Path planning method, device, equipment and storage medium

Abstract

The present application relates to the field of path planning technology, and discloses a path planning method, device, equipment and storage medium. The method includes: obtaining the starting position, target position, vehicle geometry parameters and minimum ground clearance parameters of the vehicle, as well as the pavement geometry characteristic parameters and pavement roughness characteristic parameters of the unpaved road; discrete sampling of the unpaved road to obtain multiple pavement sampling points; constructing a road roughness risk potential field model and a road boundary risk potential field model based on the pavement geometry characteristic parameters and pavement roughness characteristic parameters; traversing each pavement sampling point to determine the target path from the starting position to the target position with the lowest comprehensive cost. The embodiments of the present application can improve the safety and comfort of vehicles when driving on unpaved roads.

Description

Technical Field

[0001] The present application relates to the field of path planning technology, and in particular to a path planning method, device, equipment and storage medium. Background Art

[0002] Path planning is a commonly used function of vehicles during driving. The vehicle can plan the best route according to the current location and destination and guide the vehicle along the best route to finally reach the destination.

[0003] The roads that vehicles travel on include paved roads and unpaved roads. Since paved roads are paved with concrete or asphalt, these roads are generally located in densely populated areas, so the road information is complete and accurate, and the update speed is relatively fast, so accurate and reliable data can be obtained at any time. However, unpaved roads are generally located in sparsely populated areas. They are mainly dirt or simply paved with gravel. There are a lot of uneven features on the roads, which affect the safety and comfort of driving. Summary of the invention

[0004] The purpose of this application is to provide a path planning method, device, equipment and storage medium, aiming to improve the safety and comfort of a vehicle when driving on unpaved roads.

[0005] The present application provides a path planning method, including:

[0006] Obtaining the vehicle's starting position, target position, vehicle geometry parameters and minimum ground clearance parameters, as well as pavement geometry characteristic parameters and pavement roughness characteristic parameters of an unpaved road;

[0007] Performing discrete sampling on the unpaved road to obtain a plurality of road surface sampling points;

[0008] Constructing a road roughness risk potential field model and a road boundary risk potential field model according to the road surface geometric characteristic parameters and the road surface roughness characteristic parameters;

[0009] Traversing each of the road sampling points, determining a target path from the starting position to the target position with the lowest comprehensive cost; the comprehensive cost is obtained by fitting a smoothness cost and a safety cost, the smoothness cost characterizes the curvature of the path, the safety cost characterizes the safety of the path, and the safety cost is obtained by performing safety risk assessment on the center of mass and vehicle angle of the vehicle based on the vehicle geometric parameters and the minimum ground clearance parameters by using the road roughness risk potential field model and the road boundary risk potential field model.

[0010] In some embodiments, the discrete sampling of the unpaved road to obtain a plurality of road surface sampling points includes:

[0011] Taking the road surface edge of the unpaved road, the starting position and the target position as boundaries, continuous discrete sampling is performed in the road surface space of the unpaved road to obtain a plurality of road surface sampling points; the road surface sampling points are distributed in a plurality of sampling areas, each of the sampling areas is distributed with a plurality of the road surface sampling points, and each of the sampling areas is arranged along the road length direction of the unpaved road.

[0012] In some embodiments, the road roughness risk potential field model is:

[0013] ,

[0014] Where n=1,2,...,n obs ,k=1,2,...,k max , n obs is the total number of road roughness features, k max is the total number of target sample points, which are road surface sampling points, centroid sampling points or vehicle corner sampling points. is the height of the nth road roughness feature at the kth target sample point, is the height of the kth target sample point after the roughness features of each road surface are superimposed, is the road roughness risk potential field value of the kth target sample point, A n is the feature identification parameter of the nth road roughness feature, , , and are the distribution factors of the nth road roughness feature along the positive direction of the x-axis, the negative direction of the x-axis, the positive direction of the y-axis, and the negative direction of the y-axis with the reference point as the origin, and are the x-axis coordinate and y-axis coordinate of the k-th target sample point, respectively. and are the x-axis coordinate and y-axis coordinate of the reference point of the nth road roughness feature, C n is the reduction coefficient of the nth road roughness feature, the x-axis is parallel to the length direction of the unpaved road, and the y-axis is parallel to the width direction of the unpaved road;

[0015] The road boundary risk potential field model is:

[0016] ,

[0017] Where m=1,2,...,n road , n road is the total number of road boundaries, is the road boundary risk potential field value of the mth road boundary at the kth target sample point, is the road boundary risk potential field value of the kth target sample point, is the peak coefficient of the risk potential field value of the mth road boundary, is the y-axis coordinate of the mth road boundary, is the distribution factor of the risk potential field value of the mth road boundary, is the decrease coefficient of the risk potential field value of the mth road boundary.

[0018] In some embodiments, the pavement sampling points are distributed in a plurality of sampling areas, each of the sampling areas is distributed with a plurality of the pavement sampling points, and each of the sampling areas is arranged along the length direction of the unpaved road, and traversing each of the pavement sampling points to determine a target path from the starting position to the target position with the lowest comprehensive cost includes:

[0019] Based on the polynomial curve fitting principle, a candidate path is generated; the candidate path includes a path from the starting position to any of the road surface sampling points in the first sampling area, a path from any of the road surface sampling points in the previous sampling area to any of the road surface sampling points in the next sampling area, and a path from any of the road surface sampling points in the last sampling area to the target position;

[0020] Performing a smoothness risk assessment on the candidate path to obtain a smoothness cost of the candidate path;

[0021] Using the road roughness risk potential field model and the road boundary risk potential field model, a safety risk assessment is performed on the center of mass and the vehicle angle of the vehicle on the candidate path to obtain the safety cost of the candidate path;

[0022] Performing a weighted summation on the smoothness cost of the candidate path and the safety cost of the candidate path to obtain a comprehensive cost of the candidate path;

[0023] According to the comprehensive cost of the candidate paths, reverse path discovery is performed from the target location to the starting location to obtain the target path.

[0024] In some embodiments, performing smoothness risk assessment on the candidate path to obtain the smoothness cost of the candidate path includes:

[0025] Continuously sampling the candidate path to obtain a plurality of candidate path sampling points;

[0026] The overall curvature of the candidate path is determined according to the curvature of the candidate path at each sampling point of the candidate path to obtain the smoothness cost of the candidate path.

[0027] In some embodiments, the road roughness risk potential field model and the road boundary risk potential field model are used to perform safety risk assessment on the center of mass and vehicle angle of the vehicle on the candidate path to obtain the safety cost of the candidate path, including:

[0028] According to the vehicle geometric parameters, continuously sampling the positions of the center of mass and the vehicle corner of the vehicle on the candidate path to obtain a plurality of center of mass sampling points and a plurality of vehicle corner sampling points;

[0029] Inputting the centroid sampling point and the vehicle corner sampling point into the road roughness risk potential field model and the road boundary risk potential field model respectively, to obtain the road roughness risk potential field value and the road boundary risk potential field value of the centroid and the vehicle corner;

[0030] Calculating the safety cost of the vehicle corner according to the road roughness risk potential field value and the road boundary risk potential field value of the vehicle corner, and calculating the safety cost of the center of mass according to the minimum ground clearance parameter and the road roughness risk potential field value and the road boundary risk potential field value of the center of mass;

[0031] The safety cost of the candidate path is calculated according to the safety cost of the vehicle angle and the safety cost of the center of mass.

[0032] In some embodiments, performing reverse path discovery from the target location to the starting location based on the comprehensive cost of the candidate path to obtain the target path includes:

[0033] According to the comprehensive cost of the candidate paths, each target path point is traversed to determine the optimal cost from the starting position to each target path point; the target path point includes any of the road surface sampling points and the target position within the second to the last sampling area, and the optimal cost is the minimum comprehensive cost from the starting position through several candidate paths to the target path point;

[0034] According to the optimal cost, determining the optimal path point corresponding to the target path point; the optimal path point is the last road surface sampling point passed by the path corresponding to the optimal cost before reaching the target path point;

[0035] According to the optimal path point corresponding to the target path point, the path from the target position to the starting position is reversely traced back to obtain the target path.

[0036] The present application also provides a path planning device, including:

[0037] The first module is used to obtain the vehicle's starting position, target position, vehicle geometry parameters and minimum ground clearance parameters, as well as pavement geometry characteristic parameters and pavement roughness characteristic parameters of the unpaved road;

[0038] The second module is used to perform discrete sampling on the unpaved road to obtain a plurality of road surface sampling points;

[0039] The third module is used to construct a road roughness risk potential field model and a road boundary risk potential field model according to the road surface geometric characteristic parameters and the road surface roughness characteristic parameters;

[0040] The fourth module is used to traverse each of the road sampling points to determine a target path from the starting position to the target position with the lowest comprehensive cost; the comprehensive cost is obtained by fitting a smoothness cost and a safety cost, the smoothness cost characterizes the curvature of the path, and the safety cost characterizes the safety of the path, and the safety cost is obtained by performing a safety risk assessment on the center of mass and vehicle angle of the vehicle based on the vehicle geometric parameters and the minimum ground clearance parameters using the road roughness risk potential field model and the road boundary risk potential field model.

[0041] An embodiment of the present application further provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned path planning method when executing the computer program.

[0042] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned path planning method is implemented.

[0043] The beneficial effects of the present application are as follows: discrete sampling is performed on unpaved roads to obtain multiple road surface sampling points, and a road roughness risk potential field model and a road boundary risk potential field model are constructed according to road surface geometric characteristic parameters and road surface roughness characteristic parameters. The road roughness risk potential field model and the road boundary risk potential field model are used in combination with vehicle geometric parameters and minimum ground clearance parameters to perform safety risk assessment on the center of mass and vehicle angle of the vehicle to evaluate the safety cost of the path passing through multiple road surface sampling points, and combined with the smoothness cost determined by the curvature of the path, a target path with the lowest comprehensive cost from the starting position to the target position is determined. By adopting the road roughness risk potential field model and road boundary risk potential field model constructed based on the pavement geometric characteristic parameters and the pavement roughness characteristic parameters, and combining the vehicle geometric parameters and the minimum ground clearance parameters, the safety risk assessment of the vehicle's center of mass and vehicle angle is carried out. The safety cost of the vehicle including the roughness risk factors and the boundary risk factors when driving on unpaved roads can be accurately determined. At the same time, combined with the smoothness cost determined by the curvature of the path, the comprehensive cost of each potential driving path is evaluated, so as to select the target path with the lowest comprehensive cost, which can improve the safety and comfort of the vehicle when driving on unpaved roads. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of the path planning method provided in an embodiment of the present application.

[0045] Figure 2 It is a flowchart of the specific method of step S104 provided in an embodiment of the present application.

[0046] Figure 3 It is a flowchart of the specific method of step S203 provided in an embodiment of the present application.

[0047] Figure 4 It is a flowchart of the specific method of step S205 provided in an embodiment of the present application.

[0048] Figure 5 It is a structural diagram of the path planning device provided in an embodiment of the present application.

[0049] Figure 6 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application.

[0050] Figure 7 It is a schematic diagram of road surface sampling points obtained by sampling provided in this embodiment.

[0051] Figure 8 It is a schematic diagram of obtaining centroid sampling points and vehicle corner sampling points by sampling provided in this embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown can be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second" and the like in the specification, claims and drawings are used to distinguish similar objects, and are not used to describe a specific order or sequence.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0055] See also Figure 1 , Figure 1 is a flow chart of a path planning method provided in an embodiment of the present application. In some embodiments of the present application, Figure 1 The method may specifically include but is not limited to steps S101 to S104. Figure 1 These four steps are introduced in detail.

[0056] Step S101, obtaining the starting position, target position, vehicle geometry parameters and minimum ground clearance parameters of the vehicle, and pavement geometry characteristic parameters and pavement roughness characteristic parameters of the unpaved road.

[0057] Vehicle geometric parameters may include vehicle length, height, width, wheelbase and track parameters. These parameters are important indicators for measuring vehicle size and structure. These parameters can be used to determine the relative distance between the center of mass of the vehicle and the four corners.

[0058] The minimum ground clearance parameter refers to the shortest distance between the lowest protruding part of the chassis and the horizontal ground when the vehicle is parked on the level ground and fully loaded. This parameter reflects the adaptability of the vehicle to different road conditions. For off-road driving, a larger minimum ground clearance means that the vehicle can more easily climb over a steep slope, safely drive into a river of a certain depth, and drive at high speed on a rugged mountain road. For urban driving, a larger minimum ground clearance means that the vehicle does not have to worry about scratches that may occur on a slope with a smaller curvature or when parking on the curb.

[0059] The vehicle's starting position and target position can be obtained from navigation software.

[0060] The pavement geometry characteristic parameters may include the road length and road width of the unpaved road and the peak coefficient, distribution factor and drop coefficient of the road boundary risk potential field value. The road length of the unpaved road may be determined by generating a corresponding driving path through the navigation software after the starting position and the target position are determined, and the road length of the unpaved road may be determined according to the generated formal path. The road width of the unpaved road and the peak coefficient, distribution factor and drop coefficient of the road boundary risk potential field value may be obtained by collecting the pavement surface geometry data of the unpaved road through the wheel tracker, and combining the data collection results and empirical values ​​to set.

[0061] Step S102: discrete sampling is performed on the unpaved road to obtain a plurality of road surface sampling points.

[0062] In step S102, for the unpaved road on which the vehicle is to travel, the continuous unpaved road space is divided into a set of finite road surface sampling points. Through a corresponding sampling method, the unpaved road is discretely sampled with the starting position and the target position as the boundary to obtain multiple discrete road surface sampling points. The multiple road surface sampling points obtained by sampling cover the unpaved road.

[0063] In a specific embodiment, step S102 specifically includes the following steps:

[0064] Taking the road surface edge, the starting position and the target position of the unpaved road as boundaries, continuous discrete sampling is performed in the road surface space of the unpaved road to obtain multiple road surface sampling points.

[0065] Among them, the road surface sampling points are distributed in multiple sampling areas, each sampling area is distributed with multiple road surface sampling points, and each sampling area is arranged along the length direction of the unpaved road.

[0066] Specifically, the road surface space of the unpaved road is divided into multiple sampling areas with the road surface edge, starting position and target position of the unpaved road as boundaries. Each sampling area is arranged along the road length direction of the unpaved road and covers the road surface space of the unpaved road. Continuous discrete sampling is performed in each sampling area to obtain multiple road surface sampling points distributed in each sampling area. The positions of the road surface sampling points in the road surface space of the unpaved road are represented by establishing a coordinate system.

[0067] More specifically, Figure 7As shown, there are multiple road surface roughness features on the unpaved road. The unpaved road can be bounded by the road edge, the starting position and the target position of the unpaved road, and a Cartesian coordinate system is established in the road surface space of the unpaved road (the origin of the Cartesian coordinate system is the initial position of the vehicle, the x-axis of the Cartesian coordinate system is parallel to the road length direction of the unpaved road, and the y-axis of the Cartesian coordinate system is parallel to the road width direction of the unpaved road), and multiple sampling areas are divided along the positive direction of the x-axis, and then continuous discrete sampling is performed in each sampling area, so as to obtain multiple road surface sampling points distributed in each sampling area. For example, first, continuous sampling is performed along the positive direction of the x-axis from the origin to obtain multiple road surface sampling points, and each road surface sampling point on the x-axis corresponds to a sampling area, and then continuous sampling is performed at the sampling point in the positive direction of the x-axis respectively along the positive direction of the y-axis and the negative direction of the y-axis to obtain multiple road surface sampling points, and the road surface sampling points in the same sampling area are arranged in a row, and the road surface sampling points in each sampling area are arranged in a matrix.

[0068] In some embodiments, the distance between two adjacent road surface sampling points is no greater than 0.1 m.

[0069] Step S103: constructing a road roughness risk potential field model and a road boundary risk potential field model according to the road surface geometric characteristic parameters and the road surface roughness characteristic parameters.

[0070] In step S103, based on the pavement geometric characteristic parameters and the pavement roughness characteristic parameters, an improved two-dimensional normal distribution function is used to calculate the road roughness risk potential field value and the road boundary risk potential field value on the unpaved road of the target sample point, and then the road roughness risk potential field value and the road boundary risk potential field value of all target sample points of the same type are used to construct the corresponding road roughness risk potential field model and road boundary risk potential field model.

[0071] Among them, the target sample point is a road surface sampling point, a centroid sampling point or a vehicle corner sampling point.

[0072] In a specific embodiment, the road roughness risk potential field model is:

[0073] ,

[0074] Where n=1,2,...,n obs ,k=1,2,...,k max , n obs is the total number of road roughness features, k max is the total number of target sample points, is the height of the nth road roughness feature at the kth target sample point, is the height of the kth target sample point after the roughness features of each road surface are superimposed, is the road roughness risk potential field value of the kth target sample point, A n is the feature identification parameter of the nth road roughness feature, , , and are the distribution factors of the nth road roughness feature along the positive direction of the x-axis, the negative direction of the x-axis, the positive direction of the y-axis, and the negative direction of the y-axis with the reference point as the origin, and are the x-axis coordinate and y-axis coordinate of the k-th target sample point, respectively. and are the x-axis coordinate and y-axis coordinate of the reference point of the nth road roughness feature, C n is the reduction coefficient of the nth road roughness feature, the x-axis is parallel to the length direction of the unpaved road, and the y-axis is parallel to the width direction of the unpaved road;

[0075] The road boundary risk potential field model is:

[0076] ,

[0077] Where m=1,2,...,n road , n road is the total number of road boundaries, is the road boundary risk potential field value of the mth road boundary at the kth target sample point, is the road boundary risk potential field value of the kth target sample point, is the peak coefficient of the risk potential field value of the mth road boundary, is the y-axis coordinate of the mth road boundary, is the distribution factor of the risk potential field value of the mth road boundary, is the decrease coefficient of the risk potential field value of the mth road boundary.

[0078] Step S104, traverse each road sampling point to determine a target path from the starting position to the target position with the lowest comprehensive cost.

[0079] Among them, the comprehensive cost is obtained by fitting the smoothness cost and the safety cost. The smoothness cost represents the curvature of the path, and the safety cost represents the safety of the path. The safety cost is based on the vehicle geometric parameters and the minimum ground clearance parameters, and the road roughness risk potential field model and the road boundary risk potential field model are used to perform safety risk assessment on the center of mass and vehicle angle of the vehicle.

[0080] In step S104, each road sampling point is traversed to calculate the comprehensive cost of the path from the starting position to the road sampling point, the comprehensive cost of the path from any road sampling point to another road sampling point, and the comprehensive cost of the path from the road sampling point to the target position, so as to determine the target path with the lowest comprehensive cost from the starting position to the target position.

[0081] See also Figure 2 In a specific embodiment, step S104 may specifically include but is not limited to steps S201 to S205. Figure 2 These five steps are introduced in detail.

[0082] Step S201, generating candidate paths based on the polynomial curve fitting principle.

[0083] The candidate paths include a path from the starting position to any road sampling point in the first sampling area, a path from any road sampling point in the previous sampling area to any road sampling point in the next sampling area, and a path from any road sampling point in the last sampling area to the target position.

[0084] In step S201, each road sampling point is traversed to determine multiple candidate paths, and a fifth-order polynomial curve is fitted through the two endpoints of the candidate path, and the specific path trajectory of the candidate path is generated using the fitted fifth-order polynomial curve. Among them, the endpoints of the candidate path are the starting position, the road sampling point or the target position. The fifth-order polynomial curve is fitted through the two endpoints of the candidate path, specifically, the coordinates of the two endpoints are substituted into the preset fifth-order polynomial and the first-order derivative expression and the second-order derivative expression of the fifth-order polynomial, and then the first-order derivative expression and the second-order derivative expression are set to 0, and the values ​​of each polynomial coefficient in the fifth-order polynomial are solved to obtain the fitted fifth-order polynomial curve, and then the candidate path is generated.

[0085] The fifth-order polynomial expression is:

[0086] ,

[0087] Among them, a0, a1, a2, a3, a4 and a5 are polynomial coefficients, x s is the x-axis coordinate of the starting point of the quintic polynomial curve, and (x,y(x)) is the coordinate of any point on the quintic polynomial curve;

[0088] Substituting the two endpoints of the candidate path into the first-order derivative expression and the second-order derivative expression, we get:

[0089] ,

[0090] Among them, (x s ,y(xs )) is the coordinate of the starting point of the candidate path, (x e ,y(x e )) is the coordinate of the end point of the candidate path, Δx=x e -x s ;

[0091] Let the first-order derivative expression and the second-order derivative expression be equal to 0, that is, let , , and are all equal to 0, so as to solve the values ​​of the polynomial coefficients in the quintic polynomial, obtain the fitted quintic polynomial curve, and then generate the corresponding candidate path.

[0092] Step S202 , performing a smoothness risk assessment on the candidate path to obtain a smoothness cost of the candidate path.

[0093] In a specific embodiment, step S202 specifically includes the following steps:

[0094] Continuously sampling the candidate paths to obtain multiple candidate path sampling points;

[0095] According to the curvature of the candidate path at each candidate path sampling point, the overall curvature of the candidate path is determined to obtain the smoothness cost of the candidate path.

[0096] Specifically, the calculation formula of the smoothness cost of the candidate path is:

[0097] ,

[0098] Where o=1,2,...,n candidate , n candidate is the total number of candidate path sampling points, is the smoothness cost of the candidate path, is the curvature of the candidate path at the oth candidate path sampling point.

[0099] Step S203, using the road roughness risk potential field model and the road boundary risk potential field model, the safety risk assessment is performed on the center of mass and vehicle angle of the vehicle on the candidate path to obtain the safety cost of the candidate path.

[0100] See also Figure 3 In a specific embodiment, step S203 may specifically include but is not limited to steps S301 to S304. Figure 3 These four steps are introduced in detail.

[0101] Step S301 : continuously sampling the positions of the centroid and the vehicle corner of the vehicle on the candidate path according to the vehicle geometric parameters, to obtain a plurality of centroid sampling points and a plurality of vehicle corner sampling points.

[0102] In step S301, the candidate paths are continuously sampled to obtain a plurality of candidate path sampling points, and the positions of the center of mass and the vehicle corners of the vehicle are determined when the vehicle is on the corresponding candidate path sampling points in combination with the vehicle geometric parameters, thereby obtaining a plurality of center of mass sampling points and a plurality of vehicle corner sampling points.

[0103] like Figure 8 As shown, the vehicle's outer contour is approximated as a rectangle. When the vehicle travels on the candidate path, the center of mass of the vehicle coincides with the candidate path, that is, when the vehicle travels to the sampling point of the candidate path, the coordinates of the center of mass sampling point are the same as the coordinates of the candidate path sampling point. Therefore, the coordinates of each center of mass sampling point and each vehicle corner sampling point can be determined by combining the vehicle's geometric parameters and the coordinates of the candidate path sampling points.

[0104] Step S302: input the centroid sampling point and the vehicle corner sampling point into the road roughness risk potential field model and the road boundary risk potential field model respectively, and obtain the road roughness risk potential field value and the road boundary risk potential field value of both the centroid and the vehicle corner.

[0105] Step S303, calculate the safety cost of the vehicle corner according to the road roughness risk potential field value and the road boundary risk potential field value of the vehicle corner, and calculate the safety cost of the center of mass according to the minimum ground clearance parameter and the road roughness risk potential field value and the road boundary risk potential field value of the center of mass.

[0106] The calculation formula of the safety cost of the vehicle angle is:

[0107] ,

[0108] in, The safety cost of the car corners, is the road roughness risk potential field value of the z-th vehicle angle, is the road boundary risk potential field value of the z-th vehicle corner.

[0109] The calculation formula of the safety cost of the centroid is:

[0110] ,

[0111] in, is the safety cost of the center of mass, is the road roughness risk potential field value of the center of mass, is the road boundary risk potential field value at the center of mass, is the height of the center of mass after the roughness features of each road surface are superimposed, It is the minimum ground clearance parameter.

[0112] Step S304, calculating the safety cost of the candidate path according to the safety cost of the vehicle corner and the safety cost of the center of mass.

[0113] The calculation formula of the safety cost of the candidate path is:

[0114] ,

[0115] in, is the safety cost of the candidate path.

[0116] Step S204 , performing weighted summation on the smoothness cost of the candidate path and the safety cost of the candidate path to obtain a comprehensive cost of the candidate path.

[0117] The calculation formula of the comprehensive cost of the candidate path is:

[0118] ,

[0119] in, is the comprehensive cost of the candidate path, and are all weight coefficients.

[0120] Step S205 , based on the comprehensive cost of the candidate paths, reverse path discovery is performed from the target location to the starting location to obtain the target path.

[0121] In a specific embodiment, step S205 specifically includes the following steps:

[0122] See also Figure 4 In a specific embodiment, step S205 may specifically include but is not limited to steps S401 to S403. Figure 4 These three steps are introduced in detail.

[0123] Step S401, based on the comprehensive cost of the candidate paths, traverse each target path point to determine the optimal cost from the starting position to each target path point.

[0124] The target path point includes any road sampling point and the target position within the second to the last sampling area, and the optimal cost is the minimum comprehensive cost from the starting position through several candidate paths to the target path point.

[0125] Step S402, determining the optimal path point corresponding to the target path point according to the optimal cost.

[0126] The optimal path point is the last road sampling point that the path corresponding to the optimal cost passes before reaching the target path point.

[0127] Step S403, based on the optimal path point corresponding to the target path point, reverse backtracking is performed from the target position to the starting position to obtain the target path.

[0128] In step S401 to step S403, according to the comprehensive cost of the candidate path, the comprehensive cost of reaching each road sampling point in the first sampling area from the starting position is first calculated, and then the comprehensive cost of reaching any road sampling point in the second sampling area after passing through the road sampling points in the first sampling area from the starting position is calculated, and the optimal path point corresponding to each road sampling point in the second sampling area is determined (located in the first sampling area), and so on, until the comprehensive cost of reaching any road sampling point in the last sampling area after passing through the road sampling points in several sampling areas from the starting position is calculated, and the optimal path point corresponding to each road sampling point in the last sampling area is determined (located in the second to last sampling area), and then the comprehensive cost of reaching the target position after passing through the road sampling points in several sampling areas from the starting position is calculated, and the optimal path point corresponding to the target position is determined (located in the last sampling area), and finally, according to the optimal path point corresponding to the target position, the optimal path point located in the second to last sampling area is selected according to the optimal path point, and so on, until the optimal path point located in the first sampling area is selected, thereby generating a target path passing through the starting position, each selected optimal path point and the target position.

[0129] Steps S201 to S205 are described below with a specific embodiment. First, an empty optimal cost matrix, an optimal path point number matrix, and a temporary cost matrix are established. Then, starting from the second sampling area, the comprehensive cost of the candidate path formed by each road surface sampling point in the current sampling area and each road surface sampling point in the previous sampling area is calculated, and the comprehensive cost of reaching each road surface sampling point in the current sampling area after passing through the previous sampling areas from the starting position (if there is no previous sampling area, it is reached directly), the calculated comprehensive cost is stored in the temporary cost matrix, the minimum value calculation is performed on the comprehensive cost in the temporary cost matrix, and the optimal cost is obtained. The optimal cost is stored in the optimal cost matrix, and the number of the optimal path point corresponding to the optimal cost is stored in the optimal path point number matrix, and so on, until the optimal cost from the starting position to the target position after passing through the previous sampling areas and the optimal path point corresponding to the optimal cost (i.e., the optimal path point corresponding to the target position) are determined. Finally, starting from the target position, the optimal path point is selected in the corresponding sampling area according to the elements in the optimal path point sequence matrix, so as to generate the target path. According to the elements in the optimal cost matrix, the comprehensive cost of the target path can be calculated.

[0130] See also Figure 5 The present application also provides a path planning device, which can implement the above path planning method, and the device includes:

[0131] The first module 501 is used to obtain the starting position, target position, vehicle geometry parameters and minimum ground clearance parameters of the vehicle, as well as pavement geometry characteristic parameters and pavement roughness characteristic parameters of the unpaved road;

[0132] The second module 502 is used to perform discrete sampling on the unpaved road to obtain a plurality of road surface sampling points;

[0133] The third module 503 is used to construct a road roughness risk potential field model and a road boundary risk potential field model according to the road surface geometric characteristic parameters and the road surface roughness characteristic parameters;

[0134] The fourth module 504 is used to traverse each road sampling point to determine the target path with the lowest comprehensive cost from the starting position to the target position; the comprehensive cost is obtained by fitting the smoothness cost and the safety cost, the smoothness cost represents the curvature of the path, the safety cost represents the safety of the path, and the safety cost is based on the vehicle geometric parameters and the minimum ground clearance parameters, and the road roughness risk potential field model and the road boundary risk potential field model are used to perform safety risk assessment on the center of mass and vehicle angle of the vehicle.

[0135] The specific implementation of the path planning device is basically the same as the specific implementation of the above-mentioned path planning method, and will not be repeated here.

[0136] Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment.

[0137] Refer to the following Figure 6 The electronic device 600 according to this embodiment of the present disclosure is described. Figure 6 The electronic device 600 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0138] like Figure 6 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0139] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the steps described in the above path planning method part of this specification according to various exemplary embodiments of the present disclosure.

[0140] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0141] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0142] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0143] The electronic device 600 may also communicate with one or more external devices 600' (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0144] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned path planning method is implemented.

[0145] The path planning method, device, equipment and storage medium provided in the embodiments of the present application perform discrete sampling on unpaved roads to obtain multiple road surface sampling points, and construct a road roughness risk potential field model and a road boundary risk potential field model according to road surface geometric characteristic parameters and road surface roughness characteristic parameters. The road roughness risk potential field model and the road boundary risk potential field model are used to perform safety risk assessment on the center of mass and vehicle angle of the vehicle in combination with vehicle geometric parameters and minimum ground clearance parameters to assess the safety cost of the path passing through multiple road surface sampling points, and determine a target path from a starting position to a target position with the lowest comprehensive cost in combination with a smoothness cost determined by the curvature of the path. By adopting the road roughness risk potential field model and road boundary risk potential field model constructed based on the pavement geometric characteristic parameters and the pavement roughness characteristic parameters, and combining the vehicle geometric parameters and the minimum ground clearance parameters, the safety risk assessment of the vehicle's center of mass and vehicle angle is carried out. The safety cost of the vehicle including the roughness risk factors and the boundary risk factors when driving on unpaved roads can be accurately determined. At the same time, combined with the smoothness cost determined by the curvature of the path, the comprehensive cost of each potential driving path is evaluated, so as to select the target path with the lowest comprehensive cost, which can improve the safety and comfort of the vehicle when driving on unpaved roads.

[0146] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above method according to the implementation of the present disclosure.

[0147] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0148] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program codes contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0149] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0150] Those skilled in the art will appreciate that the above modules can be distributed in the device according to the description of the embodiment, or can be changed accordingly and only used in one or more devices different from the embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

[0151] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0152] The exemplary embodiments of the present disclosure are specifically shown and described above. It should be understood that the present disclosure is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present disclosure is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended claims.

Claims

1. A path planning method, characterized in that: include: Obtaining the vehicle's starting position, target position, vehicle geometry parameters and minimum ground clearance parameters, as well as pavement geometry characteristic parameters and pavement roughness characteristic parameters of an unpaved road; Performing discrete sampling on the unpaved road to obtain a plurality of road surface sampling points; Constructing a road roughness risk potential field model and a road boundary risk potential field model according to the road surface geometric characteristic parameters and the road surface roughness characteristic parameters; Traversing each of the road sampling points, determining a target path with the lowest comprehensive cost from the starting position to the target position; the comprehensive cost is obtained by fitting a smoothness cost and a safety cost, the smoothness cost represents the curvature of the path, the safety cost represents the safety of the path, and the safety cost is obtained by performing a safety risk assessment on the center of mass and the vehicle angle of the vehicle based on the vehicle geometric parameters and the minimum ground clearance parameters by using the road roughness risk potential field model and the road boundary risk potential field model; The road roughness risk potential field model is: ， Where n=1,2,...,n obs ,k=1,2,...,k max , n obs is the total number of road roughness features, k max is the total number of target sample points, which are road surface sampling points, centroid sampling points or vehicle corner sampling points. is the height of the nth road roughness feature at the kth target sample point, is the height of the kth target sample point after the roughness features of each road surface are superimposed, is the road roughness risk potential field value of the kth target sample point, A n is the feature identification parameter of the nth road roughness feature, , , and are the distribution factors of the nth road roughness feature along the positive direction of the x-axis, the negative direction of the x-axis, the positive direction of the y-axis, and the negative direction of the y-axis with the reference point as the origin, and are the x-axis coordinate and y-axis coordinate of the k-th target sample point, respectively. and are the x-axis coordinate and y-axis coordinate of the reference point of the nth road roughness feature, C n is the reduction coefficient of the nth road roughness feature, the x-axis is parallel to the length direction of the unpaved road, and the y-axis is parallel to the width direction of the unpaved road; The road boundary risk potential field model is: ， Where m=1,2,...,n road , n road is the total number of road boundaries, is the road boundary risk potential field value of the mth road boundary at the kth target sample point, is the road boundary risk potential field value of the kth target sample point, is the peak coefficient of the risk potential field value of the mth road boundary, is the y-axis coordinate of the mth road boundary, is the distribution factor of the risk potential field value of the mth road boundary, is the decrease coefficient of the risk potential field value of the mth road boundary.

2. The path planning method according to claim 1, characterized in that: The discrete sampling of the unpaved road to obtain a plurality of road surface sampling points includes: Taking the road surface edge of the unpaved road, the starting position and the target position as boundaries, continuous discrete sampling is performed in the road surface space of the unpaved road to obtain a plurality of road surface sampling points; the road surface sampling points are distributed in a plurality of sampling areas, each of the sampling areas is distributed with a plurality of the road surface sampling points, and each of the sampling areas is arranged along the road length direction of the unpaved road.

3. The path planning method according to claim 1, characterized in that: The road surface sampling points are distributed in a plurality of sampling areas, each of the sampling areas is distributed with a plurality of the road surface sampling points, and each of the sampling areas is arranged along the length direction of the unpaved road. The traversing of each of the road surface sampling points to determine a target path with the lowest comprehensive cost from the starting position to the target position includes: Based on the polynomial curve fitting principle, a candidate path is generated; the candidate path includes a path from the starting position to any of the road surface sampling points in the first sampling area, a path from any of the road surface sampling points in the previous sampling area to any of the road surface sampling points in the next sampling area, and a path from any of the road surface sampling points in the last sampling area to the target position; Performing a smoothness risk assessment on the candidate path to obtain a smoothness cost of the candidate path; Using the road roughness risk potential field model and the road boundary risk potential field model, a safety risk assessment is performed on the center of mass and the vehicle angle of the vehicle on the candidate path to obtain the safety cost of the candidate path; Performing a weighted summation on the smoothness cost of the candidate path and the safety cost of the candidate path to obtain a comprehensive cost of the candidate path; According to the comprehensive cost of the candidate paths, reverse path discovery is performed from the target location to the starting location to obtain the target path.

4. The path planning method according to claim 3, characterized in that: The step of performing a smoothness risk assessment on the candidate path to obtain a smoothness cost of the candidate path includes: Continuously sampling the candidate path to obtain a plurality of candidate path sampling points; The overall curvature of the candidate path is determined according to the curvature of the candidate path at each sampling point of the candidate path to obtain the smoothness cost of the candidate path.

5. The path planning method according to claim 3, characterized in that: The adopting the road roughness risk potential field model and the road boundary risk potential field model to perform safety risk assessment on the center of mass and vehicle angle of the vehicle on the candidate path to obtain the safety cost of the candidate path includes: According to the vehicle geometric parameters, continuously sampling the positions of the center of mass and the vehicle corner of the vehicle on the candidate path to obtain a plurality of center of mass sampling points and a plurality of vehicle corner sampling points; Inputting the centroid sampling point and the vehicle corner sampling point into the road roughness risk potential field model and the road boundary risk potential field model respectively, to obtain the road roughness risk potential field value and the road boundary risk potential field value of the centroid and the vehicle corner; Calculating the safety cost of the vehicle corner according to the road roughness risk potential field value and the road boundary risk potential field value of the vehicle corner, and calculating the safety cost of the center of mass according to the minimum ground clearance parameter and the road roughness risk potential field value and the road boundary risk potential field value of the center of mass; The safety cost of the candidate path is calculated according to the safety cost of the vehicle angle and the safety cost of the center of mass.

6. The path planning method according to claim 3, characterized in that: The step of performing reverse path discovery from the target location to the starting location based on the comprehensive cost of the candidate path to obtain the target path includes: According to the comprehensive cost of the candidate paths, each target path point is traversed to determine the optimal cost from the starting position to each target path point; the target path point includes any of the road surface sampling points and the target position within the second to the last sampling area, and the optimal cost is the minimum comprehensive cost from the starting position through several candidate paths to the target path point; According to the optimal cost, determining the optimal path point corresponding to the target path point; the optimal path point is the last road surface sampling point passed by the path corresponding to the optimal cost before reaching the target path point; According to the optimal path point corresponding to the target path point, the path from the target position to the starting position is reversely traced back to obtain the target path.

7. A path planning device, characterized in that: include: The first module is used to obtain the vehicle's starting position, target position, vehicle geometry parameters and minimum ground clearance parameters, as well as pavement geometry characteristic parameters and pavement roughness characteristic parameters of the unpaved road; The second module is used to perform discrete sampling on the unpaved road to obtain a plurality of road surface sampling points; The third module is used to construct a road roughness risk potential field model and a road boundary risk potential field model according to the road surface geometric characteristic parameters and the road surface roughness characteristic parameters; The fourth module is used to traverse each of the road sampling points to determine a target path with the lowest comprehensive cost from the starting position to the target position; the comprehensive cost is obtained by fitting a smoothness cost and a safety cost, the smoothness cost represents the curvature of the path, the safety cost represents the safety of the path, and the safety cost is obtained by performing a safety risk assessment on the center of mass and the vehicle angle of the vehicle based on the vehicle geometric parameters and the minimum ground clearance parameters by using the road roughness risk potential field model and the road boundary risk potential field model; The road roughness risk potential field model is: ， Where n=1,2,...,n obs ,k=1,2,...,k max , n obs is the total number of road roughness features, k max is the total number of target sample points, which are road surface sampling points, centroid sampling points or vehicle corner sampling points. is the height of the nth road roughness feature at the kth target sample point, is the height of the kth target sample point after the roughness features of each road surface are superimposed, is the road roughness risk potential field value of the kth target sample point, A n is the feature identification parameter of the nth road roughness feature, , , and are the distribution factors of the nth road roughness feature along the positive direction of the x-axis, the negative direction of the x-axis, the positive direction of the y-axis, and the negative direction of the y-axis with the reference point as the origin, and are the x-axis coordinate and y-axis coordinate of the k-th target sample point, respectively. and are the x-axis coordinate and y-axis coordinate of the reference point of the nth road roughness feature, C n is the reduction coefficient of the nth road roughness feature, the x-axis is parallel to the length direction of the unpaved road, and the y-axis is parallel to the width direction of the unpaved road; The road boundary risk potential field model is: ， Where m=1,2,...,n road , n road is the total number of road boundaries, is the road boundary risk potential field value of the mth road boundary at the kth target sample point, is the road boundary risk potential field value of the kth target sample point, is the peak coefficient of the risk potential field value of the mth road boundary, is the y-axis coordinate of the mth road boundary, is the distribution factor of the risk potential field value of the mth road boundary, is the decrease coefficient of the risk potential field value of the mth road boundary.

8. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the path planning method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the path planning method according to any one of claims 1 to 6 is implemented.

Images