A Segmented Planning Method for Obstacle Avoidance Path of Unmanned Tractors

Abstract

The present invention provides a method for segmented planning of obstacle avoidance paths for unmanned tractors, belonging to the technical field of obstacle avoidance path planning for tractors. The present invention fully considers the situation where the boundary of the obstacle is not parallel (perpendicular) to the operation row, calculates the farthest corner point of the obstacle from the operation row, divides the obstacle avoidance path into two segments for processing. Instead of being restricted to using the obstacle avoidance area circle as the path, path sampling is carried out in the direction of the obstacle on the basis of this circle, and a shorter path is flexibly selected from the generated path set; the sampling of the exit of the second segment path can not only shorten the path, but also enable the tractor to return to the operation path earlier, effectively increasing the operation area; in addition, the path fitted by quintic spline avoids the problem of discontinuous curvature and is easier to control and track.

Description

Technical Field

[0001] The present invention relates to the technical field of obstacle avoidance path planning for tractors, and particularly relates to a segmented planning method for obstacle avoidance paths of driverless tractors. Background Art

[0002] The statements in this part merely provide background art related to the present invention and do not necessarily constitute prior art.

[0003] The obstacle avoidance path planning of a driverless tractor refers to using a suitable algorithm to calculate and generate a path / trajectory from a starting point to an ending point, and adjusting part of the path / trajectory according to the obstacle information received on the path to avoid collisions with obstacles; currently, most of the obstacle avoidance path planning of driverless tractors is based on the circumscribed circle method of obstacles, which has the advantages of simplicity, speed, and short obstacle avoidance paths.

[0004] The obstacle avoidance path planning based on the circumscribed circle method of obstacles includes: based on the circumscribed circle of the obstacle, determining the information of the regional circle on the obstacle avoidance path through the minimum turning radius of the agricultural machine, the circumscribed circle of the obstacle, and the body width; calculating the obstacle avoidance points on the operation path and the tangent points on the circle according to the regional circle and the minimum turning radius, obtaining the coordinates of the key path points, and driving along the arc on the obstacle avoidance regional circle; the specific implementation principle is as Figure 1 shown. The shaded part in the figure is the obstacle, the circle O0 with a radius of R0 is the obstacle avoidance regional circle, and the small circle in the center is the obstacle regional circle. Determine whether there will be a collision between the obstacle and the straight operation path AE. If there is no collision point, continue to drive straight; otherwise, perform obstacle avoidance path planning: calculate the circle O1 that is tangent to both the operation path AF and the obstacle avoidance regional circle O0 at the same time, and the radius of this circle is the minimum turning radius of the agricultural machine. Similarly, O2, O3, and O4 can be calculated; determine the starting points B1, B2 of the obstacle avoidance path, the ending points D1, D2 of the obstacle avoidance path, and the tangent points H, I, J, K of the minimum turning radius and the regional circle; according to the distances from C1 and C2 to the already operated area, determine the obstacle avoidance route as A - B1 - H - C1 - I - D1 - E or A - B2 - J - C2 - K - D2 - E.

[0005] The inventor found that the above-mentioned obstacle avoidance strategy has the following problems: the generated path has discontinuous path curvature and is prone to difficult tracking; the drivable space within the obstacle avoidance regional circle caused by not considering the shape of the obstacle is ignored, resulting in the omission of the optimal solution for path planning. Summary of the Invention

[0006] In order to solve the deficiencies of the prior art, the present invention provides a segmented planning method for obstacle avoidance paths of driverless tractors, which further shortens the obstacle avoidance path on the premise of ensuring a relatively large operation area.

[0007] In order to achieve the above purpose, the present invention adopts the following technical solutions:

[0008] The first aspect of the present invention provides a method for segmental planning of an obstacle avoidance path for an unmanned tractor.

[0009] A method for segmental planning of an obstacle avoidance path for an unmanned tractor includes the following processes:

[0010] Taking the vertical direction of the operation path from the operation starting point to the operation ending point as the transverse direction, obtaining the circumscribed rectangle of the obstacle, the circumscribed circle of the obstacle, the avoidance area circle, and the first entry point and the first exit point located on the first side of the operation path, wherein the four corner points of the circumscribed rectangle of the obstacle are all located on the circumscribed circle of the obstacle;

[0011] When the radius of the avoidance area circle is greater than the minimum turning radius of the tractor, taking the corner point with the maximum transverse distance from the operation path on the first side of the operation path as the first segmentation point, dividing the area between the first entry point and the first exit point into two segments according to the first segmentation point, and separately optimizing the two segments to obtain a first alternative path and a second alternative path, and connecting the first alternative path and the second alternative path as the optimal path on the first side of the operation path.

[0012] As an optional implementation manner of the first aspect of the present invention, taking the position after extending the operation width by half along the transverse direction from the first segmentation point as the sampling start point, taking the point on the avoidance area circle extended along the transverse direction from the sampling start point as the sampling end point, taking the range between the sampling start point and the sampling end point as the sampling range, generating multiple sampling points within the sampling range, and taking each sampling point as the end point and the first entry point as the start point to select the first alternative path.

[0013] As a further limitation of the first aspect of the present invention, taking each sampling point as the end point and the first entry point as the start point, generating paths corresponding to the number of sampling points by using a quintic spline curve, deleting the paths with collision points on the first side of the operation path, and taking the path with the shortest length among the remaining paths as the first alternative path.

[0014] As an optional implementation manner of the first aspect of the present invention, on the connection line direction with the perpendicular point of the first segmentation point and the operation path as the start point and the first exit point as the end point, finding the first point on the operation path with a perpendicular distance greater than half of the operation width from the obstacle boundary, taking this point as the sampling start point and the first exit point as the sampling end point, discretizing the line segment between the sampling start point and the sampling end point to obtain multiple discrete points, and taking the end point of the first alternative path as the start point and each discrete point as the end point to select the second alternative path.

[0015] As a further limitation of the first aspect of the present invention, taking the end point of the first alternative path as the start point and each discrete point as the end point, generating paths corresponding to the number of discrete points by using a quintic spline curve, deleting the paths with collision points on the first side of the operation path, and taking the path with the shortest length among the remaining paths as the second alternative path.

[0016] As a further limitation of the first aspect of the present invention, the path with a collision point on the first side of the deletion operation path includes:

[0017] Calculate the curvature of each path, and delete the path with a curvature greater than 1 / r, where r is the minimum turning radius of the tractor.

[0018] As an optional implementation manner of the first aspect of the present invention, obtain the circumscribed rectangle of the obstacle, the circumscribed circle of the obstacle, and the second entry point and the second exit point located on the second side of the operation path. Take the corner point with the maximum lateral distance from the operation path on the second side of the operation path as the second segmentation point, divide the area between the second entry point and the second exit point into two segments according to the second segmentation point, optimize the two segments respectively to obtain the third alternative path and the fourth alternative path, and connect the third alternative path and the fourth alternative path as the optimal path on the second side of the operation path;

[0019] Take the shorter one of the optimal path on the first side of the operation path and the optimal path on the second side of the operation path as the optimal obstacle avoidance path.

[0020] As a further limitation of the first aspect of the present invention, take the position after extending the operation width by half laterally from the second segmentation point as the sampling start point, take the point on the circumscribed circle of the obstacle avoidance area extended laterally from the sampling start point as the sampling end point, take the range between the sampling start point and the sampling end point as the sampling range, generate multiple sampling points within the sampling range, and take each sampling point as the end point and the second entry point as the start point to select the third alternative path.

[0021] As a further limitation of the first aspect of the present invention, take each sampling point as the end point and the second entry point as the start point, use the quintic spline curve to generate the paths corresponding to the number of sampling points, delete the paths with collision points on the second side of the operation path, and take the shortest one of the remaining paths as the third alternative path.

[0022] As a further limitation of the first aspect of the present invention, in the direction of the line connecting the perpendicular point of the second segmentation point and the operation path as the start point and the second exit point as the end point, find the first point on the operation path whose perpendicular distance from the obstacle boundary is greater than half of the operation width, take this point as the sampling start point and the second exit point as the sampling end point, discretize the line segment between the sampling start point and the sampling end point to obtain multiple discrete points, take the end point of the third alternative path as the start point and each discrete point as the end point to select the fourth alternative path.

[0023] As a further limitation of the first aspect of the present invention, take the end point of the third alternative path as the start point and each discrete point as the end point, use the quintic spline curve to generate the paths corresponding to the number of discrete points, delete the paths with collision points on the second side of the operation path, and take the shortest one of the remaining paths as the fourth alternative path.

[0024] As a further limitation of the first aspect of the present invention, deleting the path with a collision point on the second side of the operation path includes:

[0025] Calculating the curvature of each path, and deleting the path with a curvature greater than 1 / r, where r is the minimum turning radius of the tractor.

[0026] As an optional implementation manner of the first aspect of the present invention, when the minimum turning radius of the tractor is greater than or equal to the sum of the circumradius of the obstacle and half of the working width, the radius of the obstacle avoidance area circle is the minimum turning radius of the tractor; otherwise, the radius of the obstacle avoidance area circle is the sum of the circumradius of the obstacle and half of the working width.

[0027] As an optional implementation manner of the first aspect of the present invention, when the radius of the obstacle avoidance area circle is less than or equal to the minimum turning radius of the tractor, obtaining the first circle and the second circle tangent to the obstacle avoidance area circle on the first side of the operation path and the third circle and the fourth circle tangent to the obstacle avoidance area circle on the second side of the operation path;

[0028] The tangent point of the first circle and the obstacle avoidance area circle is the first tangent point, the tangent point of the first circle and the operation path is the second tangent point, the tangent point of the second circle and the obstacle avoidance area circle is the third tangent point, and the tangent point of the second circle and the operation path is the fourth tangent point;

[0029] The tangent point of the third circle and the obstacle avoidance area circle is the fifth tangent point, the tangent point of the third circle and the operation path is the sixth tangent point, the tangent point of the fourth circle and the obstacle avoidance area circle is the seventh tangent point, and the tangent point of the fourth circle and the operation path is the eighth tangent point;

[0030] The obstacle avoidance path on the first side of the operation path is the starting point, the first tangent point, the arc segment of the first circle between the first tangent point and the second tangent point, the second tangent point, the arc segment of the obstacle avoidance area circle between the second tangent point and the third tangent point, the third tangent point, the arc segment of the second circle between the third tangent point and the fourth tangent point, the fourth tangent point and the end point;

[0031] The obstacle avoidance path on the second side of the operation path is the starting point, the fifth tangent point, the arc segment of the third circle between the fifth tangent point and the sixth tangent point, the sixth tangent point, the arc segment of the obstacle avoidance area circle between the sixth tangent point and the seventh tangent point, the seventh tangent point, the arc segment of the fourth circle between the seventh tangent point and the eighth tangent point, the eighth tangent point and the end point.

[0032] The second aspect of the present invention provides a segmented planning system for the obstacle avoidance path of an unmanned tractor.

[0033] A segmented planning system for the obstacle avoidance path of an unmanned tractor includes:

[0034] A parameter acquisition module, configured to: take the vertical direction of the operation path direction from the operation start point to the operation end point as the lateral direction, and acquire the circumscribed rectangle of the obstacle, the circumscribed circle of the obstacle, the obstacle avoidance area circle, and the first entry point and the first exit point located on the first side of the operation path, wherein the four corner points of the circumscribed rectangle of the obstacle are all located on the circumscribed circle of the obstacle;

[0035] The first path segment optimization module, configured to: when the radius of the obstacle avoidance area circle is greater than the minimum turning radius of the tractor, take the corner point with the largest lateral distance from the operation path on the first side of the operation path as the first segmentation point, and divide the area between the first entry point and the first exit point into two segments according to the first segmentation point. The two segments are respectively optimized to obtain a first alternative path and a second alternative path, and the first alternative path and the second alternative path are connected as the optimal path on the first side of the operation path.

[0036] As an optional implementation manner of the second aspect of the present invention, a second path segment optimization module, configured to: acquire the circumscribed rectangle of the obstacle, the circumscribed circle of the obstacle, and the second entry point and the second exit point located on the second side of the operation path, take the corner point with the largest lateral distance from the operation path on the second side of the operation path as the second segmentation point, and divide the area between the second entry point and the second exit point into two segments according to the second segmentation point. The two segments are respectively optimized to obtain a third alternative path and a fourth alternative path, and the first alternative path and the second alternative path are connected as the optimal path on the second side of the operation path;

[0037] The comprehensive path optimization module, configured to: take the shorter one of the optimal path on the first side of the operation path and the optimal path on the second side of the operation path as the optimal obstacle avoidance path.

[0038] Compared with the prior art, the beneficial effects of the present invention are:

[0039] 1. The present invention innovatively proposes a method for segmental planning of the obstacle avoidance path of an unmanned tractor, fully studies the static obstacle conditions when the unmanned tractor makes an obstacle avoidance path plan, optimizes the existing technical solutions, and generates a better obstacle avoidance path for the unmanned tractor. On the premise of ensuring a relatively large operation area (referring to the operation width multiplied by the operation length in the operation state of the tractor), the obstacle avoidance path is further shortened.

[0040] 2. The present invention innovatively proposes a method for segmental planning of the obstacle avoidance path of an unmanned tractor, fully considering the situation where the obstacle boundary is not parallel (perpendicular) to the operation row, calculating the farthest corner point of the obstacle from the operation row, dividing the obstacle avoidance path into two segments for processing, not being limited to using the obstacle avoidance area circle as the path, but on the basis of this circle, sampling paths in the direction of the obstacle, and being able to flexibly select a shorter path from the generated path set.

[0041] 3. The present invention innovatively proposes a method for segmented planning of obstacle avoidance paths for unmanned tractors. The sampling of the exit of the second - stage path can not only shorten the path, but also enable the tractor to return to the operation path earlier, effectively increasing the operation area.

[0042] 4. The present invention innovatively proposes a method for segmented planning of obstacle avoidance paths for unmanned tractors. The path fitted by quintic spline avoids the problem of discontinuous curvature and is easier to control and track. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings forming a part of this specification are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0044] Figure 1 It is a schematic diagram of the existing obstacle avoidance path planning method provided in the background art;

[0045] Figure 2 It is a schematic diagram of the method for segmented planning of obstacle avoidance paths for unmanned tractors provided in Embodiment 1 of the present invention;

[0046] Figure 3 It is a schematic diagram of the path set provided in Embodiment 1 of the present invention;

[0047] Figure 4 It is a schematic flowchart of the method for segmented planning of obstacle avoidance paths for unmanned tractors provided in Embodiment 1 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0049] It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0050] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0051] Without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0052] Embodiment 1:

[0053] As described in the background art, for driverless tractors, most of them treat obstacles as circles and then drive along the circumcircle of the obstacles, rarely considering the collision-free drivable area within the regional circle caused by the shape of the obstacles. For example, when the obstacle is a polygon not close to a circle, when the radius of the circumcircle of the obstacle plus half of the body width is greater than the minimum turning radius of the agricultural machinery, there is a path with less obstacle avoidance consumption within the regional circle.

[0054] In view of this, Embodiment 1 of the present invention provides a method for segmentally planning an obstacle avoidance path for an unmanned tractor. When receiving obstacle information, the obstacle is processed into a rectangle, that is, the circumscribed rectangle of the obstacle is obtained, and the circumcircle of the obstacle is calculated and generated (find the two vertices of the obstacle polygon with the farthest distance, take half of the distance to draw a circle, and the obtained circle can enclose the entire polygon), with a radius of R, an operation width of w, and a minimum turning radius of the tractor of r (that is, when the vehicle is driving at a low speed, the steering wheel is turned to the limit, and the radius of the circular trajectory traveled by the outer wheel. When the vehicle turns, the degree of curvature of the passable path is limited by the minimum turning radius). To ensure no collision with the obstacle, the radius R0 of the obstacle avoidance area circle must be greater than or equal to R + w / 2. Considering the limitation of the minimum turning radius during the actual driving of the tractor, R0 is greater than or equal to r. Therefore, the calculation method of R0 is shown in formula (1):

[0055]

[0056] More specifically, it includes the following process:

[0057] S1: When the radius R0 of the obstacle avoidance area circle is greater than the minimum turning radius r of the tractor, according to Figure 1 the existing scheme described above, the obstacle avoidance area circle O0 and the circles O1 (i.e., the first circle), O2 (i.e., the second circle), O3 (i.e., the third circle), and O4 (i.e., the fourth circle) tangent to the obstacle avoidance area circle O0, the obstacle avoidance path entry points B1 (i.e., the first entry point) and B2 (i.e., the second entry point), and the obstacle avoidance path exit points D1 (i.e., the first exit point) and D2 (i.e., the second exit point) are calculated.

[0058] S2: Taking the driving direction as the longitudinal direction (i.e., taking the direction from the starting point to the ending point as the operation direction and the operation direction as the driving direction), the direction perpendicular to the driving direction as the transverse direction, and the counterclockwise direction of the driving direction as the left side of the driving direction (i.e., the first side, which can also be the second side here, and those skilled in the art can make a preference, which will not be elaborated here);

[0059] According to the lateral distance between the corner points of the obstacle and the original operation path, the obstacle avoidance path is divided into two segments for processing. The following steps will be described in detail taking the left side as an example.

[0060] S3: Calculate the position of the segmentation point. Select the corner point with the maximum horizontal distance from the original operation path in the obstacle avoidance direction as the segmentation point. The calculation process is as follows:

[0061] Calculate the vertical distance from the corner points on the left side of the driving direction of the obstacle to the current operation line in sequence, and take the maximum value. For example, Figure 2 in this figure, there is only one corner point P1 in this direction, then calculate the distance d from P1 to AE (where A is the starting point of the tractor and E is the ending point of the tractor).

[0062] S4: Calculate the horizontal range of the sampling points of the first - stage path. To ensure normal operation, the distance between the path and P1 should be greater than or equal to w / 2. Denote the point where the horizontal distance between the obstacle - avoidance path and P1 is w / 2 as the sampling start point H0;

[0063] To ensure that the sampling range is not too long and a feasible obstacle - avoidance path can be generated, select a point on the circle of the obstacle - avoidance area as the sampling end point. Horizontally move H0 to obtain the sampling end point H on the circle of the obstacle - avoidance area. n The distance from H0 to H n is denoted as s.

[0064] S5: Generate sampling points within the sampling range and use a quintic spline curve to generate a path. Select an appropriate discrete distance m. For the points on the discrete line segment H0H n that is, obtain the evenly - distributed points H n with a horizontal distance of m between H0 and H i (i = 0, 1, 2, 3 ··· n);

[0065] The starting point of the left - hand side obstacle - avoidance path is the entrance point B1. Using the relevant state parameters of the starting point and sampling points, through quintic spline curve fitting, obtain the path of (B1, H i )(i = 0, 1, 2, 3 ··· n), and obtain a path set of n paths, as shown on the left side of Figure 3 .

[0066] In this embodiment, the quintic spline curve is:

[0067] y = a1x 5 +a2x 4 +a3x 3 +a4x 2 +a5x + a6 (2)

[0068] In an x - y coordinate system, given the information of the starting point (x0, y0) and the ending point (x1, y1), the values of the six coefficients a1, a2, a3, a4, a5, a6 of the quintic polynomial can be obtained through the constraint of the information conditions, so as to determine a quintic polynomial curve.

[0069] S6: Path selection. In the path set generated in S5, the width of the tractor and the working row is considered, and the paths with collision points are determined in turn. The curvature k of each path is calculated. i (where i represents the i-th path), the tractor's path trajectory is limited by the minimum turning radius r, so deleting k i >1 / r, calculate the length of the remaining paths and select the shortest one as the candidate path B1H.

[0070] S7: Calculate the range of sampling points of the second path segment, generate sampling points and paths, take the foot of the perpendicular between the segmentation point and the working path AE as the starting point, search for a point on the straight line AE with a vertical distance greater than w / 2 from the obstacle boundary in the direction of the obstacle avoidance path exit, take this point (i.e., the first point greater than w / 2) as the sampling starting point Z0, take the obstacle avoidance exit point D1 as the sampling end point, and re-record it as Z n , discrete line segment Z0Z n , that is, we get Z0 to Z n Uniformly distributed points Z with a lateral distance m between them i (i=0,1,2,3...n), take the end point H of the path selected by S6 as the new starting point, sampling point Z i As the end point, a set of paths is generated by quintic spline fitting, such as Figure 3 Shown on the right.

[0071] S8: Path selection. The operation is the same as S6. The selected path is HZ. The path B1H-HZ is connected. At this point, the obstacle avoidance path on the left side of the working direction is obtained.

[0072] S9: Similarly, the obstacle avoidance path on the right can be obtained.

[0073] S10: Compare the left obstacle avoidance path with the right obstacle avoidance path, and select the shorter one as the final obstacle avoidance path. The specific process is as follows: Figure 4 shown.

[0074] It can be understood that in some other implementations, obstacle avoidance can be specified along the left side (i.e., the first side of the working path). In this case, there is no need to calculate the obstacle avoidance path on the right side (i.e., the second side of the working path); or an obstacle avoidance path on the right side (i.e., the second side of the working path) can be specified for obstacle avoidance. In this case, there is no need to calculate the obstacle avoidance path on the left side (i.e., the first side of the working path). Technical personnel in this field can make a choice based on the specific working conditions, which will not be elaborated here.

[0075] It should be noted that when the radius R0 of the obstacle avoidance area is less than or equal to the minimum turning radius r of the tractor, Figure 1 The existing solution performs obstacle avoidance path selection.

[0076] Example 2:

[0077] Example 2 of the present invention provides a segmented planning system for obstacle avoidance paths of an unmanned tractor, including:

[0078] A parameter acquisition module, configured to: take the vertical direction of the operation path from the operation starting point to the operation ending point as the transverse direction, and acquire the circumscribed rectangle of the obstacle, the circumscribed circle of the obstacle, the obstacle avoidance area circle, and the first entry point and the first exit point located on the first side of the operation path, wherein the four corner points of the circumscribed rectangle of the obstacle are all located on the circumscribed circle of the obstacle;

[0079] A first path segmentation and optimization module, configured to: when the radius of the obstacle avoidance area circle is greater than the minimum turning radius of the tractor, take the corner point with the maximum transverse distance from the operation path on the first side of the operation path as the first segmentation point, divide the area between the first entry point and the first exit point into two segments according to the first segmentation point, respectively optimize the two segments to obtain a first alternative path and a second alternative path, and connect the first alternative path and the second alternative path as the optimal path on the first side of the operation path.

[0080] In this embodiment, the system further includes:

[0081] A second path segmentation and optimization module, configured to: acquire the circumscribed rectangle of the obstacle, the circumscribed circle of the obstacle, and the second entry point and the second exit point located on the second side of the operation path, take the corner point with the maximum transverse distance from the operation path on the second side of the operation path as the second segmentation point, divide the area between the second entry point and the second exit point into two segments according to the second segmentation point, respectively optimize the two segments to obtain a third alternative path and a fourth alternative path, and connect the first alternative path and the second alternative path as the optimal path on the second side of the operation path;

[0082] A comprehensive path optimization module, configured to: take the shorter one of the optimal path on the first side of the operation path and the optimal path on the second side of the operation path as the optimal obstacle avoidance path.

[0083] The working method of the system is the same as the segmented planning method for obstacle avoidance paths of the unmanned tractor provided in Example 1, and will not be elaborated here.

[0084] Example 3:

[0085] Example 3 of the present invention provides a computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, it implements the steps in the segmented planning method for obstacle avoidance paths of the unmanned tractor as described in Example 1 of the present invention.

[0086] Example 4:

[0087] Embodiment 4 of the present invention provides an electronic device, including a memory, a processor, and a program stored on the memory and executable on the processor. When the processor executes the program, the steps in the segmented obstacle avoidance path planning method for an unmanned tractor as described in Embodiment 1 of the present invention are implemented.

[0088] Embodiment 5:

[0089] Embodiment 5 of the present invention provides an unmanned tractor that performs path planning using the segmented obstacle avoidance path planning method for an unmanned tractor as described in Embodiment 1 of the present invention; or includes the segmented obstacle avoidance path planning system for an unmanned tractor as described in Embodiment 2 of the present invention; or includes the computer-readable storage medium as described in Embodiment 3 of the present invention; or includes the electronic device as described in Embodiment 4 of the present invention.

[0090] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories and optical memories, etc.) that contain computer-usable program code.

[0091] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0092] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the process Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps for the functions specified in one block or a plurality of blocks.

[0094] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0095] The foregoing are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for segmented planning of obstacle avoidance paths for an unmanned tractor, characterized in that, It includes the following processes: Taking the vertical direction of the operation path from the operation starting point to the operation ending point as the lateral direction, obtaining the circumscribed rectangle of the obstacle, the circumscribed circle of the obstacle, the avoidance area circle, and the first entry point and the first exit point located on the first side of the operation path, wherein the four corner points of the circumscribed rectangle of the obstacle are all located on the circumscribed circle of the obstacle; When the radius of the avoidance area circle is greater than the minimum turning radius of the tractor, taking the corner point with the maximum lateral distance from the operation path on the first side of the operation path as the first segmentation point, dividing the area between the first entry point and the first exit point into two segments according to the first segmentation point, and respectively optimizing the two segments to obtain the first alternative path and the second alternative path, and connecting the first alternative path and the second alternative path as the optimal path on the first side of the operation path; Taking the position after extending the operation width by half along the lateral direction from the first segmentation point as the sampling start point, taking the point on the avoidance area circle extended along the lateral direction from the sampling start point as the sampling end point, taking the range between the sampling start point and the sampling end point as the sampling range, generating multiple sampling points within the sampling range, and taking each sampling point as the end point and the first entry point as the start point to select the first alternative path; Taking each sampling point as the end point and the first entry point as the start point, generating the same number of paths as the sampling points by using the quintic spline curve, deleting the paths with collision points on the first side of the operation path, and taking the path with the shortest length among the remaining paths as the first alternative path.

2. The method for segmental planning of the obstacle avoidance path of an unmanned tractor according to claim 1, wherein On the connection line direction with the perpendicular point of the first segmentation point and the operation path as the starting point and the first exit point as the ending point, searching for the first point on the operation path with a perpendicular distance greater than half of the operation width from the obstacle boundary, taking this point as the sampling starting point and the first exit point as the sampling ending point, and after discretizing the line segment between the sampling starting point and the sampling ending point, obtaining multiple discrete points, taking the ending point of the first alternative path as the starting point and each discrete point as the ending point to select the second alternative path.

3. The method for segmental planning of the obstacle avoidance path of an unmanned tractor according to claim 2, wherein Taking the ending point of the first alternative path as the starting point and each discrete point as the ending point, generating the same number of paths as the discrete points by using the quintic spline curve, deleting the paths with collision points on the first side of the operation path, and taking the path with the shortest length among the remaining paths as the second alternative path.

4. The method for segmental planning of the obstacle avoidance path of an unmanned tractor according to claim 1, wherein Deleting the paths with collision points on the first side of the operation path includes: Calculating the curvature of each path and deleting the paths with a curvature greater than 1 / r, where r is the minimum turning radius of the tractor.

5. The method for segmental planning of the obstacle avoidance path of an unmanned tractor according to any one of claims 1-4, wherein Obtain the circumscribed rectangle of the obstacle, the circumscribed circle of the obstacle, and the second entry point and the second exit point located on the second side of the operation path. Use the corner point with the maximum lateral distance from the operation path on the second side of the operation path as the second segmentation point. Divide the area between the second entry point and the second exit point into two segments according to the second segmentation point, and optimize each segment to obtain the third alternative path and the fourth alternative path. Connect the third alternative path and the fourth alternative path as the optimal path on the second side of the operation path; Take the shorter of the optimal path on the first side of the operation path and the optimal path on the second side of the operation path as the optimal obstacle avoidance path.

6. The segmented planning method for the obstacle avoidance path of an unmanned tractor according to claim 5, wherein: Use the position after extending the operation width by half laterally from the second segmentation point as the sampling start point, use the point on the circumscribed circle of the obstacle avoidance area extended laterally from the sampling start point as the sampling end point, use the range between the sampling start point and the sampling end point as the sampling range, generate multiple sampling points within the sampling range, and use each sampling point as the end point and the second entry point as the start point to select the third alternative path.

7. The segmented planning method for the obstacle avoidance path of an unmanned tractor according to claim 6, wherein: Use each sampling point as the end point and the second entry point as the start point, generate the same number of paths as the sampling points using the quintic spline curve, delete the paths with collision points on the second side of the operation path, and take the path with the shortest length among the remaining paths as the third alternative path.

8. The segmented planning method for the obstacle avoidance path of an unmanned tractor according to claim 6, wherein: In the direction of the line connecting the perpendicular point of the second segmentation point and the operation path as the start point and the second exit point as the end point, find the first point on the operation path with a perpendicular distance greater than half of the operation width from the obstacle boundary. Use this point as the sampling start point and the second exit point as the sampling end point. After discretizing the line segment between the sampling start point and the sampling end point, obtain multiple discrete points. Use the end point of the third alternative path as the start point and each discrete point as the end point to select the fourth alternative path.

9. The segmented planning method for the obstacle avoidance path of an unmanned tractor according to claim 8, wherein: Use the end point of the third alternative path as the start point and each discrete point as the end point, generate the same number of paths as the discrete points using the quintic spline curve, delete the paths with collision points on the second side of the operation path, and take the path with the shortest length among the remaining paths as the fourth alternative path.

10. An obstacle avoidance path segmented planning system for an unmanned tractor, based on the obstacle avoidance path segmented planning method for an unmanned tractor according to any one of claims 1 to 4, characterized in that, Comprising: A parameter acquisition module configured to: take the vertical direction of the operation path from the operation start point to the operation end point as the lateral direction, and obtain the circumscribed rectangle of the obstacle, the circumscribed circle of the obstacle, the circumscribed circle of the obstacle avoidance area, and the first entry point and the first exit point located on the first side of the operation path, wherein the four corner points of the circumscribed rectangle of the obstacle are all located on the circumscribed circle of the obstacle; The first path segmentation optimization module is configured to: when the radius of the obstacle avoidance area circle is greater than the minimum turning radius of the tractor, use the corner point with the largest lateral distance from the first side of the operation path to the operation path as the first segmentation point, divide the area between the first entry point and the first exit point into two segments according to the first segmentation point, optimize the two segments separately to obtain a first alternative path and a second alternative path, and connect the first alternative path and the second alternative path as the optimal path on the first side of the operation path.

11. The obstacle avoidance path segmented planning system for an unmanned tractor according to claim 10, wherein, It further includes: The second path segmentation optimization module is configured to: obtain the circumscribed rectangle of the obstacle, the circumscribed circle of the obstacle, and the second entry point and the second exit point located on the second side of the operation path, use the corner point with the largest lateral distance from the second side of the operation path to the operation path as the second segmentation point, divide the area between the second entry point and the second exit point into two segments according to the second segmentation point, optimize the two segments separately to obtain a third alternative path and a fourth alternative path, and connect the first alternative path and the second alternative path as the optimal path on the second side of the operation path; the comprehensive path optimization module is configured to: use the shortest path among the optimal path on the first side of the operation path and the optimal path on the second side of the operation path as the optimal obstacle avoidance path.

Images