Path planning method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides a path planning method and device, electronic equipment and a computer readable storage medium. The method comprises the steps that boundary information in a target area is acquired; determining a driving path of the target equipment according to the boundary information; a set position point in the driving path is optimized through a local path planning algorithm; the target device is configured to travel in the target area according to the optimized travel path. According to the embodiment of the invention, the set position point in the driving path is optimized according to the local path algorithm, the set position point in the path can be dynamically adjusted and optimized according to the real-time environment information of the target area, and the safety and stability of the driving path are improved.

Description

Technical Field

[0001] The present application relates to the field of path planning, and more specifically, to a path planning method, device, electronic device, and computer-readable storage medium. Background Art

[0002] In modern production and living environments, the driving routes of equipment are not fixed, but need to be dynamically adjusted according to actual working conditions. For example, agricultural machinery working in farmland needs to flexibly move to the next designated location after completing different tasks. This requires the path planning algorithm to respond to changes in working conditions and terrain in real time to provide the optimal path.

[0003] However, due to its fixed nature, the traditional reciprocating path planning method is difficult to cope with the complex and changeable farmland environment, resulting in inefficiency of the target equipment when performing tasks, and may even cause errors, affecting work efficiency and accuracy. Summary of the invention

[0004] In view of this, the purpose of the embodiments of the present application is to provide a path planning method, device, electronic device and computer-readable storage medium, which can improve the safety and stability of the driving path while improving the adaptability of the target device to complex environments.

[0005] In a first aspect, an embodiment of the present application provides a path planning method for obtaining boundary information in a target area; determining a driving path of a target device based on the boundary information; optimizing set position points in the driving path through a local path planning algorithm; wherein the target device is configured to travel in the target area according to the optimized driving path.

[0006] In the above implementation process, by optimizing the set position points in the driving path according to the local path algorithm, the set position points in the path can be dynamically adjusted and optimized according to the real-time environmental information of the target area, thereby improving the safety and stability of the driving path while improving the adaptability of the target device to complex environments.

[0007] In one embodiment, the local path planning algorithm is a B-spline curve optimization algorithm, and the optimization of the set position points in the driving path by the local path planning algorithm includes: calculating the curvature of each point in the driving path; traversing all position points in the driving path to determine the point set that does not meet the curvature constraint condition; and optimizing the path adjacent to the point set by the B-spline curve optimization algorithm.

[0008] In the above implementation process, by calculating the curvature of each point in the driving path, and filtering out the point set that does not meet the curvature constraint condition through the curvature constraint condition, and then optimizing the point set that does not meet the curvature constraint condition, each position point in the optimized driving path can meet the curvature constraint condition, thereby improving the smoothness of the driving path, reducing the loss of the target device, and improving the adaptability of the target device to complex environments, while improving the accuracy and stability of the driving path.

[0009] In one embodiment, the optimizing process of the path adjacent to the point set by the B-spline curve optimization algorithm includes: establishing a non-uniform rational B-spline curve; constructing an objective function according to the non-uniform rational B-spline curve; wherein the objective function is configured to define a distance between a minimized path and an actual position point; and establishing an optimization model based on the objective function and the curvature constraint; wherein the optimization model is configured to optimize the path adjacent to the point set.

[0010] In the above implementation process, by using the B-spline curve optimization algorithm to optimize the driving path, the driving path of the target equipment can be accurately optimized to ensure that the target equipment has good smoothness while maintaining efficient operation. Not only can the turning radius of the target equipment when operating in the target area be reduced, thereby improving operating efficiency and reducing energy consumption. In addition, when the target area is a farmland, this method is particularly effective in protecting farmland crops and soil. During the turning process of the target equipment (such as intelligent agricultural machinery), due to the smooth optimization of the path, the direct crushing and friction of the crops by the intelligent agricultural machinery can be greatly reduced, effectively avoiding the risk of crop damage. At the same time, the reduction in the turning radius also means that the compaction effect of the intelligent agricultural machinery on the soil is weakened, which helps to maintain the looseness and air permeability of the soil and provide more favorable conditions for the root growth of crops.

[0011] In one embodiment, the boundary information includes a boundary path; before determining the driving path of the target device according to the boundary information, the method also includes: constructing a nonlinear boundary area according to the boundary information; smoothing the boundary of the nonlinear boundary area; determining the extreme point area in the nonlinear boundary area; and designing a nonlinear spiral path for the nonlinear boundary area according to the extreme point area.

[0012] In the above implementation process, by constructing a nonlinear boundary area and designing a nonlinear spiral line based on the extreme points in the nonlinear boundary area, complex geometric areas can be effectively covered, the overlaps and gaps between paths can be reduced, the utilization rate of the paths can be improved, and the mobility efficiency of mobile devices can be improved.

[0013] In one embodiment, the boundary information includes a boundary path; determining the driving path of the target device based on the boundary information includes: constructing a contour line equation based on the boundary information; obtaining multiple paths based on the contour line equation; merging the multiple paths into one path; wherein the merged path is the driving path.

[0014] In the above implementation process, by dividing the target area into multiple paths and merging the multiple paths into one path, complex geometric areas can be effectively covered and the overlaps and gaps between paths can be reduced. This can not only optimize the driving path, but also save the action time of the target equipment and the fuel required for the operation, thereby improving the overall efficiency of the operation.

[0015] In one embodiment, the extreme point region in the nonlinear boundary region is a single extreme point region; the nonlinear spiral path design of the nonlinear boundary region according to the extreme point region includes: taking the extreme point as the center, constructing multiple nonlinear equidistant paths with a first set spacing inside the nonlinear boundary until the spacing between adjacent paths is less than a second set spacing; selecting a position point on any path as a first position point, and determining a second position point adjacent to the first position point on the same path according to the shape parameters of the target device; wherein the first position point is a starting point; for each path, determining a third position point on a subsequent path adjacent to the previous path that is closest to the second position point on the previous path, and determining a second position point adjacent to the third position point on the same path according to the shape parameters of the target device; until a corresponding position point is found in each of the multiple paths; disconnecting the line between two adjacent position points on each path, and connecting two position points closest to each other on two adjacent paths to obtain a path.

[0016] In the above implementation process, for the single extreme point area, multiple paths can be merged into one path by disconnecting the line between two adjacent position points on each path and connecting the two closest position points on two adjacent paths. The entire implementation method is simple and easy to implement. Moreover, when connecting adjacent paths, the closest position points are selected for connection, which can reduce the overall path length of the driving path, reduce the driving distance of the target equipment, and improve work efficiency.

[0017] In one embodiment, the extreme point region in the nonlinear boundary region is a multi-extreme point region, and the method of constructing a plurality of nonlinear equidistant paths with a first set spacing inside the nonlinear boundary with the extreme point as the center until the spacing between adjacent paths is less than the second set spacing includes: constructing a plurality of nonlinear equidistant paths with a first set spacing inside each nonlinear boundary with each extreme point as the center, until the spacing between adjacent paths inside each nonlinear boundary is less than the second set spacing; determining whether the paths corresponding to the adjacent extreme points are connectable; and when it is determined that the paths corresponding to the adjacent extreme points are connectable, connecting the adjacent paths by performing a broken edge reconnection operation on the boundary paths of the paths corresponding to the adjacent extreme points; and when connecting the adjacent A position point is selected as the first position point on any path of the overall path formed after the target device is determined, and a second position point adjacent to the first position point on the same path is determined according to the shape parameters of the target device; wherein the first position point is the starting point; for each path, a third position point on a subsequent path adjacent to the previous path is determined that is closest to the second position point on the previous path, and a second position point adjacent to the third position point on the same path is determined according to the shape parameters of the target device; until the corresponding position point is found in each of the multiple paths; disconnect the line between two adjacent position points on each path, and connect the two position points closest to each other on two adjacent paths to obtain a path.

[0018] In the above implementation process, for areas with multiple extreme points, by judging whether the paths corresponding to adjacent extreme points can be connected, if the adjacent extreme points can be connected, the boundary paths corresponding to the adjacent extreme points are opened up to form an overall path, and then the various paths in the overall path are merged into one path, so that the driving path can cope with complex terrain environments, thereby increasing the use scenarios of the path planning method.

[0019] In one embodiment, obtaining boundary information in a target area includes: preprocessing a captured target image of the target area; initializing a level set function to calculate an image gradient of the target image; determining a boundary of the target area in the target image based on the image gradient; updating the level set function by regularizing the level set evolution equation; and outputting the boundary information of the target image when the level set function approaches the boundary of the target area.

[0020] In the above implementation process, by adopting the regularized level set evolution equation to determine the boundary information of the target area, the smoothness and shape of the boundary can be controlled and adjusted, thereby improving the accuracy of boundary information extraction and the smoothness and stability of the boundary.

[0021] In a second aspect, an embodiment of the present application also provides a path planning device, comprising: an acquisition module for acquiring boundary information in a target area; a determination module for determining a driving path of a target device based on the boundary information; an optimization module for optimizing set position points in the driving path through a local path planning algorithm; wherein the target device is configured to travel in the target area according to the optimized driving path.

[0022] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform the steps of the method in the above-mentioned first aspect, or any possible implementation of the first aspect.

[0023] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the path planning method in the above-mentioned first aspect, or any possible implementation manner of the first aspect are executed.

[0024] In order to make the above-mentioned objects, features and advantages of the present application more obvious and understandable, embodiments are given below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 A block diagram of an electronic device provided in an embodiment of the present application;

[0027] Figure 2 A flow chart of a path planning method provided in an embodiment of the present application;

[0028] Figure 3 A schematic diagram showing the comparison of the driving path before and after optimization provided in the embodiment of the present application;

[0029] Figure 4 A schematic diagram of a nonlinear boundary region provided in an embodiment of the present application;

[0030] Figure 5 A schematic diagram of single extreme point area path planning provided in an embodiment of the present application;

[0031] Figure 6A schematic diagram of a multi-extreme point area path planning provided in an embodiment of the present application;

[0032] Figure 7 A process diagram of generating a driving path for the path planning method provided in an embodiment of the present application;

[0033] Figure 8 A schematic diagram of driving path merging in a single extreme point area provided in an embodiment of the present application;

[0034] Fig. 9 A schematic diagram of merging driving paths in a multi-extreme point area provided in an embodiment of the present application;

[0035] Fig.10 A schematic diagram of the functional modules of the path planning device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings in the embodiments of the present application.

[0037] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0038] With the advancement of science and technology, production mechanization has become a key factor in improving agricultural and / or industrial production efficiency and competitiveness. The use of automated equipment can not only significantly reduce labor intensity and improve work efficiency, but also achieve quantitative production in large-scale production, optimize resource allocation, and reduce production costs. For example, in the process of agricultural modernization, the popularization and application of agricultural machinery has significantly improved the yield and quality of crops, helping agriculture to transform from traditional labor-intensive to technology-intensive.

[0039] However, in areas with complex terrain and widespread hills and mountains, such as southern my country, since most of the farmlands in these areas are small and scattered, numerous small and fragmented fields have been formed. This terrain feature determines the particularity of agricultural production in the south and also makes agricultural mechanization face unique challenges. Due to the scattered small and fragmented plots of land in hilly and mountainous areas and the undulating terrain, traditional large agricultural machinery is difficult to operate flexibly in these areas and is easily restricted by the terrain, resulting in low operating efficiency. In addition, the farmland environment in hilly areas is complex and there are many obstacles, which further increases the difficulty of agricultural machinery operation. When agricultural machinery operates in these areas, it is often necessary to manually plan the path, or only some straight-in and straight-out paths can be planned. This process takes a lot of time and manpower, and is prone to errors, reducing operating efficiency and accuracy.

[0040] In view of this, the present application proposes a path planning method, which optimizes the set position points in the driving path according to the local path algorithm, and can dynamically adjust and optimize the set position points in the path according to the real-time environmental information of the target area, thereby improving the safety and stability of the driving path while improving the adaptability of the target device to complex environments.

[0041] To facilitate understanding of this embodiment, an electronic device that executes the path planning method disclosed in the embodiment of the present application is first introduced in detail.

[0042] like Figure 1 , which is a block diagram of an electronic device. The electronic device 100 may include a memory 111 and a processor 113. A person skilled in the art may understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the electronic device 100. For example, the electronic device 100 may further include Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0043] The memory 111 and the processor 113 are directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, these elements can be electrically connected to each other via one or more communication buses or signal lines. The processor 113 is used to execute the executable module stored in the memory.

[0044] The memory 111 may be, but not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc. The memory 111 is used to store programs, and the processor 113 executes the program after receiving the execution instruction. The method executed by the electronic device 100 defined by the process disclosed in any embodiment of the present application can be applied to the processor 113, or implemented by the processor 113.

[0045] The processor 113 may be an integrated circuit chip with signal processing capability. The processor 113 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be 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, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0046] The electronic device 100 in this embodiment can be used to execute each step in each method provided in the embodiments of the present application. The implementation process of the path planning method is described in detail below through several embodiments.

[0047] See also Figure 2 , is a flow chart of the path planning method provided in the embodiment of the present application. Figure 2 The specific process shown is described in detail.

[0048] Step 201: Obtain boundary information in a target area.

[0049] The target area here is the area where the target equipment performs work, such as a field, a mine-clearing area, a cleaning area, etc. The target area can be selected according to actual conditions.

[0050] Optionally, the target device may be a sweeping robot, an intelligent agricultural machine, a mine-sweeping robot, a reconnaissance drone, etc. The target device may be selected according to actual conditions.

[0051] In one embodiment, before step 201, the method further includes: acquiring an image of the target area.

[0052] Among them, the target area image can be obtained by an image acquisition device such as an aerial survey drone, a camera, and a sky eye. The image acquisition device used to obtain the target area image can be selected according to actual conditions.

[0053] It can be understood that after the target area image of the target area is acquired, the boundary information in the target area image can be extracted by edge detection operators, morphological algorithms, chain code boundary extraction, etc.

[0054] The boundary information may include edge pixels, edge direction, edge strength, edge curvature, boundary path and other information, and the boundary information may be selected according to actual conditions.

[0055] Step 202: determine the driving path of the target device according to the boundary information.

[0056] The driving path here can be determined by a global planning method, a local planning method, etc., and the method for determining the driving path can be selected according to actual conditions.

[0057] The driving path configuration is determined based on the starting point, the end point and the boundary information of the target area of ​​the target device.

[0058] Step 203: Optimize the set position points in the driving path through a local path planning algorithm.

[0059] Understandably, the driving path determined directly based on the starting point, end point, and boundary information of the target area of ​​the target equipment may have discontinuous curvature, which may cause the front wheel angle to change suddenly when the agricultural machinery turns, and there are certain risks. Based on this, after determining the driving path, the set position points in the driving path can be further optimized through the local path planning algorithm, so that the optimized driving path has continuous curvature and smooth transition, thereby improving the accuracy of the target equipment.

[0060] The local path planning algorithm here can be an algorithm such as the shortest tangent method, the Bezier curve method, and the B-spline curve optimization algorithm. The local path planning algorithm can be selected according to actual conditions.

[0061] Among them, the shortest tangent method refers to a method of avoiding obstacles by calculating the tangent path, thereby finding a path as short as possible. The shortest tangent method has the advantages of fast path generation speed and simple implementation.

[0062] The Bezier curve method refers to a method of defining and generating a smooth curve by controlling points. The Bezier curve method has the advantages of improving the continuity of the path and reducing the steering load.

[0063] The B-spline curve optimization algorithm is a method for generating smooth trajectories based on a parametric curve based on control points. The B-spline curve optimization algorithm has the advantages of making the path curvature continuous and smooth by reasonably setting the control points, significantly reducing the sharp changes when the target device turns, ensuring the accuracy and stability of path tracking, and being able to flexibly cope with complex terrain environments.

[0064] The above-mentioned set position point refers to any position point in the driving path, and the set position point can be selected according to actual conditions.

[0065] In one embodiment, the target device is configured to travel in the target area according to the optimized driving path.

[0066] In the above implementation process, by optimizing the set position points in the driving path according to the local path algorithm, the set position points in the path can be dynamically adjusted and optimized according to the real-time environmental information of the target area, thereby improving the safety and stability of the driving path and improving the adaptability of the target device to complex environments.

[0067] In a possible implementation, step 203 includes: calculating the curvature of each point in the driving path; traversing all position points in the driving path to determine a point set that does not satisfy the curvature constraint condition; and optimizing the path adjacent to the point set using a B-spline curve optimization algorithm.

[0068] The curvature calculation here can be achieved by the three-point method, that is, the curvature of each point on the driving path is solved and analyzed by traversing three points to form an approximate arc.

[0069] For example, if there are i+1 original path points p i , the corresponding curvature radius of each path point is r i The solution formula can be:

[0070]

[0071] Then the curvature k i Can be:

[0072]

[0073] In order to satisfy the curvature constraint, the following constraints can be set:

[0074] r i ≥r min ;

[0075] in, is the straight line between the ith original path point and the i+1th original path point, is the straight line between the ith original path point and the i-1th original path point, r min is the minimum radius of curvature.

[0076] It can be understood that when a position point in the driving path satisfies the curvature constraint, it is determined that the curvature at the position point can make the target device transition smoothly. Therefore, no further optimization is required for the position point that satisfies the curvature constraint. When a position point in the driving path does not satisfy the curvature constraint, it is determined that the curvature at the position point cannot make the target device transition smoothly, which may affect the driving stability of the target device. Therefore, the position point that does not satisfy the curvature constraint needs to be further optimized so that the optimized curvature satisfies the curvature constraint.

[0077] In the above implementation process, by calculating the curvature of each point in the driving path, and filtering out the point set that does not meet the curvature constraint condition through the curvature constraint condition, and then optimizing the point set that does not meet the curvature constraint condition, each position point in the optimized driving path can meet the curvature constraint condition, thereby improving the smoothness of the driving path, reducing the loss of the target device, and improving the adaptability of the target device to complex environments, while improving the accuracy and stability of the driving path.

[0078] In a possible implementation, a path adjacent to a point set is optimized by a B-spline curve optimization algorithm, including: establishing a non-uniform rational B-spline curve; constructing an objective function according to the non-uniform rational B-spline curve; and establishing an optimization model based on the objective function and curvature constraints.

[0079] Among them, the non-uniform rational B-spline curve can be expressed by the following formula:

[0080]

[0081] Where C(u) is a non-uniform rational B-spline curve, N i , p(u) is the B-spline curve basis function, P i is the path control point, ω i is the weight coefficient.

[0082] The objective function here is configured to define the distance between the path and the actual position point to be minimized, and the objective function satisfies the curvature constraint.

[0083] In one embodiment, the objective function can be expressed as:

[0084]

[0085] Among them, J is the objective function, D j is the actual point on the path, and m is the number of path points.

[0086] The above optimization model is configured to optimize the paths adjacent to the point set. The optimization model can be expressed as:

[0087]

[0088] Understandably, if Figure 3 As shown, Figure 3 The comparison of the driving path before and after optimization is shown in Figure 3 The driving path before optimization shown in (a) is Figure 3 The driving path before optimization is shown in (b) of FIG. Figure 3 It can be seen that the B-spline curve optimization algorithm under the curvature constraint condition can accurately optimize the driving path of the target equipment, ensuring that the target equipment has good smoothness while maintaining efficient operation. Not only can the turning radius of the target equipment when operating in the target area be reduced, thereby improving operating efficiency and reducing energy consumption. Moreover, when the target area is a farmland, this method is particularly effective in protecting farmland crops and soil. During the turning process of the target equipment (such as intelligent agricultural machinery), due to the smooth optimization of the path, the direct crushing and friction of the intelligent agricultural machinery on the crops can be greatly reduced, effectively avoiding the risk of crop damage. At the same time, the reduction in the turning radius also means that the compaction effect of the intelligent agricultural machinery on the soil is weakened, which helps to maintain the looseness and air permeability of the soil and provide more favorable conditions for the root growth of crops.

[0089] In the above implementation process, by using the B-spline curve optimization algorithm to optimize the driving path, the driving path of the target equipment can be accurately optimized to ensure that the target equipment has good smoothness while maintaining efficient operation. Not only can the turning radius of the target equipment when operating in the target area be reduced, thereby improving operating efficiency and reducing energy consumption. In addition, when the target area is a farmland, this method is particularly effective in protecting farmland crops and soil. During the turning process of the target equipment (such as intelligent agricultural machinery), due to the smooth optimization of the path, the direct crushing and friction of the crops by the intelligent agricultural machinery can be greatly reduced, effectively avoiding the risk of crop damage. At the same time, the reduction in the turning radius also means that the compaction effect of the intelligent agricultural machinery on the soil is weakened, which helps to maintain the looseness and air permeability of the soil and provide more favorable conditions for the root growth of crops.

[0090] In a possible implementation, before step 202, the method further includes: constructing a nonlinear boundary region based on boundary information; performing boundary smoothing on the boundary of the nonlinear boundary region; determining an extreme point region in the nonlinear boundary region; and performing a nonlinear spiral path design on the nonlinear boundary region based on the extreme point region.

[0091] like Figure 4 As shown, the nonlinear boundary region here is configured to include a plurality of straight lines and / or curves connected end to end, and the nonlinear boundary region is a closed region. The nonlinear boundary region can be expressed as:

[0092]

[0093] Where L is the nonlinear boundary region, L i is the i-th curve, and n is the total number of curves that constitute the nonlinear boundary region.

[0094] For each curve in the nonlinear boundary region, it can be assumed that each curve L i (where i = 1, 2, ..., n-1, n) are all continuous and differentiable paths in the plane. These paths can be parameterized, such as L i = i (), where t is the parameter, r i () is a two-dimensional vector function used to represent points on the curve.

[0095] Furthermore, the endpoints of these curves can be defined. For example, suppose L i The starting point is P i , the end point is P i+1 (Among them, we can make P n+1 =1, to indicate closure). Therefore, each segment of the curve L i Connect point P i and P i+1 Then a closed plane region R can be constructed, which consists of the above curve segments L i The plane area R can be expressed as:

[0096] t 1,2 ,…,t n For i in the region and for all t i ,t i+1 , so that x is located from r i ( i ) to r i+1 ( i+1 ) is established on the path.

[0097] Among them, in order to ensure the area is closed, r n ( n ) coincides with the starting point of r1(1), that is, P n+1 =1 to ensure the closedness of the area.

[0098] The boundary smoothing of the above nonlinear boundary can be processed by arc.

[0099] For example, if a circular arc with a radius of r is used to smooth the boundary L so that the minimum curvature radius of the smoothed curve is greater than r, then the curvature of the curve needs to be constrained. The curvature is a measure of the degree of curvature of the curve at a certain point.

[0100] For a two-dimensional curve y=f(x), its curvature can be expressed as:

[0101]

[0102] For a parameterized curve r(t)=(x(t),y(t)), its curvature can be expressed as:

[0103]

[0104] The determination of extreme point regions here can be divided into single extreme point region determination and multiple extreme point region determination.

[0105] Among them, Figure 5 As shown, the single extreme point area can be determined in the following way: Based on the nonlinear boundary L1-L2-…L n-1 -L n Construct the inscribed circle O-O1 and the circumscribed circle O-O2, as well as multiple intermediate circles OO between the inscribed circle and the circumscribed circle x The origins of the above intermediate circles, inscribed circles, and circumscribed circles form a circle with a radius not exceeding r. L The origin area. L The region is regarded as the pole region of the nonlinear region and is used as the radius r of the inscribed circle. o1 , the radius of the circumscribed circle r o2 and the radius of the middle circle r ox .

[0106] like Figure 6 As shown, the multi-extreme point area can be determined by the following method: constructing inscribed circles O3-O3, O5-O5, circumscribed circles O3-O4, O5-O6, and multiple intermediate circles O3-O4 between the inscribed circles and the circumscribed circles based on the nonlinear boundary. x 、O5-O x The origins of the above intermediate circles, inscribed circles, and circumscribed circles form a circle with a radius not exceeding r. L3 、r L2 The origin area.

[0107] Judgment area O3-r L3 、O5-r L5 The criterion for whether they overlap is:

[0108] 0 <r L3 <D,0<r L5 <D,r L3 +r L5 <D;

[0109] That is, if the distance between the two poles is greater than the sum of the radii of the two poles, then it can be considered that the nonlinear region has two poles.

[0110] In the above implementation process, by constructing a nonlinear boundary area and designing a nonlinear spiral line based on the extreme points in the nonlinear boundary area, complex geometric areas can be effectively covered, the overlaps and gaps between paths can be reduced, the utilization rate of the paths can be improved, and the mobility efficiency of mobile devices can be improved.

[0111] In a possible implementation, step 202 includes: constructing a contour line equation according to the boundary information; obtaining multiple paths according to the contour line equation; and merging the multiple paths into one path.

[0112] Among them, the contour line equation can be expressed as:

[0113] S Q = k*d;

[0114] Where k is the number of path layers generated by the target, and d is the wheelbase of the target device or the path spacing in the target area.

[0115] Here the contour equations are configured to divide the target area into multiple spiral paths.

[0116] In one embodiment, the driving path may be generated based on an Archimedean equidistant spiral.

[0117] Among them, the Archimedean spiral is an equidistant spiral. In some special scenarios, an equidistant and constant speed environment is required (for example, when smart agricultural machinery is operating in the field). The Archimedean spiral can effectively cover complex geometric areas, reduce overlaps and gaps between paths, and improve filling efficiency. In addition, there is only one sharp turn in the center, and the rest of the parts are relatively smooth, which makes the generated path smoother in actual applications, which is conducive to the continuity and quality of the operation process.

[0118] The characteristic of the Archimedean spiral here is that its radius is proportional to the angle. The polar coordinate equation of the Archimedean spiral can be expressed as:

[0119] r f =a+bθ f ;

[0120] Among them, r f is the distance from the origin to point f on the curve, a and b are both constants, θ f The angle from the starting axis to point f. a is used to control the shape of the helix, and b is used to control the tightness of the helix.

[0121] It should be understood that the Archimedean spiral exhibits many superior properties in the operation path planning of the target equipment. The advantages of the Archimedean spiral can include:

[0122] (1) Equidistant and uniform coverage: The radius of the Archimedean spiral increases linearly with the angle, making it have uniform spacing in two-dimensional space. This feature is very suitable for path planning in special environment operations (such as farmland operations), which can ensure that the target equipment maintains equidistant and uniform movement during operation, improve coverage efficiency, and reduce resource waste.

[0123] (2) Reduce path overlap and gaps: The Archimedean spiral can effectively cover complex geometric areas and reduce the overlap and gaps between paths. This not only optimizes the operation path, but also saves time and fuel, and improves the overall efficiency of the operation.

[0124] (3) Smooth path: During the path generation process, the Archimedean spiral has only one sharp turn in the center, and the rest is relatively smooth. This path planning makes the target equipment move more smoothly during operation, which is conducive to improving the continuity and quality of the operation process and reducing mechanical wear and operation errors.

[0125] In actual agricultural applications, the Archimedean spiral path planning method can be widely used in operations such as sowing, fertilizing, and spraying. Intelligent agricultural machinery can move accurately along the preset Archimedean spiral trajectory to ensure full coverage of farmland. By optimizing the driving path, not only can the quality and efficiency of operations be improved, but also the efficiency of small and fragmented fields can be improved.

[0126] In one embodiment, in order to enable the target device to continuously travel in the target area, after the target area is divided into multiple paths, the multiple divided paths need to be connected and merged to obtain a completed driving path, wherein the merged path is the driving path.

[0127] As mentioned above, the target area may include one or more extreme points, and the extreme points of the target area may be selected according to actual conditions.

[0128] It can be understood that in order to combine the driving path with the actual scene, after optimizing the driving path, it is also necessary to project the waypoints on the path to the actual accurate positions of the target area.

[0129] For example, if the target area is a farmland and the target equipment is an intelligent agricultural machine, before selecting the farmland operation path, the original two longitude and latitude points of the actual map boundary can be obtained, such as Figure 7 As shown in ( Figure 7 (A and B are shown in the figure), after path planning, the projection coefficient k is calculated:

[0130]

[0131] Among them, lat A is the dimensional coordinate point of point A, lon Ais the precision coordinate point of point A, X A is the horizontal point position of point A, Y A It is the longitudinal point position of point A path.

[0132] After obtaining the projection coefficient, the complete actual path point information can be obtained through the projection function:

[0133] M i =N i +k·P i ;

[0134] Among them, N i is the latitude and longitude coordinates of the path starting point, P i are the control point coordinates.

[0135] In the above implementation process, by dividing the target area into multiple paths and merging the multiple paths into one path, complex geometric areas can be effectively covered and the overlaps and gaps between paths can be reduced. This can not only optimize the driving path, but also save the action time of the target equipment and the fuel required for the operation, thereby improving the overall efficiency of the operation.

[0136] In one possible implementation, Figure 8 As shown, a nonlinear spiral path design is performed on a nonlinear boundary region according to an extreme point region, including: taking the extreme point as the center, constructing multiple nonlinear equidistant paths with a first set spacing inside the nonlinear boundary until the spacing between adjacent paths is less than a second set spacing; selecting a position point on any path as a first position point, and determining a second position point adjacent to the first position point on the same path according to the shape parameters of the target device; wherein the first position point is a starting point; for each path, determining a third position point on a subsequent path adjacent to the previous path that is closest to the second position point on the previous path, and determining a second position point adjacent to the third position point on the same path according to the shape parameters of the target device; until a corresponding position point is found in each of the multiple paths; disconnecting the line between two adjacent position points on each path, and connecting two position points closest to each other on two adjacent paths to obtain a path.

[0137] The first set spacing here can be determined according to the number of paths inside the nonlinear boundary area, and can also be set in advance according to actual needs. The first device spacing can be set according to actual conditions.

[0138] The second set spacing mentioned above may be a multiple of the first device spacing, for example, 2 times.

[0139] In one embodiment, after constructing multiple nonlinear equidistant paths with a first set spacing inside the nonlinear boundary, a nonlinear spiral path is obtained, and the maximum curvature area in the nonlinear spiral path can be further found, and the first position point, the second position point and the third position point are determined in the maximum curvature area, and the adjacent paths are connected through the first position point, the second position point and the third position point.

[0140] As shown above, the area of ​​maximum curvature can be determined by the following formula:

[0141]

[0142] Among them, the area corresponding to the minimum value of k is the area of ​​maximum curvature.

[0143] The first position point here is the starting point.

[0144] It can be understood that in order to reduce invalid driving paths of the target device, the first position point can be selected as the position point closest to the target device among the multiple paths.

[0145] The shape parameters here refer to the shape parameters of the target device, for example, the length of the target device, the width of the target device, the height of the target device, etc. The shape parameters can be selected according to the situation.

[0146] It should be understood that in order to ensure that the target device reaches each area in each path as much as possible during the driving process, when determining the distance between the first position point and the second position point, it can be determined according to the width of the target device along the direction perpendicular to the moving direction of the target device. That is, the distance between the first position point and the second position point is greater than or equal to the width of the target device along the direction perpendicular to the moving direction of the target device.

[0147] After determining the first position point and the second position point on the previous path, it is necessary to continue to determine two position points on the next path. When determining the third position point on the next path, it can be determined based on the second position point on the previous path. By setting the third position point as the position point on the next path that is closest to the second position point, the distance that the target device moves from the next path to the next path can be reduced, thereby reducing the ineffective movement of the target device. Similarly, after determining the third position point on the next path, the second position point on the next path can be further determined based on the width of the target device along the direction perpendicular to the movement of the target device. Iterate in this manner until the corresponding second position point and third position point are found in each of the multiple paths.

[0148] After determining the second position point and the third position point in each path, the multiple paths can be merged into one path by disconnecting the line between two adjacent position points on each path and connecting the two position points closest to each other on two adjacent paths.

[0149] For example, as shown in Figure 8, first select a point P1 on the boundary as the starting point of the connected curve (i.e., the first position point), then find point P2 in the same layer path according to the shape parameters, and find point P3 based on the wheelbase value d of point P2. Then, by removing the curve between P1 and P2 and connecting points P2 and P3, a layer of contour from points P1 to P3 can be generated. And so on, iterate continuously, find points P4, P5, P6 in turn, and finally find the end point P of the spiral line. f .

[0150] Optionally, an exit line can be further introduced, with the 2n layers below the positive direction of the Q layer gradient as the entry layer and the 2n-1 layers below the positive direction of the Q layer gradient as the exit layer. The above iterative process is performed to finally generate Figure 4 The single extreme point equidistant Archimedean spiral shown in (d).

[0151] The spacing of the outlet lines here can be set to half of the first set spacing.

[0152] In the above implementation process, for the single extreme point area, multiple paths can be merged into one path by disconnecting the line between two adjacent position points on each path and connecting the two closest position points on two adjacent paths. The entire implementation method is simple and easy to implement. Moreover, when connecting adjacent paths, the closest position points are selected for connection, which can reduce the overall path length of the driving path, reduce the driving distance of the target equipment, and improve work efficiency.

[0153] In a possible implementation, a plurality of nonlinear equidistant paths with a first set spacing are constructed inside a nonlinear boundary with an extreme point as the center until the spacing between adjacent paths is less than a second set spacing, including: constructing a plurality of nonlinear equidistant paths with a first set spacing inside each nonlinear boundary with each extreme point as the center, until the spacing between adjacent paths inside each nonlinear boundary is less than the second set spacing; determining whether the paths corresponding to the adjacent extreme points are connectable; if it is determined that the paths corresponding to the adjacent extreme points are connectable, connecting the adjacent paths by performing a broken edge reconnection operation on the boundary paths of the paths corresponding to the adjacent extreme points; and forming a A position point is selected as a first position point on any path in the formed overall path, and a second position point adjacent to the first position point on the same path is determined according to the shape parameters of the target device; for each path, a third position point on a subsequent path adjacent to the previous path that is closest to the second position point on the previous path is determined, and a second position point adjacent to the third position point on the same path is determined according to the shape parameters of the target device; until a corresponding position point is found in each of the multiple paths; the connection between two adjacent position points on each path is disconnected, and the two position points closest to each other on two adjacent paths are connected to obtain a path.

[0154] It can be understood that when the nonlinear boundary includes multiple extreme value points, multiple nonlinear equidistant paths with a first set spacing can be constructed for each extreme value point to obtain multiple nonlinear spiral paths. For adjacent nonlinear spiral paths, it can be determined whether the adjacent nonlinear spiral paths can be connected. If the adjacent nonlinear spiral paths can be connected, the adjacent nonlinear spiral paths are merged.

[0155] Optionally, before determining whether the paths corresponding to adjacent extreme value points are connectable, the method further includes: marking each path. i,j Represents each path, i is the distance from the path line to the boundary of the target area, j is the path with the distance i to the boundary, and all paths are saved in the set M.

[0156] The direct connection edge between two adjacent paths here can be expressed as:

[0157] O i,j,j’ = {p∈Q i,j |d(p,Q i+1,j’ ) <d(p,Q i+1,k ),k≠j'};

[0158] Among them, O i,j,j’ is a connected edge, d(p,Q i+1,j, ) represents the path from point p to Q i+1,j, The closest distance value of the point on, d(p,Q i+1,k) represents the path from point p to Q i+1,k The closest distance value of the points on .

[0159] The judgment of whether the paths corresponding to the above-mentioned adjacent extreme value points are connectable can be achieved in the following way:

[0160] If O i,j,j’ If it is not empty, it means that the two adjacent edge paths can be connected, then the outer boundary is reconnected once. i+1,j, and Q i+1,k Add a boundary between the corresponding nodes, and the weight of the edge is defined as the length value of the connected edge.

[0161] If O i,j,j’ If it is empty, it means that the two adjacent edge paths cannot be connected, then the multiple paths determined by the adjacent extreme points that cannot be connected are merged into one path.

[0162] In one embodiment, a position point is selected on any path as a first position point, and a second position point adjacent to the first position point on the same path is determined based on the shape parameters of the target device, including: selecting a position point on any path in the overall path formed after connecting adjacent paths as the first position point, and determining a second position point adjacent to the first position point on the same path based on the shape parameters of the target device.

[0163] It can be understood that for a region with multiple extreme points, before merging multiple paths into one path, if the paths corresponding to adjacent extreme points can be connected, the paths corresponding to adjacent extreme points are first connected to obtain an overall path containing multiple extreme points (such as Fig. 9 As shown, Fig. 9 (a) shows the combined driving path. Fig. 9 (b) shows the combined driving path with the return path added). Then, the area where the overall path is located can be regarded as a single extreme point area, and the paths in the overall path can be merged into one path according to the merging method of the single extreme point area.

[0164] In the above implementation process, for areas with multiple extreme points, by judging whether the paths corresponding to adjacent extreme points can be connected, if the adjacent extreme points can be connected, the boundary paths corresponding to the adjacent extreme points are opened up to form an overall path, and then the various paths in the overall path are merged into one path, so that the driving path can cope with complex terrain environments, thereby increasing the use scenarios of the path planning method.

[0165] In a possible implementation, step 201 includes: preprocessing a captured target image of a target area; initializing a level set function to calculate an image gradient of the target image; determining a boundary of the target area in the target image based on the image gradient; updating the level set function by regularizing the level set evolution equation; and outputting boundary information of the target image when the level set function approaches the boundary of the target area.

[0166] Among them, regularized level set evolution is a method for image segmentation that combines the level set method and regularization technology. The level set method is a numerical technique for tracking the evolution of shape boundaries over time. This method represents the boundary through an implicit function and takes the boundary as the zero level set of the function. The core idea is to evolve the level set function by solving partial differential equations so that it gradually approaches the target boundary. Regularization technology stabilizes and optimizes problem solving by introducing prior information or constraints. In image processing and computer vision, regularization can help deal with noise and incomplete data, prevent overfitting, and improve the generalization ability of the model.

[0167] Regularized level set evolution combines the advantages of the above two methods and introduces a regularization term in the level set evolution process to control and adjust the smoothness and shape of the boundary. This method represents the target boundary by evolving an implicit function and uses the regularization term to ensure the smoothness and stability of the boundary, thereby effectively segmenting the target object in the image.

[0168] The regularized level set evolution technology is widely used in medical image segmentation, target tracking, object recognition and other fields. This technology can be applied to process complex shapes and topological changes, provide smooth and continuous segmentation boundaries, process targets with complex and diverse shapes, and images with more noise or blurred boundaries.

[0169] In the agricultural field, the extraction of farmland boundaries is a major difficulty in unmanned agriculture. Farmland usually has non-standardized and complex backgrounds, including different types of plants, weeds, etc., which increase the complexity of the image. In addition, there is a lot of noise and changing obstacles in the farmland environment, such as farm tools, animals, shadows, etc., as well as complex and changing terrain with potholes, which makes boundary extraction more difficult. By using regularized level set evolution technology to extract boundary information, not only can the accuracy of boundary extraction be improved, but also the efficiency of unmanned agricultural operations can be significantly improved.

[0170] The preprocessing here may include Gaussian filtering to remove noise from the target image. The formula for the Gaussian filtering may be:

[0171]

[0172] Among them, x is the distance variable of the Gaussian function in the horizontal direction, y is the distance variable of the Gaussian function in the vertical direction, and σ is the standard deviation of the Gaussian function, which is used to control the width of the Gaussian distribution. The larger σ is, the wider the Gaussian function is, and the more obvious the blurring effect is.

[0173] The above image gradient can be calculated by the following formula:

[0174]

[0175] Among them, I X Indicates the horizontal gradient value, I y Represents the vertical gradient value, and img is the set of pixels in the target image.

[0176] It should be understood that after the image gradient of the target image is calculated, the boundary of the target area can be further determined based on the image gradient.

[0177] In one embodiment, the boundary of the target area can be constructed by constructing an edge indication function to highlight the edge of the target image. The edge indication function can be expressed as:

[0178]

[0179] Among them, f is the intensity of the image gradient, and g means highlighting the edge by suppressing areas with higher gradient intensity.

[0180] The level set evolution equation here can be expressed as:

[0181]

[0182] Among them, δ(φ) is the Dirac function, is the curvature term, and F(f,φ) is the external force term. The Dirac function is used to ensure that the evolution is only performed on the zero level plane of the level set, the curvature term is used to control the smoothness of the level set, and the external force term is used to drive the evolution of the level set.

[0183] It should be understood that the regularized level set evolution equation introduces a regularized equation on the basis of the level set evolution equation, so that it can not only capture important edges in the target image, but also maintain the smoothness and stability of the level set function, thereby improving the effect of image segmentation and edge detection.

[0184] The above regularized level set evolution equation can be expressed as:

[0185]

[0186] Among them, μ is the parameter controlling the regularization term, which is used to smooth the level set function φ; λ is the parameter controlling the internal energy term, which is usually related to the image features; ν is the parameter controlling the external energy term, which is used to drive the level set evolution.

[0187] It can be understood that in the process of obtaining the boundary information of the target image, the regularized level set evolution equation can be iteratively solved by continuously updating the level set function, so that the boundary information of the target image is output under the regularized level set evolution equation.

[0188] In the above implementation process, by adopting the regularized level set evolution equation to determine the boundary information of the target area, the smoothness and shape of the boundary can be controlled and adjusted, thereby improving the accuracy of boundary information extraction and the smoothness and stability of the boundary.

[0189] Based on the same application concept, a path planning device corresponding to the path planning method is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to that in the aforementioned path planning method embodiment, the implementation of the device in this embodiment can refer to the description in the embodiment of the above method, and the repeated parts will not be repeated.

[0190] See also Fig.10 , is a functional module diagram of a path planning device provided in an embodiment of the present application. Each module in the path planning device in this embodiment is used to execute each step in the above method embodiment. The path planning device includes an acquisition module 301, a determination module 302, and an optimization module 303;

[0191] in,

[0192] The acquisition module 301 is used to acquire boundary information in the target area.

[0193] The determination module 302 is used to determine the driving path of the target device according to the boundary information.

[0194] The optimization module 303 is used to optimize the set position points in the driving path through a local path planning algorithm; wherein the target device is configured to travel in the target area according to the optimized driving path.

[0195] In a possible implementation, the optimization module 303 is further used to: calculate the curvature of each point in the driving path; traverse all position points in the driving path to determine a point set that does not satisfy the curvature constraint; and optimize the path adjacent to the point set using the B-spline curve optimization algorithm.

[0196] In one possible implementation, the optimization module 303 is specifically used to: establish a non-uniform rational B-spline curve; construct an objective function based on the non-uniform rational B-spline curve; wherein the objective function is configured to define a distance between a minimized path and an actual position point; and establish an optimization model based on the objective function and the curvature constraint; wherein the optimization model is configured to optimize the path adjacent to the point set.

[0197] In a possible implementation, the path planning device also includes: a design module for constructing a nonlinear boundary region based on the boundary information; smoothing the boundary of the nonlinear boundary region; determining an extreme point region in the nonlinear boundary region; and designing a nonlinear spiral path for the nonlinear boundary region based on the extreme point region.

[0198] In a possible implementation, the determination module 302 is further used to: construct a contour line equation based on the boundary information; obtain multiple paths based on the contour line equation; merge the multiple paths into one path; wherein the merged path is the driving path.

[0199] In a possible implementation, the design module is specifically used to: construct multiple nonlinear equidistant paths with a first set spacing inside the nonlinear boundary with the extreme point as the center, until the spacing between adjacent paths is less than a second set spacing; select a position point on any path as the first position point, and determine a second position point adjacent to the first position point on the same path based on the shape parameters of the target device; wherein the first position point is the starting point; for each path, determine a third position point on a subsequent path adjacent to the previous path that is closest to the second position point on the previous path, and determine a second position point adjacent to the third position point on the same path based on the shape parameters of the target device; until a corresponding position point is found in each of the multiple paths; disconnect the line between two adjacent position points on each path, and connect the two position points closest to each other on two adjacent paths to obtain a path.

[0200] In a possible implementation manner, the design module is specifically used to: construct a plurality of nonlinear equidistant paths with a first set spacing inside each of the nonlinear boundaries with each of the extreme value points as the center, until the spacing between adjacent paths inside each of the nonlinear boundaries is less than a second set spacing; determine whether the paths corresponding to the adjacent extreme value points are connectable; if it is determined that the paths corresponding to the adjacent extreme value points are connectable, connect the adjacent paths by performing a broken edge reconnection operation on the boundary paths of the paths corresponding to the adjacent extreme value points; select a position point on any path in the overall path formed after connecting the adjacent paths as the first position point, and according to the target According to the shape parameters of the target device, a second position point adjacent to the first position point on the same path is determined; wherein the first position point is the starting point; for each path, a third position point on a subsequent path adjacent to the previous path is determined which is closest to the second position point on the previous path, and according to the shape parameters of the target device, a second position point adjacent to the third position point on the same path is determined; until a corresponding position point is found in each of the multiple paths; disconnect the line between two adjacent position points on each path, and connect the two position points closest to each other on two adjacent paths to obtain a path.

[0201] In a possible implementation, the determination module 302 is specifically used to: select a position point on any path in the overall path formed after connecting adjacent paths as the first position point, and determine a second position point adjacent to the first position point on the same path based on the shape parameters of the target device; wherein the first position point is the starting point.

[0202] In a possible implementation, the acquisition module 301 is also used to: preprocess the acquired target image of the target area; initialize the level set function to calculate the image gradient of the target image; determine the boundary of the target area in the target image based on the image gradient; update the level set function by regularizing the level set evolution equation; and output the boundary information of the target image when the level set function approaches the boundary of the target area.

[0203] In addition, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the path planning method described in the above method embodiment are executed.

[0204] The computer program product of the path planning method provided in the embodiment of the present application includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the steps of the path planning method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0205] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0206] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0207] If the function is implemented in the form of a software function module and sold or used as an independent product, it 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 the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) 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, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk. It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variation thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or apparatus. In the absence of more restrictions, the elements defined by the sentence "includes..." do not exclude the presence of other identical elements in the process, method, article or apparatus that includes the elements.

[0208] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application. It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0209] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A path planning method, characterized in that: include: Obtain boundary information in the target area; determining a driving path of the target device according to the boundary information; Optimizing the set position points in the driving path by using a local path planning algorithm; Wherein, the target device is configured to travel in the target area according to the optimized driving path.

2. The method according to claim 1, characterized in that The local path planning algorithm is a B-spline curve optimization algorithm, and the optimization of the set position points in the driving path by the local path planning algorithm includes: Calculating the curvature of each point in the driving path; Traversing all position points in the driving path to determine a point set that does not satisfy the curvature constraint condition; The paths adjacent to the point set are optimized using the B-spline curve optimization algorithm.

3. The method according to claim 2, characterized in that The optimizing process of the path adjacent to the point set by using the B-spline curve optimization algorithm includes: Establish non-uniform rational B-spline curve; Constructing an objective function according to the non-uniform rational B-spline curve; wherein the objective function is configured to define a distance between a minimized path and an actual position point; Based on the objective function and the curvature constraint condition, establishing an optimization model; The optimization model is configured to optimize the paths adjacent to the point set.

4. The method according to claim 1, characterized in that: in, The boundary information includes a boundary path; Before determining the driving path of the target device according to the boundary information, the method further includes: constructing a nonlinear boundary region according to the boundary information; Performing boundary smoothing on the boundary of the nonlinear boundary region; Determining an extreme point region in the nonlinear boundary region; A nonlinear spiral path is designed for the nonlinear boundary region according to the extreme point region.

5. The method according to claim 4, characterized in that in, The extreme point region in the nonlinear boundary region is a single extreme point region; The performing a nonlinear spiral path design on the nonlinear boundary region according to the extreme point region comprises: Taking the extreme point as the center, constructing a plurality of nonlinear equidistant paths with a first set spacing inside the nonlinear boundary until the spacing between adjacent paths is less than a second set spacing; Select a position point on any path as a first position point, and determine a second position point adjacent to the first position point on the same path according to the shape parameters of the target device; wherein the first position point is a starting point; For each path, determine a third position point on a subsequent path adjacent to the previous path that is closest to the second position point on the previous path, and determine a second position point adjacent to the third position point on the same path according to the shape parameters of the target device; until a corresponding position point is found in each of the multiple paths; Disconnect the line between two adjacent points on each path, and connect the two closest points on two adjacent paths to obtain a path.

6. The method according to claim 4, characterized in that in, The extreme point region in the nonlinear boundary region is a multi-extreme point region, and the method of constructing a plurality of nonlinear equidistant paths with a first set spacing inside the nonlinear boundary with the extreme point as the center until the spacing between adjacent paths is less than a second set spacing includes: Taking each of the extreme points as the center, constructing a plurality of nonlinear equidistant paths with a first set spacing inside each of the nonlinear boundaries, until the spacing between adjacent paths inside each of the nonlinear boundaries is less than a second set spacing; Determine whether the paths corresponding to adjacent extreme points are connectable; When it is determined that the paths corresponding to the adjacent extreme value points are connectable, the adjacent paths are connected by performing a broken edge reconnection operation on the boundary paths of the paths corresponding to the adjacent extreme value points; Selecting a position point on any path of the overall path formed by connecting adjacent paths as a first position point, and determining a second position point adjacent to the first position point on the same path according to the shape parameters of the target device; wherein the first position point is a starting point; For each path, determine a third position point on a subsequent path adjacent to the previous path that is closest to the second position point on the previous path, and determine a second position point adjacent to the third position point on the same path according to the shape parameters of the target device; until a corresponding position point is found in each of the multiple paths; Disconnect the line between two adjacent points on each path, and connect the two closest points on two adjacent paths to obtain a path.

7. The method according to claim 1, characterized in that The step of obtaining boundary information in the target area includes: Preprocessing the acquired target image of the target area; Initialize the level set function and calculate the image gradient of the target image; Determining a boundary of the target area in the target image according to the image gradient; By regularizing the level set evolution equation, updating the level set function; When the level set function approaches a boundary of the target region, the boundary information of the target image is output.

8. A path planning device, characterized in that: include: An acquisition module, used to acquire boundary information in a target area; A determination module, used to determine a driving path of a target device according to the boundary information; An optimization module, used for optimizing the set position points in the driving path through a local path planning algorithm; Wherein, the target device is configured to travel in the target area according to the optimized driving path.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform the steps of any method described in claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are executed.

Images