High-precision map correction method and device, storage medium and program product

Abstract

The invention belongs to the technical field of high-precision map drawing, and particularly relates to a high-precision map correction method and device, a storage medium and a program product. The high-precision map correction method comprises the following steps: acquiring an initial path between crops of every two adjacent planting rows through a primary high-precision map, enabling a vehicle to walk along the initial path, identifying the crops in the planting rows on two sides of the initial path, acquiring an actual central path of the crops, calculating a similarity value of the actual central path relative to the initial path, and correcting the high-precision map according to the similarity value. And if the similarity value is greater than a preset threshold value, recording the position of the point on the actual central path as a first position, and calculating a second position and a third position in the planting rows on the two sides of the initial path based on the first position for correcting the initial edition high-precision map. According to the method, the consistency of data and the actual environment is improved, a real path can be accurately planned, crop damage and work efficiency reduction caused by path deviation in planting rows are reduced, and therefore the intelligent level and economic benefits of agricultural production are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of high-precision map drawing, and in particular relates to a high-precision map correction method, device, storage medium and program product. Background Art

[0002] As autonomous driving technology and intelligent navigation systems become increasingly mature, the application of autonomous driving operations in modern agricultural production is becoming more and more widespread.

[0003] Of course, high-precision maps are essential for vehicles to complete their tasks when driving autonomously. Figure 1 Generally, the marking equipment is used to mark the boundaries of the plot and the various functional areas within it, record the road information in detail, plan the path, and draw a high-precision map. Among them, the various functional areas within the plot include parking areas and work area information. Among them, for work areas such as orchards and woodlands, the work area information includes but is not limited to the coordinates of the key points at the beginning of the line and the coordinates of the key points at the end of the line. In the high-precision map, the inter-row walking path planning of the vehicle in the work area is formed by straight line planning at the key points at the beginning of the line and the key points at the end of the line.

[0004] However, in orchards, woodlands and other types of working areas, the planting rows of crops such as fruit trees are relatively long, and trees and branches may extend outward during the crop growth process, resulting in the planting and growth of crops not being able to ensure that the entire row is in a straight line, which in turn causes the high-precision map to have inaccurate intra-row paths in the working area. If the vehicle uses the inter-row walking path provided by the dotting equipment to operate, it is easy to cause crop damage. Summary of the invention

[0005] The present invention aims to solve one of the technical problems in the related art at least to a certain extent.

[0006] The present invention provides a high-precision map correction method, comprising:

[0007] An initial path between each two adjacent rows of crops is obtained through the initial version of the high-precision map, and the vehicle travels along the initial path;

[0008] Identify the crops in the planting rows on both sides of the initial path and obtain the actual center path of the crops;

[0009] Calculating a similarity value between the actual central path and the initial path;

[0010] If the similarity value is greater than a preset threshold, recording the position of the point on the actual center path as the first position; and

[0011] Based on the first position, calculate the second position and the third position in the planting rows on both sides of the initial path, where the second position and the third position are used to correct the initial high-precision map.

[0012] This method enables the vehicle to travel along the initial path, facilitating the vehicle to obtain real-time information on the actual planting and growth conditions of the crops in adjacent rows. By comparing the actual center path with the initial path, the initial high-precision map is dynamically corrected, which helps improve the consistency between data and the actual environment, reduce errors, and enhance the map's accuracy and adaptability. This method obtains a more complete and accurate high-precision map. The corrected high-precision map can be applied to the complex and changeable environmental conditions within the rows in the fruit forest scenario, accurately plan the real path within the rows, avoid the deviation caused by using the initial high-precision map, optimize the vehicle operation path to a large extent, achieve collision-free full-process autonomous closed-loop operation of the vehicle, reduce crop damage and lower operation efficiency caused by path deviation within the planting rows, and thus improve the intelligent level and economic benefits of agricultural production.

[0013] As an alternative

[0014] The method for obtaining the actual center path includes:

[0015] Draw virtual lines based on the crops on adjacent planting rows respectively;

[0016] Based on the vehicle position and the two virtual lines, obtain visual navigation points and a visual center line. The intersection of the perpendicular line passing through the vehicle and the visual center line is the first position;

[0017] Convert the coordinates of the visual navigation points into coordinates in the world coordinate system; and

[0018] Calculate the direction of the first position in the world coordinate system according to the heading information of the vehicle to obtain the actual center path passing through the first position.

[0019] This method for obtaining the actual center path realizes high-precision and real-time path planning through virtual lines, visual navigation points, and coordinate transformation, and is particularly suitable for scenarios that require high-precision navigation such as agricultural automation. Specifically, this method is conducive to realizing high-precision path planning based on the virtual lines and visual navigation points of the crops, and calculates the path in real time based on the vehicle position and heading information, which is suitable for dynamic navigation tasks. The steps are clear and the calculation amount is moderate, which helps ensure real-time performance and efficiency. At the same time, this method improves the robustness of path planning through multi-sensor fusion of visual navigation points and vehicle heading information, converts visual data into the world coordinate system, realizes unified coordinate systems, and facilitates the fusion with other sensor data.

[0020] As an alternative, the vehicle obtains visual navigation points through a binocular camera. The binocular camera calculates depth information through parallax, which is beneficial for providing high-precision distance measurement, helping the vehicle accurately perceive the surrounding environment. The binocular camera has a relatively low cost, and through image recognition information, it is not easily interfered by crop branches and leaves, and is more suitable for agricultural scenarios, which is beneficial to improving the accuracy of recognition results.

[0021] The binocular camera has a relatively low cost, and through image recognition information, it is not easily interfered by crop branches and leaves, and is more suitable for agricultural scenarios, which is beneficial to improving the accuracy of recognition results. At the same time, the binocular camera can effectively solve the problems brought by the information collected by the dotting device, which is beneficial to improving the accuracy and authenticity of the corrected initial high-precision map, and at the same time, the labor cost and time cost consumed are relatively low.

[0022] As an alternative, the offset information includes lateral offset information and longitudinal offset information. This method jointly determines the visual navigation point coordinates through the lateral offset and longitudinal offset information, which is beneficial to improving the positioning accuracy, and further improves the accuracy of the high-precision map correction method.

[0023] As an alternative, the method for calculating the similarity value includes:

[0024] Calculating the normal vector of the initial path; and

[0025] Calculating the straight-line distance between the intersection point of the normal vector passing through the vehicle position and the initial path and the intersection point of the actual center path, and the straight-line distance is the similarity value.

[0026] The calculation method of this similarity value does not need to consider whether the actual center path is offset to the left or right relative to the initial path, and does not need to consider whether the actual center path is in the left front or right front relative to the initial path. Therefore, this similarity value calculation method can be applied to different working conditions, which is beneficial to simplifying the calculation difficulty of the similarity value, and further simplifies the high-precision map correction method.

[0027] As an alternative, the method for calculating the second position and the third position in the planting rows on both sides of the initial path based on the first position includes:

[0028] Taking the first position as the midpoint, and calculating the second position and the third position according to the width of the planting row and the distance from the center path to the planting row.

[0029] This method converts the first position obtained after calculating the similarity value into the planting row, so that the second position and the third position form key points in the high-precision map, and are further used as reference points for path planning.

[0030] As an alternative, the initial path planning method includes:

[0031] Taking the center points of the row heads of two adjacent planted rows as the starting points and the center points of the row tails of two adjacent planted rows as the ending points;

[0032] Performing a straight-line planning between the starting point and the ending point to form the initial path.

[0033] This initial path planning method directly connects the starting point and the ending point, with low algorithm complexity, being simple and efficient, and applicable to crops with planting and growth rules, especially applicable to the situation of real-time path correction for vehicle movement.

[0034] As an alternative, the high-precision map correction method further includes:

[0035] The vehicle travels along the initial path between every two adjacent crop rows in the operation area, collects data, and records the first positions where the similarity value is greater than a preset threshold;

[0036] Completing the correction of the initial high-precision map;

[0037] The vehicle performs path planning based on the corrected initial high-precision map.

[0038] This method helps to ensure the authenticity and accuracy of the planned path when the vehicle operates in the operation area, thereby ensuring the safety of the vehicle.

[0039] A high-precision map correction device includes:

[0040] An acquisition module, which is used to acquire the information of the initial high-precision map;

[0041] A positioning module, which is used to position the current location of the vehicle;

[0042] A vision module, which is used to identify the crops between rows;

[0043] A calculation module, which is used to calculate the similarity value according to the information of the positioning module and the information of the vision module, and compare the similarity value with a preset threshold.

[0044] This high-precision map correction device is used to execute the high-precision map correction method, which helps to ensure the stable and effective operation of the high-precision map correction method.

[0045] A storage medium stores programs or instructions, and when the programs or instructions are executed by a processor, the steps of the above-mentioned method are implemented.

[0046] A program product includes programs or instructions, and when the programs or instructions are executed by a processor, the steps of the above-mentioned method are implemented. Brief Description of the Drawings

[0047] 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 following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0048] Figure 1 is the logic diagram of the high-precision map correction method provided by the embodiments of the present invention;

[0049] Figure 2 is the schematic diagram of the crop planting situation in the theoretical scenario provided by the embodiments of the present invention;

[0050] Figure 3 is the schematic diagram of the crop planting situation in the actual scenario provided by the embodiments of the present invention;

[0051] Figure 4 is the schematic diagram of the relationship between the visual navigation point and the visual center line provided by the embodiments of the present invention;

[0052] Figure 5 is the comparison diagram of the actual center path and the initial path provided by the embodiments of the present invention;

[0053] Figure 6 is the schematic diagram of the high-precision map correction device provided by the embodiments of the present invention.

[0054] The markings in the figures are as follows:

[0055] 100 - Acquisition module;

[0056] 200 - Positioning module;

[0057] 300 - Vision module;

[0058] 400 - Calculation module. Detailed Embodiments

[0059] The following further describes the present application in detail in conjunction with the drawings and embodiments. It should be particularly noted that the following embodiments are only used to illustrate the present application, but do not limit the scope of the present application. Similarly, the following embodiments are only some embodiments of the present application rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0060] In the embodiments of the present application, all directional indications (such as up, down, left, right, front, back, etc.) are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly. The terms "include" and "have" and any variations thereof in the embodiments of the present application are intended to cover non-exclusive inclusion. 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 may optionally further include steps or units not listed, or may optionally further include other steps or components inherent to these processes, methods, products, or devices.

[0061] As Figure 1 shown, this embodiment provides a high-precision map correction method, and the high-precision map correction method includes the following steps:

[0062] S1. Obtain an initial path between crops in every two adjacent planting rows through the initial high-precision map, and the vehicle travels along the initial path.

[0063] S2. Identify the crops in the planting rows on both sides of the initial path, and obtain the actual central path of the crops.

[0064] S3. Calculate the similarity value of the actual central path relative to the initial path.

[0065] S4. If the similarity value is greater than a preset threshold, record the positions of the points on the actual central path as the first positions; and

[0066] S5. Deduce the second positions and the third positions in the planting rows on both sides of the initial path based on the first positions, and the second positions and the third positions are used to correct the initial high-precision map.

[0067] In this method, the vehicle travels along the initial path to facilitate the vehicle to obtain the actual planting information and growth condition information of the crops in two adjacent rows in real time, and dynamically correct the initial high-precision map according to the comparison between the actual central path and the initial path, which is beneficial to improving the consistency between the data and the actual environment, reducing errors, and helping to improve the map accuracy and adaptability. This method obtains a more complete and accurate high-precision map. The corrected high-precision map can be applied to the complex and changeable environmental conditions within the row in the fruit forest scene, can accurately plan the real path within the row, avoid the deviation caused by using the initial high-precision map, is beneficial to optimizing the vehicle operation path to a large extent, realizing the collision-free full-process autonomous closed-loop operation of the vehicle, reducing crop damage and operation efficiency reduction caused by path deviation within the planting row, and thus improving the intelligent level and economic benefits of agricultural production. Optionally, in this method, the vehicle driving process is carried out by an operator's manual driving.

[0068] Exemplarily, as Figure 2As shown, in the theoretical scenario, the crops in each planting row in the orchard are planted in a straight line and grow regularly. However, in the actual scenario, the crops in the orchard, as shown in Figure 3 show, there is an offset to the left or right of the crops relative to the theoretical termination position. If the actual center path deviates from the initial path by more than a predetermined threshold, and the vehicle still operates along the initial path in the theoretical scenario, it is considered that the offset-growing crops will pose a safety hazard to the vehicle's driving. For example, the offset-growing crops may cause a collision between the vehicle and the crops, and may also result in over-trimming when the vehicle trims the crops relatively close to the initial path, reducing the operation efficiency. By operating the vehicle along the corrected path, the probability of the above working conditions can be effectively reduced to improve the operation efficiency.

[0069] The vehicle in this embodiment can be any type of agricultural machinery vehicle. The orchard can be an orchard of any fruit such as grapes, blueberries, apples, pears, peaches, etc. In this embodiment, a grape orchard is taken as an example for illustration. In this embodiment, the planting is a row of grapevines planted in one direction, and the crop is a grapevine.

[0070] In this embodiment, the high-precision map is a map specially designed for the autonomous driving system, which provides road information accurate to the centimeter level, and specifically may include plot boundaries and various internal functional areas. The internal functional areas include, but are not limited to, parking areas, roadways, tractor roads, operation areas, planting rows, etc. More specifically, the high-precision map can include detailed data such as the geometry of the road, lane lines, traffic signs, signal lights, road facilities, and surrounding environment, and the accuracy usually reaches 10 - 20 centimeters.

[0071] If the similarity value is less than the preset threshold, it means that the deviation of the actual center path relative to the initial path is within the limited range of the preset threshold, and this deviation can be ignored. In the corrected high-precision map, the original path is still used for planning.

[0072] In this implementation, the high-precision map correction method is based on the vehicle's actual movement on the initial path of the crops in the planting row, and can be applied to the orchard scenario where the planting row is long and there are planting deviations.

[0073] Furthermore, this high-precision map correction method compares the similarity between the actual center path and the initial path with the preset threshold, and only needs to consider the lateral offset between the actual center path and the initial path, without considering the offset direction and angle between the two paths. This is beneficial to reducing the calculation difficulty and improving the accuracy of high-precision map correction.

[0074] As an optional solution, before obtaining the initial path between the crops in each adjacent two planting rows through the initial high-precision map in this embodiment, it further includes:

[0075] The dotting device collects the information of the plot boundary and each functional area inside the plot; draws the initial high-precision map; then the vehicle loads the initial high-precision map.

[0076] Among them, each functional area inside includes but is not limited to the parking area, the tractor road, the operation area, and the planting rows, etc. The information of the planting rows here includes the key point information of the head of each planting row and the key point information of the end of each planting row. The head is the starting position of the planting row, and the end is the ending position of the planting row. The way of collecting information by this dotting device has the advantages of high precision, strong reliability and suitability for static environments. And when the dotting device collects information for the planting rows, it only collects the key point information of the head and the end of the row, which is beneficial to improve efficiency and reduce costs.

[0077] As an alternative solution, the method for initial path planning includes:

[0078] Taking the center point of the heads of two adjacent planting rows as the starting point and the center point of the ends of two adjacent planting rows as the ending point; then a straight-line planning is carried out between the starting point and the ending point to form an initial path. This initial path planning method directly connects the starting point and the ending point, with low algorithm complexity, simple and efficient, and is suitable for crops with regular planting and growth, especially suitable for the situation where the vehicle corrects the path in real-time walking.

[0079] As an alternative solution, the method for obtaining the actual center path includes:

[0080] S21, drawing virtual lines based on the crops on two adjacent planting rows respectively; this virtual line helps to ensure that the path is aligned with the planting rows and reduces deviation.

[0081] S22, obtaining visual navigation points and a visual center line based on the vehicle position and the two virtual lines. The intersection point of the perpendicular line passing through the vehicle of the visual center line and the visual center line is the first position; the visual navigation points and the visual center line here are beneficial to accurately locate the vehicle position to improve the accuracy of calculation. At the same time, determining the first position through the position of the vehicle and the visual center line and calculating it in real-time during the vehicle's walking process is beneficial to reducing the positioning error.

[0082] S23, converting the coordinates of the visual navigation points into coordinates in the world coordinate system to avoid the accumulation of local errors.

[0083] S24, calculating the direction of the first position in the world coordinate system according to the heading information of the vehicle to obtain the actual center path passing through the first position.

[0084] The method for obtaining the actual central path realizes high-precision and real-time path planning through virtual lines, visual navigation points, and coordinate transformation, and is particularly suitable for scenarios that require high-precision navigation such as agricultural automation. Specifically, this method is conducive to realizing high-precision path planning based on the virtual lines and visual navigation points of crops, and calculates the path in real time based on the vehicle position and heading information, which is suitable for dynamic navigation tasks. The steps are clear and the computational complexity is moderate, which is conducive to ensuring real-time performance and efficiency. At the same time, this method improves the robustness of path planning through multi-sensor fusion of visual navigation points and vehicle heading information, converts visual data into the world coordinate system, realizes unified coordinate systems, and facilitates the fusion with other sensor data.

[0085] Specifically, the process of converting the coordinates of the visual navigation points into coordinates in the world coordinate system is specifically to convert the visual navigation points from the image coordinate system to the world coordinate system through the internal and external parameter matrices of the camera. The specific steps include the conversion from image coordinates to camera coordinates and then to world coordinates.

[0086] In this embodiment, the information of the visual navigation points includes the lateral deviation and heading deviation information between the current vehicle position and the visual center line. Among them, the lateral deviation information is the lateral distance between the vehicle's position and the visual center line. The heading deviation information is the angle between the vehicle's driving direction and the direction of the visual center line. The lateral deviation and heading deviation information can detect the deviation of the vehicle from the initial path in real time, dynamically update the data, adapt to environmental changes, and provide a real-time and dynamic correction basis for the high-precision map, which is conducive to improving the accuracy, robustness, and adaptability of the high-precision map.

[0087] As an alternative solution, the vehicle obtains visual navigation points through a binocular camera. The binocular camera calculates depth information through parallax, which is conducive to providing high-precision distance measurement, helping the vehicle accurately perceive the surrounding environment. The binocular camera has a lower cost, and through image recognition information, it is not easily interfered by crop branches and leaves, and is more suitable for agricultural scenarios, which is conducive to improving the accuracy of the recognition results. This binocular camera is compared with the commonly used lidar.

[0088] At the same time, compared with the dotting device used to collect the information of the initial high-precision map, the dotting device is only suitable for collecting the coordinates at the beginning and end of the planting row for straight-line planning. The dotting device cannot complete the whole-row operation of the driverless vehicle on the initial path, and for the situation where there are planting deviations in the planting row, the dotting device is still used to collect information for high-precision map correction, with too low efficiency and requiring a large amount of human and time costs. In this embodiment, the binocular camera can effectively solve the problems brought by the dotting device for collecting information, which is conducive to improving the accuracy and authenticity of correcting the initial high-precision map, and at the same time, the consumed human and time costs are relatively low.

[0089] More specifically, the binocular camera can be a binocular camera.

[0090] Specifically, as Figure 4 shown, during the vehicle's movement, the lateral deviation and the course deviation include the following four situations:

[0091] As Figure 4 shown in Figure a, the visual center line is shifted to the right relative to the vehicle position, and the vehicle's traveling direction is to the left front relative to the visual center line.

[0092] As Figure 4 shown in Figure b, the visual center line is shifted to the right relative to the vehicle position, and the vehicle's traveling direction is to the right front relative to the visual center line.

[0093] As Figure 4 shown in Figure c, the visual center line is shifted to the left relative to the vehicle position, and the vehicle's traveling direction is to the left front relative to the visual center line.

[0094] As Figure 4 shown in Figure d, the visual center line is shifted to the left relative to the vehicle position, and the vehicle's traveling direction is to the right front relative to the visual center line.

[0095] As an alternative solution, the method for calculating the similarity value includes:

[0096] S31, calculating the normal vector of the initial path; and

[0097] S32, calculating the straight-line distance between the intersection point of the normal vector passing through the vehicle position and the initial path and the intersection point of the actual center path, and the straight-line distance is the similarity value.

[0098] As Figure 5 shown, the initial path is L1, the actual center path is L2, first calculate the normal vector of the initial path L1:

[0099] The normal vector of the initial path L1 = the angle * the direction vector of L1, and the angle here is 90°.

[0100] Where P is the current vehicle position, the normal vector of the initial path L1 is the vector perpendicular to the initial path L1. In the figure, AB is perpendicular to the initial path L1, that is, the vector AB is the normal vector of the initial path L1, and B is the intersection point of the normal vector of the initial path L1 and the actual center path L2.

[0101] At this time, the similarity value is the distance between points A and B. Let the coordinates of point A be (Ax, Ay) and the coordinates of point B be (Bx, By). At this time, the calculation formula of the similarity value is as follows:

[0102]

[0103] When the similarity value |AB| is greater than the preset threshold, it is considered that the visual center line at the current position deviates from the initial path L1, and it is necessary to record this B position as the first position for correcting the initial high-precision map. After the high-precision map of the entire operation area is corrected, the corrected initial high-precision map can be used for path planning, which will greatly improve the authenticity and accuracy of the planned path.

[0104] Specifically, there are three cases where the actual center path L2 is parallel to, outwardly inclined to, and inwardly inclined to the initial path L1. Since the calculation method of the similarity value |AB| does not need to consider the angle of the actual center path L2, the similarity value calculation method of this embodiment can be applied to the three cases where the actual center path L2 is parallel to, outwardly inclined to, and inwardly inclined to the initial path L1, which is beneficial to simplifying the calculation difficulty of the similarity value, with a moderate amount of calculation, and further simplifies the method of correcting the high-precision map, making it suitable for dynamic navigation tasks.

[0105] In this embodiment, the calculation method of the similarity value |AB| does not need to consider whether the actual center path L2 deviates to the left or right relative to the initial path L1, and the calculation method of the similarity value |AB| does not need to consider whether the actual center path L2 is in the left front or right front relative to the initial path L1. Therefore, the similarity value calculation method of this embodiment can be applied to the four cases of a, b, c, and d in the drawings, which is beneficial to simplifying the calculation difficulty of the similarity value, and further simplifies the method of correcting the high-precision map.

[0106] In some embodiments, the method for calculating the second position and the third position in the planting rows on both sides of the initial path based on the first position includes: using the first position as the midpoint, and calculating the second position and the third position according to the width of the planting row and the distance from the center path to the planting row.

[0107] This method transforms the first position obtained after calculating the similarity value into the planting row, so that the second position and the third position form key points in the high-precision map, and are further used as reference points for path planning.

[0108] In this embodiment, the high-precision map correction method further includes:

[0109] S6. The vehicle travels on the initial path between each adjacent two rows of crops in the operation area, collects data, and records the first position where the similarity value is greater than the preset threshold. This step is for the vehicle to travel on each initial path and repeat the steps of S1 - S5.

[0110] S7. Complete the correction of the high-precision map.

[0111] S8. The vehicle performs path planning based on the corrected initial high-precision map.

[0112] This method is conducive to ensuring the authenticity and accuracy of the planned path when the vehicle operates in the operation area, thereby ensuring the safety of the vehicle.

[0113] Specifically, there are the following working conditions for the method of path planning based on the revised first version of the high-precision map:

[0114] First, when the vehicle is moving on the initial path, if the dual-sided camera of the vehicle only recognizes a first position with a similarity value greater than the preset threshold as a correction point, then when correcting the initial path, only the path needs to be re-planned with this correction point as the discontinuous point. At this time, the path planning method between the starting point and the correction point and between the correction point and the end point can be straight-line planning or reasonable curve planning. This method has low algorithm complexity, is simple and efficient, and is applicable to crops with regular planting and growth. It is especially suitable for the situation where the vehicle corrects the path in real-time walking, which is conducive to ensuring the safety of the vehicle when operating with the corrected initial path, and is conducive to achieving the accuracy and efficiency of path planning.

[0115] Second, when the vehicle is moving on the initial path, if the dual-sided camera of the vehicle only recognizes multiple first positions with similarity values greater than the preset threshold as correction points, then when correcting the initial path, path planning is performed between the first correction point and the starting point of the initial path, path planning is performed between the last correction point and the end point of the initial path, and path planning is sequentially performed between adjacent two correction points between the first correction point and the last correction point to form a corrected path.

[0116] Of course, the path planning between the starting point and the correction point, between the correction point and the end point, and between adjacent two correction points can be straight-line planning or reasonable curve planning.

[0117] Such as Figure 6As shown in the figure, this embodiment also provides a high-precision map correction device, which includes an acquisition module 100, a positioning module 200, a vision module 300, and a calculation module 400. Among them, the acquisition module 100 is used to acquire the initial high-precision map information. After the dotter acquires information and draws the initial high-precision map, the acquisition module 100 is used to read the initial high-precision map and read the initial path in the initial high-precision map, so that the vehicle can walk on the ground and correct the initial high-precision map between rows. The positioning module 200 is used to locate the current position of the vehicle. The vision module 300 is used to identify the crops between rows; and the actual center point positions of the crops on both sides of the current position of the vehicle are identified through the vision module 300, and then used to calculate the similarity value. The calculation module 400 is used to calculate the similarity value according to the information of the positioning module 200 and the information of the vision module 300, and compare the similarity value with a preset threshold. It can be understood that when the vision module 300 and the positioning module 200 acquire information, the calculation module 400 integrates the position information of the positioning module 200 and the vision center point information of the vision module 300 through calculation, and calculates according to a preset calculation formula. This high-precision map correction device is used to execute the high-precision map correction method, which is beneficial to ensuring the stable and effective operation of the high-precision map correction method.

[0118] Exemplarily, the vision module is a binocular camera.

[0119] This embodiment also provides a storage medium that stores programs or instructions, and the programs or instructions are executed by a processor to perform the steps of the above high-precision map correction method. Optionally, the above storage medium is an electronic storage medium. Optionally, the above storage medium is a computer-readable storage medium, but not limited thereto, and it can also be other device-readable storage mediums. Optionally, the above storage medium can be a non-transitory storage medium, but not limited thereto, and it can also be a temporary storage medium.

[0120] The processor can be a general-purpose processor or a dedicated processor, etc. For example, it can be a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control communication devices (such as base stations, baseband chips, terminals, terminal chips, DUs or CUs, etc.), execute programs, and process program data.

[0121] The present disclosure also proposes a program product, including programs and / or instructions. When the above programs and / or instructions are executed by a processor, the processor is caused to execute any of the above methods. Optionally, the above program product is a computer program product. Optionally, the above program product is stored on the above storage medium.

[0122] The present disclosure also provides a computer program which, when running on a computer, causes the computer to execute any of the above methods. Those of ordinary skill in the art will appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present disclosure.

[0123] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. They are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the present invention.

[0124] In the present invention, unless otherwise clearly defined and limited, the terms "mounted", "connected", "coupled", "fixed", etc. should be construed broadly. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection, an electrical connection, or communicable with each other; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the internal communication of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0125] In the present invention, unless otherwise clearly defined and limited, the first feature being "on" or "under" the second feature may be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, the first feature being "above", "over" and "on top of" the second feature may be that the first feature is directly above or obliquely above the second feature, or merely indicates that the first feature has a higher horizontal height than the second feature. The first feature being "under", "beneath" and "underneath" the second feature may be that the first feature is directly below or obliquely below the second feature, or merely indicates that the first feature has a lower horizontal height than the second feature.

[0126] In the present invention, terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0127] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A high-precision map correction method, characterized in that, Including: Obtain an initial path between crops in every two adjacent planting rows through a first - edition high - precision map, and the vehicle travels along the initial path; Identify the crops in the planting rows on both sides of the initial path, and obtain the actual center path of the crops; Calculate the similarity value of the actual center path relative to the initial path; If the similarity value is greater than a preset threshold, record the positions of the points on the actual center path as the first positions; And Based on the first positions, deduce second positions and third positions in the planting rows on both sides of the initial path, and the second positions and the third positions are used to correct the first - edition high - precision map.

2. The high-precision map correction method according to claim 1, wherein The method for obtaining the actual center path includes: Draw virtual lines based on the crops on two adjacent planting rows respectively; Based on the position of the vehicle and the two virtual lines, obtain visual navigation points and a visual center line. The intersection point of the perpendicular line passing through the vehicle of the visual center line and the visual center line is the first position; Convert the coordinates of the visual navigation points into coordinates in the world coordinate system; and Calculate the direction of the first position in the world coordinate system according to the heading information of the vehicle, and obtain the actual center path passing through the first position.

3. The high-precision map correction method according to claim 2, characterized in that, The vehicle obtains visual navigation points through a binocular camera.

4. The high-precision map correction method according to claim 1, wherein The method for calculating the similarity value includes: Calculate the normal vector of the initial path; and Calculate the straight - line distance between the intersection point of the normal vector passing through the vehicle position and the initial path and the intersection point of the actual center path, and the straight - line distance is the similarity value.

5. The high-precision map correction method according to any one of claims 1-4, characterized in that, The method for deducing the second positions and third positions in the planting rows on both sides of the initial path based on the first positions includes: Take the first positions as the mid - points, and calculate the second positions and the third positions according to the width of the planting rows and the distance from the center path to the planting rows.

6. The high-precision map correction method according to any one of claims 1-4, characterized in that The method for initial path planning includes: The center points of the row - heads of two adjacent planting rows are used as the starting points, and the center points of the row - tails of two adjacent planting rows are used as the ending points; Perform straight - line planning on the starting points and the ending points to form the initial path.

7. The high-precision map correction method according to any one of claims 1-4, characterized in that, Before obtaining the initial path between crops in every two adjacent planting rows through the first - edition high - precision map, it further includes: A dotting device collects plot boundary information and information on each functional area inside the plot; Draw a first - edition high - precision map; and The vehicle is added to the first - edition high - precision map.

8. The high-precision map correction method according to any one of claims 1-4, characterized in that, The high - precision map correction method further includes: The vehicle travels on the initial path between every two adjacent crop rows in the operation area, collects data, and records the first positions where the similarity value is greater than the preset threshold; Complete the correction of the first - edition high - precision map; The vehicle performs path planning according to the corrected first - edition high - precision map.

9. A high-precision map correction device, characterized in that, Including: An acquisition module, which is used to acquire first - edition high - precision map information; A positioning module, which is used to position the current position of the vehicle; A vision module, which is used to identify the crops between rows; A calculation module, which is used to calculate the similarity value according to the information of the positioning module and the information of the vision module, and compare the similarity value with the preset threshold.

10. A storage medium, characterized in that, The storage medium stores a program or instructions, and the program or instructions, when executed by a processor, implement the steps of the method according to any one of claims 1 to 8.

11. A program product, characterized in that, It includes a program or instructions, and the program or instructions, when executed by a processor, implement the steps of the method according to any one of claims 1 to 8.

Images