioned server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules, such as software or software modules used to provide distributed servers, or it can be implemented as a single software or software module, which is not specifically limited here.

[0072] like Figure 3 As shown, the specific steps are as follows:

[0073] Step S11: Obtain the current laser radar point cloud.

[0074] In the embodiment of the present application, when an unmanned forklift is planned to load and unload cargo in a cargo compartment in a designated area, the forklift positioning device initializes the algorithm and sets the rough angle of the cargo compartment in the map coordinate system. and the approximate width of the cargo door L door ; When the unmanned forklift approaches the cargo compartment entrance, the forklift positioning method of the present application is started.

[0075] Step S12: Based on the current laser radar point cloud, extract the coordinates of the edge points of the cargo compartment and the first cargo compartment angle of the cargo compartment in the laser radar coordinate system.

[0076] In the embodiment of the present application, the forklift positioning device obtains the laser radar data at the current time k and extracts the edge point B of the cargo compartment door. l and B r , and update the cargo compartment side baffle rays Angle in the lidar coordinate system That is, the first cargo compartment angle of the cargo compartment in the lidar coordinate system.

[0077] Please refer to the calibration process of the above data based on the current LiDAR point cloud. Figure 5 , Figure 5 yes Figure 3 The specific flow chart of step S12 of the forklift positioning method is shown.

[0078] like Figure 5 As shown, the specific steps are as follows:

[0079] Step S121: Perform straight line fitting and segmentation on the current laser radar point cloud to obtain several straight line point cloud classes in the laser radar coordinate system.

[0080] In an embodiment of the present application, the forklift positioning device performs straight line fitting and segmentation on the laser point cloud data, clusters the point clouds belonging to the same straight line, and obtains several straight line point cloud classes and corresponding straight line equations in the laser radar coordinate system.

[0081] Step S122: cluster the straight line point clouds on the same side of the laser radar to obtain the first type of point cloud and the second type of point cloud.

[0082] In the embodiment of the present application, in order to improve the accuracy of data extraction, before performing subsequent clustering, the forklift positioning device can pre-process the several straight line point cloud classes in step S121, that is, eliminate the point cloud classes that do not meet the clustering requirements.

[0083] Specifically, the forklift positioning device calculates the angle of the straight line converted to the map coordinate system based on the predicted angle of the laser radar in the map at the current moment. The straight line angle has two directions, and the deviation between these two angles and the rough angle of the cargo compartment in the map initially calibrated is calculated. Eliminate point cloud classes whose two deviations are greater than the threshold.

[0084] It should be noted that the predicted angle of the lidar in the map at the current moment is obtained by recursion based on the positioning result at the previous moment using the wheel odometer / IMU (Inertial Measurement Unit) and the like.

[0085] Furthermore, the forklift positioning device can also eliminate the forklifts whose distance from the laser radar position is greater than L door The laser radar position is the origin of the coordinate system where the laser radar point cloud is located.

[0086] After the forklift positioning device completes the preprocessing of the point cloud data, it clusters the straight line point clouds on the same side of the laser radar. The same side refers to: the straight line equation in the laser radar coordinate system and the Y axis L of the laser radar coordinate system. y The Y coordinates of the intersection points have the same sign, those greater than or equal to 0 are in the same category, and those less than 0 are in the same category.

[0087] The forklift positioning device selects the point cloud class with the largest number of point clouds among the different straight line classes in the previous classification results, which is the point cloud scanned to the baffles on both sides of the cargo compartment. y The point cloud whose Y coordinate of the intersection is greater than or equal to 0 is {S l}, that is, the first type of point cloud, the point cloud whose intersection coordinates are less than 0 is {S r}, that is, the second type of point cloud.

[0088] Step S123: Determine the coordinates of the edge point of the cargo compartment based on the data point with the largest horizontal coordinate obtained in the first type of point cloud and the data point with the largest horizontal coordinate obtained in the second type of point cloud.

[0089] In the embodiment of the present application, the forklift positioning device determines the first type of point cloud {S l The point with the largest X coordinate in the laser radar coordinate system is B. l, i.e. the coordinates of one of the cargo compartment edge points; determine the second type of point cloud {S r The point with the largest X coordinate in the laser radar coordinate system is B. r , that is, the coordinates of another cargo compartment edge point.

[0090] Step S124: Obtain the first straight line angle of the straight line equation corresponding to the first type of point cloud in the laser radar coordinate system.

[0091] Step S125: Obtain a second straight line angle of the straight line equation corresponding to the second type of point cloud in the laser radar coordinate system.

[0092] Step S126: Determine a first cargo compartment angle based on an average value of the first straight line angle and the second straight line angle.

[0093] In the embodiment of the present application, the forklift positioning device {S l} and {S r The angle of the straight line equation corresponding to} in the laser radar coordinate system, that is, the direction is closer to L x The average value of the positive angle is

[0094] Step S13: using the first cargo compartment angle of the cargo compartment in the laser radar coordinate system and the second cargo compartment angle of the cargo compartment in the map coordinate system, obtain the yaw angle of the laser radar in the map coordinate system.

[0095] In the embodiment of the present application, before performing positioning, the forklift positioning device needs to determine whether it can be positioned by matching laser data with a priori maps.

[0096] If the laser radar's field of view is largely blocked by the baffles on both sides of the cargo compartment and cannot scan enough contours in the prior map, it cannot be positioned by matching the map.

[0097] The forklift positioning device is based on the angle of the cargo compartment coordinate system in the laser radar coordinate system. Vector Converted to the cargo compartment coordinate system, recorded as Among them, Figure 2 As shown, the cargo compartment coordinate system and the lidar coordinate system have the same origin, with only an angle difference.

[0098] like With the cargo compartment coordinate system X axis C x The positive angle deviation is greater than 100 degrees (the parameter value is between 95 and 120 degrees), and if If the angular deviation from the positive X-axis of the cargo compartment coordinate system is also greater than 100 degrees (the parameter value is between 95 and 120), it is considered that positioning can be performed using map matching, otherwise positioning cannot be performed using map matching.

[0099] It should be noted that the first preset deviation threshold and the second preset deviation threshold may be the same or different and may be any one of the above parameter values, and no limitation is imposed on the specific numerical values.

[0100] If the laser data can be matched with the prior map for positioning, the forklift positioning device updates the positioning of the unmanned forklift by matching the prior map, and updates the coordinates of the detected cargo compartment door edge point in the map (denoted as ) and the angle θc between the cargo compartment coordinate system in the map W :

[0101]

[0102] in, is the yaw angle of the lidar in the map coordinate system at time k (calculated by matching with the map).

[0103] If positioning cannot be achieved by matching the laser data with the prior map, the process proceeds to step S14.

[0104] Step S14: Using the cargo compartment edge point coordinates, the second cargo compartment angle, and the first cargo compartment angle, solve the laser radar position coordinates of the laser radar in the map coordinate system.

[0105] In the embodiment of the present application, the forklift positioning device uses B r W and θc W and the edge points detected in step S12 That is, the angle of the cargo compartment in the laser radar coordinate system updates the positioning result, that is, the position of the laser radar in the map and angle

[0106] Specifically, the forklift positioning device calculates the yaw angle of the laser radar in the map coordinate system at the current moment as

[0107] The forklift positioning device calculates the current laser radar position coordinates in the map coordinate system:

[0108] The edge point B of the cargo door detected at the current moment l and B r The coordinates in the laser radar coordinate system are Remember the temporary 3*3 matrix A l and A r :

[0109]

[0110] Among them, the position coordinates are calculated as follows:

[0111]

[0112] Step S15: Based on the yaw angle and the laser radar position coordinates, determine the position information of the forklift where the laser radar is located.

[0113] In the embodiment of the present application, before determining the position information of the forklift where the laser radar is located, the forklift positioning device needs to evaluate whether the position calculated in the previous step is credible.

[0114] Specifically, the forklift positioning device calculates the angle deviation between the laser ray corresponding to the currently extracted edge point and the straight line where the side baffle of the cargo compartment is located: the straight line L o B l With {S l The angular deviation of the corresponding straight line equation is Note that the straight line L o B r With {S r The angular deviation of the corresponding straight line equation is The deviation of the angles of the two straight lines is the smaller angle of the included angle of the two straight lines, ranging from 0 to 90 degrees.

[0115] Forklift positioning device mark point L o To line segment B l B r The distance is d1.

[0116] like If both are greater than a threshold (generally set to 20 to 45 degrees) and less than a threshold (generally 8 to 12 meters), the yaw angle and lidar position coordinates calculated in step S14 are considered credible; otherwise, the yaw angle and lidar position coordinates calculated in step S14 are unreliable.

[0117] If the yaw angle and the laser radar position coordinates calculated in the evaluation step S14 are credible, the forklift positioning device directly outputs the calculated position; if not credible, the forklift positioning device needs to integrate the wheel odometer information to estimate the position to improve the credibility of the positioning result:

[0118] The position of the laser radar in the map at the last moment k-1 is The projection of the position change of the laser radar observed by the odometer relative to the previous moment in the k-1 laser radar coordinate system is Cargo compartment side baffle ray at time k-1 The angle in the LiDAR coordinate system is

[0119] The laser radar position changes on the X-axis C of the cargo compartment coordinate system x The projection on

[0120]

[0121] The laser radar position changes on the Y axis C of the cargo compartment coordinate system y The projection on

[0122]

[0123] The coordinates of the laser radar at time k in the map coordinate system are:

[0124]

[0125] In the present application, the forklift positioning device obtains the current laser radar point cloud; based on the current laser radar point cloud, the coordinates of the edge points of the cargo compartment and the first cargo compartment angle of the cargo compartment in the laser radar coordinate system are extracted; the yaw angle of the laser radar in the map coordinate system is obtained by using the first cargo compartment angle of the cargo compartment in the laser radar coordinate system and the second cargo compartment angle of the cargo compartment in the map coordinate system; the laser radar position coordinates of the laser radar in the map coordinate system are solved by using the coordinates of the edge points of the cargo compartment, the second cargo compartment angle, and the first cargo compartment angle; based on the yaw angle and the laser radar position coordinates, the position information of the forklift where the laser radar is located is determined. Through the above-mentioned forklift positioning method, the information of the edge points of the cargo compartment door is extracted to improve the positioning accuracy in the cargo compartment, and the positioning of the unmanned forklift outside and inside the cargo compartment is taken into account, which can achieve seamless connection, and the obtained position angle information is the information in the map coordinate system, which is convenient for control planning.

[0126] The forklift positioning method of the present application takes into account the positioning of the unmanned forklift outside and inside the cargo compartment, and can achieve seamless connection. The obtained position angle information is the information in the map coordinate system, which is convenient for control planning.

[0127] The forklift positioning method of the present application extracts information about the edge points of the cargo compartment door to improve the positioning accuracy inside the cargo compartment. The load of an unmanned forklift entering the cargo compartment will only block the laser scanning field of view inside the cargo compartment. Therefore, the laser radar can still scan the information on one side of the cargo compartment door, and there will be no situation where a directional position reference feature is missing.

[0128] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0129] In order to realize the forklift positioning method, the present application also proposes a forklift positioning device, for details, please refer to Figure 6 , Figure 6 It is a structural schematic diagram of an embodiment of a forklift positioning device provided in the present application.

[0130] The forklift positioning device 500 of this embodiment includes: an acquisition module 51 , a calibration module 52 , and a positioning module 53 .

[0131] Wherein, the acquisition module 51 is used to acquire the current laser radar point cloud.

[0132] The calibration module 52 is used to extract the coordinates of the edge points of the cargo compartment and the first cargo compartment angle of the cargo compartment in the laser radar coordinate system based on the current laser radar point cloud.

[0133] The calibration module 52 is used to obtain the yaw angle of the laser radar in the map coordinate system by using the first cargo compartment angle of the cargo compartment in the laser radar coordinate system and the second cargo compartment angle of the cargo compartment in the map coordinate system.

[0134] The calibration module 52 is used to solve the laser radar position coordinates of the laser radar in the map coordinate system by using the cargo compartment edge point coordinates, the second cargo compartment angle, and the first cargo compartment angle.

[0135] The positioning module 53 is used to determine the position information of the forklift where the laser radar is located based on the yaw angle and the position coordinates of the laser radar.

[0136] In order to implement the forklift positioning method, the present application also proposes a forklift positioning device, for details, please refer to Figure 7 , Figure 7 It is a structural schematic diagram of an embodiment of a forklift positioning device provided in the present application.

[0137] The forklift positioning device 400 of this embodiment includes a processor 41 , a memory 42 , an input / output device 43 , and a bus 44 .

[0138] The processor 41 , the memory 42 , and the input / output device 43 are respectively connected to the bus 44 . The memory 42 stores program data. The processor 41 is used to execute the program data to implement the forklift positioning method described in the above embodiment.

[0139] In the embodiment of the present application, the processor 41 may also be referred to as a CPU (Central Processing Unit). The processor 41 may be an integrated circuit chip having the ability to process signals. The processor 41 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 gates or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or the processor 41 may also be any conventional processor, etc.

[0140] This application also provides a computer storage medium, please continue to refer to Figure 8 , Figure 8 1 is a schematic diagram of the structure of an embodiment of a computer storage medium provided in the present application. The computer storage medium 600 stores a computer program 61. When the computer program 61 is executed by a processor, it is used to implement the forklift positioning method of the above embodiment.

[0141] When the embodiments of the present application are implemented in the form of software functional units and sold or used as independent products, they can be stored in 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, and the computer software product is stored in a storage medium, including several instructions to enable 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 the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0142] The above description is only an implementation method of the present application, and does not 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 used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A forklift positioning method, characterized in that: The forklift positioning method comprises: Get the current lidar point cloud; Based on the current laser radar point cloud, extracting the coordinates of the edge points of the cargo compartment and the first cargo compartment angle of the cargo compartment in the laser radar coordinate system; Using a first cargo compartment angle of the cargo compartment in the laser radar coordinate system and a second cargo compartment angle of the cargo compartment in the map coordinate system, obtaining a yaw angle of the laser radar in the map coordinate system; Solving the laser radar position coordinates of the laser radar in the map coordinate system using the cargo compartment edge point coordinates, the second cargo compartment angle, and the first cargo compartment angle; Based on the yaw angle and the laser radar position coordinates, the position information of the forklift where the laser radar is located is determined.

2. The forklift positioning method according to claim 1, characterized in that: The extracting the cargo compartment edge point coordinates and the first cargo compartment angle of the cargo compartment in the laser radar coordinate system based on the current laser radar point cloud includes: Performing straight line fitting and segmentation on the current laser radar point cloud to obtain a number of straight line point cloud classes in the laser radar coordinate system; Clustering the straight line point clouds located on the same side of the laser radar to obtain a first type of point cloud and a second type of point cloud; Determine the coordinates of the edge point of the cargo compartment based on the data point with the largest horizontal coordinate obtained in the first type of point cloud and the data point with the largest horizontal coordinate obtained in the second type of point cloud; Obtain a first straight line angle of a straight line equation corresponding to the first type of point cloud in the laser radar coordinate system; Obtain a second straight line angle of the straight line equation corresponding to the second type of point cloud in the laser radar coordinate system; The first cargo box angle is determined based on an average of the first straight line angle and the second straight line angle.

3. The forklift positioning method according to claim 2, characterized in that: Before clustering the straight line point clouds located on the same side of the laser radar to obtain the first type of point cloud and the second type of point cloud, the forklift positioning method further includes: Get the predicted angle of the current laser radar in the map coordinate system; Converting the line equation corresponding to each line point cloud class to the map coordinate system according to the predicted angle to obtain two predicted line angles of the line equation; Eliminate the straight line point cloud class whose deviations between the two predicted straight line angles and the second cargo compartment angle are both greater than a preset angle threshold.

4. The forklift positioning method according to claim 2 or 3, characterized in that: Before clustering the straight line point clouds located on the same side of the laser radar to obtain the first type of point cloud and the second type of point cloud, the forklift positioning method further includes: Get the line equation corresponding to each line point cloud class; Eliminate the straight line point cloud class whose distance between the straight line equation and the laser radar position is greater than a preset distance threshold.

5. The forklift positioning method according to claim 2, characterized in that: The forklift positioning method further comprises: Obtaining a first straight line between one of the cargo compartment edge point coordinates and the origin of the laser radar coordinate system, and a second straight line between another of the cargo compartment edge point coordinates and the origin of the laser radar coordinate system; Obtaining a first angle deviation between the first straight line and a straight line equation corresponding to the first type of point cloud, and a second angle deviation between the second straight line and a straight line equation corresponding to the second type of point cloud; Based on the cargo compartment edge point coordinates, determining edge point line segments; Obtaining the edge point distance from the origin of the laser radar coordinate system to the edge point line segment; In response to the first angle deviation and the second angle deviation being both greater than a preset angle deviation threshold, and the edge point distance being less than a preset edge threshold, confirming that the yaw angle and the laser radar position coordinates are credible; The determining, based on the yaw angle and the laser radar position coordinates, the position information of the forklift where the laser radar is located includes: In response to the yaw angle and the laser radar position coordinates being credible, the yaw angle and the laser radar position coordinates are used as position information of the forklift where the laser radar is located.

6. The forklift positioning method according to claim 5, characterized in that: The determining, based on the yaw angle and the laser radar position coordinates, the position information of the forklift where the laser radar is located includes: In response to the yaw angle and the laser radar position coordinates being unreliable, obtaining the position coordinates at the last moment and a projection of the position change; By using the position coordinates at the last moment and the projection of the position change, the laser radar position coordinates are fused to obtain the position information of the forklift where the laser radar is located.

7. The forklift positioning method according to claim 1, characterized in that: Before obtaining the yaw angle of the laser radar in the map coordinate system by using the first cargo compartment angle of the cargo compartment in the laser radar coordinate system and the second cargo compartment angle of the cargo compartment in the map coordinate system, the forklift positioning method further includes: Obtain the first vector and the second vector of the cargo compartment edge point coordinates and the origin of the laser radar coordinate system; According to the first cargo compartment angle, converting the first vector and the second vector into a cargo compartment coordinate system to obtain a third vector and a fourth vector; In response to the angular deviation between the third vector and the horizontal axis of the cargo compartment coordinate system being less than or equal to a first preset deviation threshold, or the angular deviation between the fourth vector and the horizontal axis of the cargo compartment coordinate system being less than or equal to a second preset deviation threshold, it is determined to use the cargo compartment edge point coordinates, the second cargo compartment angle, and the first cargo compartment angle for positioning.

8. A forklift positioning device, characterized in that: The forklift positioning device comprises: an acquisition module, a calibration module, and a positioning module; wherein, The acquisition module is used to acquire the current laser radar point cloud; The calibration module is used to extract the coordinates of the edge points of the cargo compartment and the first cargo compartment angle of the cargo compartment in the laser radar coordinate system based on the current laser radar point cloud; The calibration module is used to obtain the yaw angle of the laser radar in the map coordinate system by using the first cargo compartment angle of the cargo compartment in the laser radar coordinate system and the second cargo compartment angle of the cargo compartment in the map coordinate system; The calibration module is used to solve the laser radar position coordinates of the laser radar in the map coordinate system by using the cargo compartment edge point coordinates, the second cargo compartment angle, and the first cargo compartment angle; The positioning module is used to determine the position information of the forklift where the laser radar is located based on the yaw angle and the laser radar position coordinates.

9. A forklift positioning device, characterized in that: The forklift positioning device includes a memory and a processor coupled to the memory; The memory is used to store program data, and the processor is used to execute the program data to implement the forklift positioning method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium is used to store program data, and when the program data is executed by a computer, it is used to implement the forklift positioning method according to any one of claims 1 to 7.

Images